https://daiviet.dev Hourly AI intelligence, model releases, benchmark updates, global AI deals, verified promo codes and free quotas. en-us Tue, 03 Nov 2026 09:55:45 GMT https://daiviet.dev/ai-news/paper-simit-self-improving-vision-language-models-via-imagination-at-test-time https://daiviet.dev/ai-news/paper-simit-self-improving-vision-language-models-via-imagination-at-test-time We introduce SIMIT, a test-time self-improvement framework in which a vision-language model creates its own query-specific training data before answering an unlabeled test query. Our goal is to improve performance on a given target test set without annotations or external models. To pursue this goal, some test-time methods improve answers through longer reasoning or repeated sampling but leave the model unchanged. Others update the model using rewards based on majority agreement among multiple candidate answers or the model's own judgments of correctness, but such rewards can reinforce existing mistakes. SIMIT instead imagines similar problems whose solutions it controls: a model need not correctly solve the target query to construct useful practice examples. It synthesizes diverse (question, answer, image) triplets by specifying each answer before realizing its image. To support diverse multimodal tasks, SIMIT combines native image generation with an extensible skill library for structured visuals, including documents, charts, and diagrams. Within this pipeline, multi-stage verification checks that images support their assigned answers, while difficulty filtering retains informative examples. Adaptive budgeting further targets this practice by allocating more samples to queries the model is less confident in answering. The resulting data can improve the model in-context (SIMIT-ICL) or in-weight (SIMIT-FT). Across 17 diverse benchmarks, SIMIT outperforms existing self-improvement methods. Its best configuration achieves a +7.20% mean relative gain over BAGEL-7B, while training-free SIMIT-ICL achieves +6.98%. Ecosystem Updates Tue, 03 Nov 2026 09:46:58 GMT https://daiviet.dev/ai-news/paper-can-large-language-model-agents-learn-by-watching-tutorial-videos https://daiviet.dev/ai-news/paper-can-large-language-model-agents-learn-by-watching-tutorial-videos Humans continuously acquire knowledge from carefully crafted materials such as books and tutorial videos, carrying that understanding into future tasks. Millions of such instructional videos are uploaded online every day, yet LLM agents remain unable to exploit this ever-expanding wealth of human teaching. Their capabilities are frozen after training, while parameter updates at scale remain prohibitively expensive. This raises the central question: can LLM agents learn from this vast instructional resource without parameter updates? We introduce Tutorial Agentic Learning (TAL), a nonparametric continual-learning paradigm that consolidates tutorial videos into a persistent, structured tutorialbook memory through a two-stage adversarial process that harvests hard, video-grounded questions and uses them to refine the memory. At inference time, TAL retrieves through a Table-of-Contents (TOC) tree, tying retrieval directly to the model's reasoning rather than to embedding similarity. To study this setting, we introduce VidLearn, a multimodal QA benchmark built from 72 chess tutorial videos spanning 12 openings. On VidLearn, TAL outperforms all evaluated baselines and improves monotonically as more videos are consumed, achieving up to 113% and 91% relative gains over the corresponding vanilla MLLMs on the training and test splits, respectively. In actual gameplay, TAL reaches a stronger opening-phase position than its vanilla counterpart in 69% of head-to-head games. Evaluation in a second domain further demonstrates the generality of TAL. Together, these results highlight instructional videos as a scalable resource for parameter-update-free agent continual learning. Ecosystem Updates Tue, 03 Nov 2026 09:46:58 GMT https://daiviet.dev/ai-news/paper-when-morphs-look-better-face-image-quality-as-a-training-free-signal-for-morphing-attack-detection https://daiviet.dev/ai-news/paper-when-morphs-look-better-face-image-quality-as-a-training-free-signal-for-morphing-attack-detection Face image quality assessment (FIQA) estimates the utility of a face image for automated face recognition and has been proposed as a morphing attack detection (MAD) signal that requires no morph-specific training. We evaluate 17 FIQA methods from all current FIQA categories on 20 morphing attack sets from two datasets, FRLL and FEI, including five diffusion-based attack sets. Each quality score is used directly as a MAD decision score. Unlike prior work, which inverted a quality measure when this lowered its error, we fix the score direction of each method in advance from its definition, so that cases in which morphs receive higher quality than bona fide samples remain visible. On FRLL, DifFIQA(R) achieves a mean D-EER of 11.42%, and together with CLIB-FIQA and eDifFIQA(L) clearly outperforms all other FIQA methods. A strong separation of bona fide and morph scores does not imply good detection performance: on the diffusion-based attacks, up to 11 of 17 methods assign higher quality to morphs than to bona fide samples, and the largest reversed separation in the study coincides with the worst detection result of the study. Performance also depends strongly on the attack: GraFIQs(L), the best detector of DCMorph and Arc2Morph on FRLL, performs poorly on the landmark-based and GAN-based attacks. On FEI, the lowest mean D-EER is 39.75%, and a threshold set on the bona fide data of one dataset does not transfer to the other. Ecosystem Updates Tue, 03 Nov 2026 09:32:12 GMT https://daiviet.dev/ai-news/paper-can-coding-agents-sustain-continual-evolution-without-forgetting https://daiviet.dev/ai-news/paper-can-coding-agents-sustain-continual-evolution-without-forgetting Recently, harness self-evolution has emerged as an important paradigm for improving agent performance. Prior studies show that evolving the agent harness can effectively enhance agent capabilities without modifying the foundation model's parameters. We find that existing approaches largely study agent evolution on a single task. In practice, coding agents may need to handle multiple task types over time. Whether an agent harness can continuously evolve across multiple tasks without suffering from catastrophic forgetting remains an important open question. In this paper, we investigate this open question through a comprehensive empirical study of continual harness self-evolution. We organize three software engineering task datasets into six different evolution directions and apply two representative harness evolution methods to perform continual evolution along these directions. Our experimental results show that evolution on a subsequent dataset can substantially undermine the performance on previously seen datasets. For example, with DeepSeek-V4-Flash-0731, Meta-Harness improves its performance on SWE-Bench to 94.0% after evolution. However, after further evolution on FeatureBench, its performance on SWE-Bench drops to 32.0% by the fifth round, corresponding to a 66% relative decrease. Finally, based on our experimental findings, we identify several insights, providing directions for the continual self-evolution of agent harnesses. Code is available at https://github.com/THU-Agent/continual-harness-evolution. Ecosystem Updates Tue, 03 Nov 2026 09:16:59 GMT https://daiviet.dev/ai-news/paper-worldflow-joint-video-and-3d-motion-prediction-via-large-scale-pretraining https://daiviet.dev/ai-news/paper-worldflow-joint-video-and-3d-motion-prediction-via-large-scale-pretraining Predicting future physical states stands as a central challenge in embodied intelligence. Existing video world models leave 3D dynamics implicit, action-based formulations remain tied to specific robot configurations, and 3D motion prediction models use flow-only supervision, providing a limited learning signal for physical dynamics. To circumvent these limitations, we introduce , a generative world model that jointly predicts future video and query-based 3D trajectories. By parameterizing 3D motion as continuous displacement tokens aligned with the video grid, a unified Mixture-of-Transformers (MoT) backbone jointly denoises both modalities under a rectified-flow objective. This formulation couples explicit geometric dynamics with visual evolution, effectively unlocking the physical commonsense embedded within pretrained video models. To empirically scale and validate this unified architecture, we train on a heterogeneous mixture of 1.44 million object-level samples spanning simulated and real-world domains. We further introduce WorldFlowBench, comprising 1,678 evaluation samples from 11 data sources across simulated and real-world interactions, including spatial reasoning tasks. Across all three evaluation sets, WorldFlow achieves the lowest average displacement error (ADE) and final displacement error (FDE) among the evaluated learning-based methods. Notably, on the challenging SpatialCog set, WorldFlow achieves an ADE of 0.060 m, a 54.2\% reduction compared with the strongest external baseline. It also reduces ADE and FDE by 55.9\% and 68.5\%, respectively, compared with its flow-only variant. Project page: https://worldflow-rbs.github.io/. Ecosystem Updates Tue, 03 Nov 2026 09:16:59 GMT https://daiviet.dev/ai-news/paper-lab2sim-turning-real-world-experiment-videos-into-interactive-virtual-experiments https://daiviet.dev/ai-news/paper-lab2sim-turning-real-world-experiment-videos-into-interactive-virtual-experiments Science experiment videos demonstrate how experiments are performed, but offer no direct interaction for learners. Turning them into virtual experiments requires not only reproducing the observed apparatus and state changes, but also enforcing the preconditions governing each operation. We introduce Lab2Sim, a benchmark of 218 science experiment videos with evidence-grounded specifications and 11,881 rubric items. To address this task, we propose EduVideo2Code, which extracts experimental procedures hierarchically, encodes them as explicit state machines to guide code generation, and refines the resulting pages through execution-based verification. Experiments show that existing multimodal models readily generate runnable pages but struggle to faithfully reconstruct experimental apparatus. EduVideo2Code consistently improves all four evaluation dimensions across two backbone models, with apparatus fidelity gains of 24.15 points. Ecosystem Updates Tue, 03 Nov 2026 08:46:58 GMT https://daiviet.dev/ai-news/paper-flamia-flash-microscaling-attention-for-fast-and-causally-safe-training-on-blackwell https://daiviet.dev/ai-news/paper-flamia-flash-microscaling-attention-for-fast-and-causally-safe-training-on-blackwell Attention remains a substantial computational cost in Transformer training, particularly at long context lengths. NVIDIA Blackwell GPUs provide high-throughput low-precision matrix multiplication, but exploiting it in attention requires addressing quantization overhead, causal information leakage through shared scales, and numerical inconsistencies between the forward and backward passes. We present FLAMIA, a family of attention kernels for Blackwell with MXFP8 and mixed NVFP4/FP8 training paths. Our design combines token-block scaling that reuses quantized operands across matrix orientations, targeted safeguards against scale-induced leakage, and consistent forward and backward computations. Fused quantization and architecture-specific kernel optimizations reduce overhead, while document-local scaling and workload-aware scheduling support variable-length documents directly in packed layouts without repacking. Across various causal packed-document workloads, the MXFP8 path accelerates the combined forward and backward attention call, including quantization, by factors of 1.10--1.40times on B200 and 1.06--1.42times on B300 relative to the fastest evaluated baseline for each workload. We validate training stability and quality preservation on pretraining Llama-style models. These results show how jointly designing quantization, training numerics, and document scheduling translates low-bit hardware throughput into practical attention acceleration. Ecosystem Updates Tue, 03 Nov 2026 08:46:58 GMT https://daiviet.dev/ai-news/da-decoupling-description-and-assessment-enables-vlms-as-zero-shot-robotic-reward-models https://daiviet.dev/ai-news/da-decoupling-description-and-assessment-enables-vlms-as-zero-shot-robotic-reward-models Vision-Language Models (VLMs) hold promise for zero-shot video task-progress estimation in robot learning, yet existing frameworks frequently suffer from confirmation bias, hallucinating progress in failed executions due to implicit success assumptions or relative temporal ranking designs. Naive prompting of frontier models collapses into a binary success detector that fails to capture nuanced, no Ecosystem Updates Tue, 03 Nov 2026 08:16:59 GMT https://daiviet.dev/ai-news/paper-measuring-ai-agents-as-teammates-with-collaborative-intelligence https://daiviet.dev/ai-news/paper-measuring-ai-agents-as-teammates-with-collaborative-intelligence Progress in AI is often measured by what a single model can do on its own. Yet teams of AI agents are starting to make breakthroughs and discoveries in science, medicine, mathematics and software engineering. As AI begins to work in teams of agents and people, the ability to collaborate becomes a core part of their intelligence. Research on human teams has measured this ability for decades. Inspired by this, we introduce the Collaborative Intelligence Benchmark, which measures how well an AI agent works as a teammate. It contains 240 tasks across 8 dimensions of teamwork, from refusing an unsafe shortcut to checking the work that a weaker model leaves behind. Each task comes from a real record or an existing benchmark, from aviation accident reports and clinical cases to coding tasks and negotiations, and has a programmatically verifiable outcome. To isolate teamwork from individual capability, models are scored only on tasks that they can solve by themselves when they have full information. We evaluate 18 closed- and open-weight models and find that every model, across sizes and families, has clear weaknesses as a teammate, with the best model scoring only 82.2 out of 100. Frontier models almost always refuse unsafe shortcuts and report misconduct, yet they cave under interpersonal pressure, reaching the best overall deal in only 14% of conflicts, and their pass rate drops from 97% to 81% when they take over a task in which a weaker model has cheated. Crucially, general capability does not guarantee good teamwork, as models with nearly the same capability score differ by up to 11 points as teammates. The benchmark includes 160 public tasks with code and data, along with 80 held-out tasks for evaluation. As AI agents increasingly work alongside other agents and people, the ability to collaborate effectively is becoming a crucial capability to measure and develop. Ecosystem Updates Tue, 03 Nov 2026 08:16:58 GMT https://daiviet.dev/ai-news/pixel-a-co-designed-full-stack-robot-system-for-learning-general-purpose-mobile-manipulation https://daiviet.dev/ai-news/pixel-a-co-designed-full-stack-robot-system-for-learning-general-purpose-mobile-manipulation General-purpose mobile manipulation requires a combination of capable robot hardware, scalable demonstration collection, expressive whole-body control, and effective policy learning. Yet these components are often developed independently, creating mismatches that limit the capabilities of the complete system. We present Pixel, a co-designed full-stack system for learning general-purpose mobile man Ecosystem Updates Tue, 03 Nov 2026 08:02:13 GMT https://daiviet.dev/ai-news/webharbor-docking-real-websites-for-evolving-gui-agent-environments https://daiviet.dev/ai-news/webharbor-docking-real-websites-for-evolving-gui-agent-environments GUI web agents require realistic and interactive environments that remain stable during both evaluation and training. Live website evaluation suffers from changing content, access restrictions, and limited coverage of authenticated workflows, while existing synthetic environments for training often lack functional depth and visual fidelity. We propose WebHarbor, a suite of 153 executable and docke Ecosystem Updates Tue, 03 Nov 2026 08:02:13 GMT https://daiviet.dev/ai-news/paper-reviso-not-all-visual-evidence-deserves-equal-attention-in-video-captioning https://daiviet.dev/ai-news/paper-reviso-not-all-visual-evidence-deserves-equal-attention-in-video-captioning Multimodal large language models (MLLMs) can generate detailed video captions, yet they may overemphasize minor details while overlooking essential context and key events. We argue that not all visual evidence deserves equal attention, as the importance of visual information depends on the content of each video. Motivated by this observation, we propose Reviso, an agentic video captioning framework that learns what to observe and how to gather relevant visual evidence. From a low-frame-rate global preview, Reviso constructs a hierarchical Context--Focus--Points (CFP) observation plan that identifies the video context, prioritizes key aspects, and defines concrete observation targets and corresponding tools. Guided by this plan, Reviso performs goal-directed active perception by selectively revisiting temporal segments and combining tools for fine-grained inspection. It interprets the acquired evidence, updates its plan as needed, and integrates global and local information to generate the final caption. To learn this observation strategy, we develop a verification-guided pipeline that constructs high-quality training trajectories through factual verification and teacher-guided refinement. We further train Reviso using Group Relative Policy Optimization (GRPO), incorporating a key-fact reward for caption quality, a Plan Alignment Reward (PAR) for identifying important observation targets, and an Unproductive Tool-Call Penalty (UTCP) that adjusts observation-cost penalties based on caption quality. Experiments across four video captioning benchmarks show that Reviso outperforms the evaluated open-source baselines, while its generated captions better support downstream video question answering. These findings highlight the effectiveness and potential of priority-guided active observation for video captioning. Ecosystem Updates Tue, 03 Nov 2026 08:02:13 GMT https://daiviet.dev/ai-news/pixel-umi-learning-environment-aware-whole-body-manipulation-from-sensorized-human-demonstrations https://daiviet.dev/ai-news/pixel-umi-learning-environment-aware-whole-body-manipulation-from-sensorized-human-demonstrations Sensorized human demonstrations offer scalable data for mobile manipulation, but embodiment differences complicate policy learning. We present Pixel-UMI, a pipeline for learning environment-aware whole-body policies from human data. We first introduce Environment-Aware Retargeting (EAR), which combines reconstructed scene geometry with demonstrated head and gripper trajectories to determine robot Ecosystem Updates Tue, 03 Nov 2026 08:02:13 GMT https://daiviet.dev/ai-news/paper-coworkosscaling-agent-coworkers-for-real-world-automation https://daiviet.dev/ai-news/paper-coworkosscaling-agent-coworkers-for-real-world-automation Rapid advances in cowork agents are shifting human-AI collaboration toward real-world automation, delivering software, designs, and other artifacts. However, such productivity work demands both high-quality delivery on complex productivity tasks and continued monitoring and decision-making over long horizons, a combination that remains an open challenge. We introduce CoworkOS, a general-purpose harness for long-horizon work that separates task strategy from execution management: the model decides actions, delegation, and acceptance, while the runtime maintains state and feedback. Its three-layer architecture enables direct execution or delegation to Subagents, synchronously or asynchronously, under stable responsibilities. Through a shared application layer, humans and agents inspect and revise the same evolving documents, presentations, CAD models, and Blender scenes, so human-in-the-loop participation can enter both through conversation and through direct modification of the work itself. To sustain continuity across agents and sessions, CoworkOS further introduces hierarchical workspaces and persistent semantic memory, so working files, key decisions, and long-running Job logs remain shareable, reusable, and resumable after interruption. Across 12 benchmarks and 6 categories of real-world applications, CoworkOS proves highly competitive with frontier agent applications such as Codex and DeepSeek Harness. As a sustained-work case study, CoworkOS uses GLM-5.3 as its backbone to conduct RSI-driven automated post-training on Qwen3.6-35B-A3B. Over five rounds, the model's average score across eight benchmarks rose from 33.19 to 42.95 (+9.76). Looking ahead, we believe CoworkOS opens a meaningful path toward general cowork-agent intelligence. Ecosystem Updates Tue, 03 Nov 2026 08:02:13 GMT https://daiviet.dev/ai-news/from-natural-language-to-exact-cover-a-neuro-symbolic-approach-to-zebra-puzzles https://daiviet.dev/ai-news/from-natural-language-to-exact-cover-a-neuro-symbolic-approach-to-zebra-puzzles Chain-of-Thought (CoT) generation has substantially improved the performance of Large Language Models (LLMs) on complex reasoning tasks, including code generation, data analysis, and exam-style question answering. Despite these advances, purely neural LLMs continue to struggle with elementary logical reasoning problems and lack the determinism, soundness, and reliability characteristic of symbolic Ecosystem Updates Tue, 03 Nov 2026 08:02:13 GMT https://daiviet.dev/ai-news/paper-byod-build-your-own-dlm-efficient-autoregressive-to-diffusion-language-model-conversion https://daiviet.dev/ai-news/paper-byod-build-your-own-dlm-efficient-autoregressive-to-diffusion-language-model-conversion Unlike autoregressive (AR) models, diffusion language models (DLMs) permit parallel token updates, flexible generation, and bidirectional attention, but leading systems rely on costly pretraining or full-model fine-tuning. We present Build Your Own DLM (BYOD), a generalizable LoRA-only recipe for parameter-efficient AR-to-DLM conversion. Without architecture-specific tuning, BYOD induces diffusion generation in Gemma 2 9B, Llama 3.1 8B, Qwen2.5 7B, and Ministral 8B; to our knowledge, this is the first reported AR-to-DLM conversion of a Mistral model. The adapters comprise 4.1-5.8% of final parameters while every base-model parameter remains frozen; each 25,000-iteration conversion needs at most 102.4M tokens, processed in 3.1-4.0 hours on one Google Colab GPU. All four models generate from fully masked sequences, use bidirectional context in a controlled attention test, and retain substantial parent-model knowledge. BYOD-Gemma is the strongest BYOD conversion on our nine-task evaluation, reaching 50.6% average accuracy compared with 51.9% for LLaDA 8B Instruct in the same harness. Open-generation quality at low network function evaluation (NFE) budgets remains the principal limitation: BYOD perplexity is 8.3-11.1 versus 4.1 for LLaDA and 2.2-3.0 for the AR parents when generating 128 tokens in 64 steps. To enable further experimentation and inspection, we provide a standalone training and evaluation implementation and interactive demos for all four conversions. BYOD thus provides a practical route for extending diffusion generation to other existing model families while identifying the gap that efficient conversion must next close. Ecosystem Updates Tue, 03 Nov 2026 07:47:13 GMT https://daiviet.dev/ai-news/apple-watchs-ai-features-for-rewinding-and-recapping-conversations-begin-beta-testing https://daiviet.dev/ai-news/apple-watchs-ai-features-for-rewinding-and-recapping-conversations-begin-beta-testing Now in beta: Apple's new Audio Intelligence features can help you remember what someone said or take notes on conversations. Ecosystem Updates Tue, 03 Nov 2026 07:32:05 GMT https://daiviet.dev/ai-news/paper-library-of-layers-lol-adaptively-ordering-transformer-layers-at-runtime https://daiviet.dev/ai-news/paper-library-of-layers-lol-adaptively-ordering-transformer-layers-at-runtime Computer programmers chain together the same reusable computational primitives, for example, conditional statements or loops, but in different orders to implement different algorithms. In contrast, existing language model architectures always execute their layers in the same order. We introduce Library of Layers (LoL), an architecture that dynamically orders its layers during inference to solve the problem at hand. LoL has a single hyperparameter, the size of its global library of transformer blocks, that allows it to transition seamlessly between parameter reuse and sparsity, generalizing the parameter-efficiency and FLOPs-efficiency tradeoffs of dense, depth-recurrent, and mixture of experts architectures in one unified family. We show that LoL achieves competitive performance with all three above baselines when pretrained on text data. On synthetic sudoku and maze data, we observe that the model employs distinct layer orderings to implement different solution strategies, and we can intervene on routing to force a model to apply a specific solution strategy to a problem instance. In a multilingual natural language setting, we find that LoL chooses different layer order patterns based on language and script. Similarly, we train LoL on safety data and fit probes to its router outputs, finding that these probes distinguish safe from unsafe text with high AUROC. LoL provides a path toward a future in which models dynamically compose their own computational graph, enabling more efficient and controllable reasoning. Ecosystem Updates Tue, 03 Nov 2026 07:31:59 GMT https://daiviet.dev/ai-news/cities-worldwide-build-and-scale-ai-services-with-nvidia-physical-and-agentic-ai https://daiviet.dev/ai-news/cities-worldwide-build-and-scale-ai-services-with-nvidia-physical-and-agentic-ai Cities generate enormous amounts of data from cameras, sensors and operational systems, but turning it into useful action — for planning, maintenance and public services — remains a challenge. Physical and agentic AI offer new ways to close that gap, from digital twins for infrastructure planning to vision and service agents, while keeping local governments […] Ecosystem Updates Tue, 03 Nov 2026 07:17:03 GMT https://daiviet.dev/ai-news/transformers-model-integration-contracts https://daiviet.dev/ai-news/transformers-model-integration-contracts Official developer intelligence from Hugging Face Blog. Ecosystem Updates Tue, 03 Nov 2026 07:17:03 GMT https://daiviet.dev/ai-news/complianceatlas-a-taxonomy-driven-agentic-ai-framework-for-automated-ai-act-gap-analysis-and-remediation https://daiviet.dev/ai-news/complianceatlas-a-taxonomy-driven-agentic-ai-framework-for-automated-ai-act-gap-analysis-and-remediation Assessing regulatory compliance for high-risk AI systems requires systematic identification of technical gaps such as missing controls, in- adequate processes, or shallow evaluation of practices. Compliance officers typically admin- ister structured questionnaires collecting evi- dence of current practices, where organizations respond with descriptions of their existing pro- cesses, technical capa Ecosystem Updates Tue, 03 Nov 2026 07:16:59 GMT https://daiviet.dev/ai-news/cua-master-scaling-computer-use-agents-through-open-world-recursive-improvements https://daiviet.dev/ai-news/cua-master-scaling-computer-use-agents-through-open-world-recursive-improvements Despite recent advances in CUAs, their development remains constrained by the limited diversity, controllability, and reliability of interaction data. Moreover, conventional optimization pipelines lack iterative feedback, while existing recursive improvement approaches often rely on self-generated experiences, limiting ability expansion and yielding diminishing returns. To address these challenges Ecosystem Updates Tue, 03 Nov 2026 07:02:03 GMT https://daiviet.dev/ai-news/paper-crossswe-benchmarking-cross-repository-joint-development-for-coding-agents https://daiviet.dev/ai-news/paper-crossswe-benchmarking-cross-repository-joint-development-for-coding-agents As coding agents achieve increasingly high success rates on software engineering benchmarks, recent efforts have sought to increase task complexity through longer horizons and more extensive code modifications. However, real-world software development often spans multiple interdependent repositories, introducing additional challenges in dependency reasoning, change propagation, and interface consistency. Rather than further increasing complexity within individual repositories, we introduce CrossSWE, a benchmark for cross-repository joint development comprising 171 real-world instances spanning 165 repositories, 20 technical domains, and 13 programming languages. CrossSWE verifies the necessity of coordinated changes by testing whether partial repository modifications are insufficient to achieve the intended behavior. Our evaluation of five LLMs reveals substantial challenges, with the strongest model, GPT-6.1 Sol, achieving only 58.48% Pass@1. Furthermore, cross-repository inconsistencies emerge as the most prevalent failure mode (44.2%), highlighting the difficulty of maintaining consistency across interdependent repositories. Ecosystem Updates Tue, 03 Nov 2026 07:02:03 GMT https://daiviet.dev/ai-news/meet-students-where-they-are-student-prefix-teacher-adaptation-for-on-policy-distillation https://daiviet.dev/ai-news/meet-students-where-they-are-student-prefix-teacher-adaptation-for-on-policy-distillation On-policy distillation (OPD) mitigates the student's exposure bias by optimizing on student-generated trajectories. However, student-generated prefixes may contain reasoning errors or follow patterns unfamiliar to the teacher, undermining the reliability of its token-level supervision. This degradation becomes more pronounced as prefixes grow longer. To address this teacher-side distribution misma Ecosystem Updates Tue, 03 Nov 2026 07:02:03 GMT https://daiviet.dev/ai-news/visual-to-executable-procedural-reconstruction-of-buildings https://daiviet.dev/ai-news/visual-to-executable-procedural-reconstruction-of-buildings Procedural modeling offers compact, editable, and reusable representations for architectural content, but building such models still depends heavily on manually authored grammars. We study image-based procedural building reconstruction from in-the-wild images, with the goal of recovering an executable procedural description that can be instantiated as an editable 3D building asset. Because a singl Ecosystem Updates Tue, 03 Nov 2026 07:02:03 GMT https://daiviet.dev/ai-news/depthgraft-structural-regularization-through-hierarchical-cross-layer-kv-reconstruction https://daiviet.dev/ai-news/depthgraft-structural-regularization-through-hierarchical-cross-layer-kv-reconstruction Scaling depth is a key route to stronger large language models, but Pre-LN architectures often suffer from depth-wise information dilution, limiting the effective use of deep layers. While cross-layer connectivity has proven effective at mitigating this problem, existing designs usually introduce additional computation or memory access. We revisit cross-layer KV sharing as an efficient form of suc Ecosystem Updates Tue, 03 Nov 2026 07:02:03 GMT https://daiviet.dev/ai-news/paper-cua-master-scaling-computer-use-agents-through-open-world-recursive-improvements https://daiviet.dev/ai-news/paper-cua-master-scaling-computer-use-agents-through-open-world-recursive-improvements Despite recent advances in CUAs, their development remains constrained by the limited diversity, controllability, and reliability of interaction data. Moreover, conventional optimization pipelines lack iterative feedback, while existing recursive improvement approaches often rely on self-generated experiences, limiting ability expansion and yielding diminishing returns. To address these challenges, we introduce CUA-Master, a nested double-loop recursive improvement framework. At the system level, an outer world-data-model flywheel continuously incorporates open-world corpus and leverages evolving model weaknesses to guide subsequent data construction and optimization iterations. At the data level, an inner flywheel couples open-world seeding and autocatalytic propagation. The former mines authentic workflows as seed tasks from instructional videos, and employs visual-semantic dual-path trajectory reconstruction; The latter transforms these seeds into reusable primitives for controllable synthesis of diverse, complex, and verifiable tasks. To enable efficient and reliable trajectory collection, we further introduce a feedback-guided snapshot-rollback retry mechanism in various real environments. Extensive experiments demonstrate that CUA-Master-27B achieves competitive performance across GUI-only and GUI-CLI hybrid benchmarks, scoring 80.2 on OSWorld Verified, 36.9 on OSWorld 2.0, 43.9 on WeaveBench, and 25.0 on Agents' Last Exam. Our framework also substantially improves the quality and efficiency of data synthesis, and exhibits continuous gains across recursive iterations. Ecosystem Updates Tue, 03 Nov 2026 06:32:02 GMT https://daiviet.dev/ai-news/paper-avatar-intelligence-amplifying-human-agency-through-persistent-personal-agents https://daiviet.dev/ai-news/paper-avatar-intelligence-amplifying-human-agency-through-persistent-personal-agents Personal AI agents are increasingly capable of handling long-horizon tasks across applications, yet users often need to invest substantial effort in specifying goals, resolving ambiguity, and verifying outcomes. We argue that progress should be measured by how effectively agents amplify human agency: enabling people to pursue their goals with less routine supervision while retaining control over consequential decisions. We advocate Avatar Intelligence, a paradigm of persistent personal agents that represent users' goals, values, and constraints through sustained decision delegation across contexts and time. We describe a maturity roadmap from human-directed execution to autonomous operation within delegated domains, and introduce the Agentic Oversight Index (AOI) as a framework for evaluating delivered value against agent-side operational cost and human oversight burden. We identify three core research challenges: identity-continuous personalization that carries user preferences across tasks, user-situated evolution through Rehearsal Engineering, and safety mechanisms that combine technical control with accountability and recourse. These directions define a research agenda for reliable decision delegation to personal agents across tasks and over time. Ecosystem Updates Tue, 03 Nov 2026 06:17:01 GMT https://daiviet.dev/ai-news/surgstream-a-workflow-anchored-proactive-streaming-framework-and-benchmark-for-real-time-surgical-video-understanding https://daiviet.dev/ai-news/surgstream-a-workflow-anchored-proactive-streaming-framework-and-benchmark-for-real-time-surgical-video-understanding Surgical video understanding is essential for intraoperative assistance such as workflow monitoring, instrument preparation and procedural documentation. Delivering such assistance in real time requires a model to jointly perceive the ongoing scene, remember past surgical events, and respond before clinically relevant moments pass. Existing approaches provide limited support for jointly retaining Ecosystem Updates Tue, 03 Nov 2026 05:01:59 GMT https://daiviet.dev/ai-news/to-align-long-plan-short-simulating-diverse-profile-aligned-students-by-realizing-short-term-plans-in-long-horizon-learning-environments https://daiviet.dev/ai-news/to-align-long-plan-short-simulating-diverse-profile-aligned-students-by-realizing-short-term-plans-in-long-horizon-learning-environments Simulated students offer a scalable way to test learning platforms and AI tutors before deployment with real students and to augment scarce data for studying learning at scale. Existing LLM-based simulators primarily target short, language-centered interactions. In open-ended learning environments, however, student behavior emerges from patterns across long-horizon interaction trajectories, where Ecosystem Updates Tue, 03 Nov 2026 04:46:59 GMT https://daiviet.dev/ai-news/safety4dm-a-vision-language-framework-for-risk-aware-dynamic-maps-in-vehicle-road-cloud-collaborative-driving https://daiviet.dev/ai-news/safety4dm-a-vision-language-framework-for-risk-aware-dynamic-maps-in-vehicle-road-cloud-collaborative-driving Dynamic map (DM) is a core information infrastructure for vehicle-road-cloud (VRC) cooperative autonomous driving. It fuses perception data from multiple sources to overcome the inherent line-of-sight and field-of-view limits of single-vehicle perception. However, DM still falls short on driving safety in two ways. First, DM data specifications already define road conditions semantically, but no p Ecosystem Updates Tue, 03 Nov 2026 04:46:59 GMT https://daiviet.dev/ai-news/rubricworld-world-model-guided-rubric-optimization-for-llm-graders https://daiviet.dev/ai-news/rubricworld-world-model-guided-rubric-optimization-for-llm-graders Rubric optimization improves LLM grading by revising scoring instructions while keeping the grader's parameters fixed. Existing optimizers often judge edits by aggregate validation performance, limiting the supervision they retain about which errors an edit corrects or introduces. Testing each candidate also requires rescoring validation answers, which limits how many edits can be explored within Ecosystem Updates Tue, 03 Nov 2026 04:46:59 GMT https://daiviet.dev/ai-news/trackmem-tracking-evolving-beliefs-in-long-horizon-financial-dialogue https://daiviet.dev/ai-news/trackmem-tracking-evolving-beliefs-in-long-horizon-financial-dialogue Memory systems for LLM agents are evaluated mostly on social dialogue, where facts accumulate and rarely change, so remembering reduces largely to finding the turn in which something was said. Financial dialogue breaks this assumption: figures are revised, stances shift without being restated, rules stated once govern later questions, and a single company is discussed under several analytical lens Ecosystem Updates Tue, 03 Nov 2026 04:46:59 GMT https://daiviet.dev/ai-news/paper-democratizing-robot-use-agents-a-unified-harness-with-open-models https://daiviet.dev/ai-news/paper-democratizing-robot-use-agents-a-unified-harness-with-open-models Robot-use Agents (RUAs) have shown promising zero-shot manipulation capabilities, but reliance on frontier, proprietary models limits research into further training. To democratize RUA research, we introduce uni-robot-agent, a unified harness for competitive open-weight robot use that supports further training. Without privileged inputs, an out-of-the-box Qwen3.8-Flash-Next achieves a RoboDojo Score of 31.39, surpassing the published GPT-6 Astra-RoboProbe result of 28.97 and many VLA/WAM baselines, and performs competitively on 19 real-world tasks. Our analysis across model generations, families, and sizes links effective robot use to four general capabilities, suggesting that future RUA training should develop them jointly. Ecosystem Updates Tue, 03 Nov 2026 04:46:58 GMT https://daiviet.dev/ai-news/paper-northcua-technical-report-turbocharging-computer-use-agents-through-experience-at-scale https://daiviet.dev/ai-news/paper-northcua-technical-report-turbocharging-computer-use-agents-through-experience-at-scale Scaling computer-use agents from individual actions to complex software work requires experience that connects decisions to complete outcomes. We present NorthCUA, an integrated system for turbocharging computer-use agents through experience at scale. Its Experience Flywheel supplies diverse executable tasks to the NorthCUA Harness, which sustains long interactions, records decisions, and checks task outcomes. The Flywheel uses these records to curate verified trajectories. For unsolved tasks, recursive self-improvement evolves reusable skills and preserves verified milestones so later attempts build on earlier progress. Staged Learning combines this experience with grounding data from the Flywheel to develop GUI competence through mid-training and long-horizon supervised fine-tuning. The policy then learns from fresh attempts in the same Harness through joint desktop-web reinforcement learning, closing the loop between experience production and policy improvement. The resulting Nano, Mini, and Pro family achieves state-of-the-art results among open-source models across GUI grounding, desktop execution, and Web interaction under the reported evaluation settings. For more responsive Web workflows, NorthCUA-Ultrafast pairs direct action selection with open-ended generation on pre-RL Nano, offering a measured quality-latency tradeoff. Together, these advances establish NorthCUA as a high-performing model family and a reusable foundation for agents that carry complex software work from intent to completion. Ecosystem Updates Tue, 03 Nov 2026 04:31:58 GMT https://daiviet.dev/ai-news/paper-wave-forcing-towards-speed-of-light-streaming-video-generation https://daiviet.dev/ai-news/paper-wave-forcing-towards-speed-of-light-streaming-video-generation Real-time long-video generation requires continuous output with consistent appearance and natural motion. Existing chunk-wise autoregressive methods face challenges in both generation efficiency and long-video quality: serialized denoising and history-cache refresh require two forward passes even with one-step denoising, and longer rollouts can degrade quality and cause camera drift. We propose Wave Forcing (WF), which co-designs generation, training, and execution for continuous video output with multi-step denoising. WF uses chunk-wise causal attention to access earlier, cleaner chunks before their denoising is complete, and distributes staggered denoising and cache-refresh stages across full-model replicas to achieve 1F1C: one output chunk per concurrent forward round after pipeline fill. To adapt the model to this continuous generation process, we develop a three-stage training procedure that successively introduces mixed-noise denoising, motion supervision, and causal adaptation using self-generated history. To execute this process efficiently, Wave Runtime (WaveRT) uses Wave Parallelism (WP) for early K/V delivery and communication-computation overlap, together with optimized kernels and pipelined VAE decoding. Experiments on Wan2.1-T2V-1.3B show that 5-step WF maintains overall quality comparable to Rolling Forcing while achieving higher Dynamic Degree on both short and long videos. Our system efficiency experiments show that 4-step WF achieves 147.6 DiT FPS and 134.8 end-to-end FPS on eight H200 GPUs, yielding 7.07x the single-GPU end-to-end throughput. In DiT-only tests with matched SageAttention+W8A8 backends, denoising steps, and GPU counts, WP delivers up to 2.53x the throughput of the faster of the Ulysses and Ring context-parallel baselines across six model scales (1.3B-14B). Ecosystem Updates Tue, 03 Nov 2026 04:16:58 GMT https://daiviet.dev/ai-news/toward-bounding-coding-agent-autonomy-in-software-maintenance-a-pilot-study-of-boundary-contracts https://daiviet.dev/ai-news/toward-bounding-coding-agent-autonomy-in-software-maintenance-a-pilot-study-of-boundary-contracts As coding agents gain greater autonomy to modify software repositories, relevant context alone does not define their operational authority. An artifact may be relevant to a maintenance task while being inappropriate to edit; conversely, another artifact may be required even when it is not explicitly mentioned in the request. We explore Boundary Contracts, a machine-readable abstraction that makes Ecosystem Updates Tue, 03 Nov 2026 04:02:06 GMT https://daiviet.dev/ai-news/paper-tinyastral-transferring-self-evolving-harnesses-to-tiny-generalist-manipulation-agents https://daiviet.dev/ai-news/paper-tinyastral-transferring-self-evolving-harnesses-to-tiny-generalist-manipulation-agents Robot agents built on vision-language models depend on both the planner and its harness: the tools, feedback, memory, and recovery logic around it. Can improvements to a large teacher's harness be carried into a compact agent with lower inference compute cost? We present TinyAstral, a two-stage approach. We first freeze an open-weight teacher and improve its harness through recursive self-improvement (RSI): frontier LLM agents read the teacher's trajectories and propose harness edits, and each edit is accepted only if it passes a paired statistical test. We then freeze the final harness, collect teacher trajectories with reasoning and failure recovery, and distill a small student that replaces the teacher in the same harness. On RoboTwin, harness evolution raises the teacher's success from 33.4% to 63.6%; the final 4B student reaches 62.8%. Across four harness versions, distilled 4B students score close to their corresponding teachers, and later versions yield stronger students, showing that harness evolution gains carry into compact models. The harness gains also transfer to other frozen planners without retraining. On identical episodes, the final 4B student outperforms open 4B agents, the open 27B harness-RSI model SenseNova-RoboRSI, and our own teacher model placed in three competitors' harnesses. It stays close to its teacher on all three training benchmarks, and on three benchmarks never used for RSI or training it scores close to a 552B planner running the same harness. On the measured deployment episodes, it uses about one fifth of its teacher's accelerator time. Ecosystem Updates Tue, 03 Nov 2026 03:46:56 GMT https://daiviet.dev/ai-news/ez-ar-vc-robust-arabic-voice-anonymization-with-generalization-across-dialects-and-code-switching https://daiviet.dev/ai-news/ez-ar-vc-robust-arabic-voice-anonymization-with-generalization-across-dialects-and-code-switching Voice conversion (VC) models can be used to anonymize speech data while preserving naturalness. Existing models, however, are mainly optimized for English and other high-resource languages, and they fail to generalize well to Arabic due to its distinct phonology. In this work, we comprehensively evaluate existing zero-shot VC systems for Arabic speech, identifying limitations in pronunciation pres Ecosystem Updates Tue, 03 Nov 2026 03:46:56 GMT https://daiviet.dev/ai-news/character-name-concentration-in-llm-fiction-measuring-displacement-and-mitigating-repetition https://daiviet.dev/ai-news/character-name-concentration-in-llm-fiction-measuring-displacement-and-mitigating-repetition Character names in large language model (LLM) fiction concentrate on a handful of recurrent names such as 'Elara' and 'Elias', a measurable face of AI slop. Existing fixes either require logit access or retraining, or operate per request and cannot control concentration across a corpus. How much prompt-level strategies reduce concentration, and at what cost to name naturalness, has not been system Ecosystem Updates Tue, 03 Nov 2026 03:46:56 GMT https://daiviet.dev/ai-news/geometry-of-confabulation-and-refusal-in-small-language-models https://daiviet.dev/ai-news/geometry-of-confabulation-and-refusal-in-small-language-models Faced with an unanswerable question, small language models can either refuse or confabulate: confidently produce a wrong answer. Can the hidden state before the first generated token provide a clue? Can we flip confabulations into refusals? I introduce ConfabQA, a 784-item benchmark whose obscure-pre-cutoff category breaks the typical correctness/knowledge-cutoff confound and map the geometry of t Ecosystem Updates Tue, 03 Nov 2026 03:46:56 GMT https://daiviet.dev/ai-news/ontodoc-automatically-generating-ontology-resource-descriptions https://daiviet.dev/ai-news/ontodoc-automatically-generating-ontology-resource-descriptions Knowledge graphs and ontologies form the backbone of structured, machine-readable knowledge representation, yet ontology terms often lack natural language descriptions, limiting their accessibility and reuse. Existing ontology verbalization approaches tend to rely on rule-based or template-driven techniques that operate on strict, formal schema axioms, resulting in rigid verbalizations that fail t Ecosystem Updates Tue, 03 Nov 2026 03:46:56 GMT https://daiviet.dev/ai-news/google-takes-dreambeans-to-india-in-bid-to-bring-ai-generated-personal-stories-to-the-masses https://daiviet.dev/ai-news/google-takes-dreambeans-to-india-in-bid-to-bring-ai-generated-personal-stories-to-the-masses Google's Dreambeans, its latest AI experiment, now supports 13 Indian languages. Ecosystem Updates Tue, 03 Nov 2026 03:32:04 GMT https://daiviet.dev/ai-news/paper-lost-in-recovery-demystifying-recovery-behavior-of-computer-use-agents-via-goal-oriented-action-replay https://daiviet.dev/ai-news/paper-lost-in-recovery-demystifying-recovery-behavior-of-computer-use-agents-via-goal-oriented-action-replay Recent advances in large (vision) language models have enabled computer-use agents that automate digital workflows via fine-grained keyboard and mouse operations. However, such agents remain fragile in long-horizon settings, where errors accumulate and executed actions leave unintended side effects, making the ability to recover from failures critical. Yet, existing remedies remain inadequate: environment resets are infeasible in proprietary settings, action replay is prohibitively expensive over long horizons, and API-based rollback is limited to web environments, leaving model-based recovery largely unexplored. To address this gap, we present ReTrace, a scalable evaluation framework for systematically studying recovery behavior in computer-use agents. We formalize Transition-Consistent Recovery: identical downstream actions from the recovered and target states must yield identical outcomes. We operationalize this criterion through goal-oriented action replay following controlled error injection. Using ReTrace, we present the first systematic study of autonomous, model-based recovery, revealing that (i) ideal recovery can unlock model's latent task completion capabilities, (ii) current computer-use agents fail to exploit their latent recovery capabilities, and (iii) accurate model-based recovery yields measurable end-to-end gains. Together, these findings establish recovery as a fundamental capability for building reliable computer-use agents. Our code and dataset is available at https://github.com/BangProx/ReTRACE. Ecosystem Updates Tue, 03 Nov 2026 03:31:58 GMT https://daiviet.dev/ai-news/paper-video-generation-meets-agent-harness-agentic-video-generation-agentic-world-modeling-and-recursive-self-improvement https://daiviet.dev/ai-news/paper-video-generation-meets-agent-harness-agentic-video-generation-agentic-world-modeling-and-recursive-self-improvement Video generation is shifting from end-to-end synthesis toward agentic generation, where planning, tool use, and feedback enable coherent, controllable multi-shot videos. In parallel, video world models provide action-conditioned observations and predicted futures, serving as interactive environments for agents. We study their intersection through the agent harness: an executable runtime that constructs context, exposes tools, maintains state, routes feedback, and manages budgets around video models. This report examines three directions. First, agentic video generation, where harnesses coordinate scripting, shot planning, asset management, production, and editing, alongside the evaluation challenges of these systems. Second, agentic world modeling, where harnesses mediate observation, control, execution, and state. We discuss hybrid designs in which game engines or agent-written programs maintain world state while video models render observations, and how agents and world models can mutually evaluate and improve one another. Third, recursive self-improvement (RSI) in video model development, distinguishing output revisions, updates to harness state, generator parameters, and evaluators, and changes to the improvement procedure itself. We identify how these improvements feed back into subsequent development. Across these directions, we analyze essential agent capabilities, including audiovisual perception, long-horizon planning, memory, code-based interaction, feedback-guided control, skill reuse, and multi-agent coordination. We conclude with challenges in autonomous video production, lifelong memory, programmable hybrid control, autonomous model development, provenance, cost accounting, and evaluation linking video quality and task performance to sustained improvements in models and harnesses. Ecosystem Updates Tue, 03 Nov 2026 03:31:58 GMT https://daiviet.dev/ai-news/paper-on-policy-self-distillation-with-teacher-evolution https://daiviet.dev/ai-news/paper-on-policy-self-distillation-with-teacher-evolution On-Policy Self-Distillation (OPSD), which aligns a student model's token-level distribution with that of its self-teacher prompted by privileged context, has emerged as a promising direction to mitigate reward sparsity in sequence-level post-training paradigms. However, OPSD often fails to achieve continuous performance gains during training. In this paper, we find that the model's limited self-teaching capability underlies this phenomenon by generating unreliable guidance on certain samples. To address this problem, we propose Teacher-Evolution Self-Distillation (TESD), which enables the self-teacher to generate rollouts and receive environmental feedback based on task correctness and context independence. First, using these rewards as training objectives, we perform teacher-oriented optimization to continuously enhance the model's self-teaching capability during distillation. Second, by estimating teacher guidance reliability from these rewards, we apply adaptive student-oriented optimization to down-weight samples with unreliable guidance. Extensive experiments across multiple datasets and model scales show that TESD consistently outperforms representative token-level and sequence-level methods, highlighting the necessity of improving supervision quality in OPSD. Ecosystem Updates Tue, 03 Nov 2026 03:16:57 GMT https://daiviet.dev/ai-news/paper-from-fragmentation-to-fusion-a-survey-and-roadmap-for-omnimodal-embeddings https://daiviet.dev/ai-news/paper-from-fragmentation-to-fusion-a-survey-and-roadmap-for-omnimodal-embeddings Embedding models underpin virtually every modern AI system, from search engines to recommendation systems. Despite shared mathematical foundations, research on embedding models remains fragmented by modality: the communities develop largely in isolation, seldom exchanging insights. We argue that this fragmentation obscures a deeper convergence. Driven by contrastive learning, Transformer architectures, and a granularity shift, embedding research across modalities is converging toward a common set of principles, even as modality-specific challenges remain underexplored. To reason across this convergence without conflating it, we propose a framework of three progressively harder capabilities: coverage, comparability, and compositionality. Three paths toward unification satisfy these in turn: transformation broadens coverage, alignment enables comparability, and joint embedding, the terminus we advocate, aims at compositionality. This position paper traces the resulting evolution, providing the first unified, cross-cutting treatment of omnimodal embedding research. Ecosystem Updates Tue, 03 Nov 2026 03:16:57 GMT https://daiviet.dev/ai-news/paper-maservebench-benchmarking-multi-agent-llm-serving-systems-with-hierarchical-collaboration-workloads https://daiviet.dev/ai-news/paper-maservebench-benchmarking-multi-agent-llm-serving-systems-with-hierarchical-collaboration-workloads Large language model (LLM)-based multi-agent systems (MAS) coordinate specialized agents to solve complex tasks, turning each user request into interdependent model and tool operations. Unlike independent requests, these operations become ready at different times and consume evolving context as agents coordinate and exchange results. This creates changing patterns of concurrency, computation, and memory demand that can expose different bottlenecks in LLM serving hardware. Yet benchmarking these effects requires capturing the collaboration rules that generate serving workloads, beyond the requests observed during execution. We present MAServeBench, a benchmark that treats multi-agent collaboration as a configurable dimension of serving workloads for LLM serving and hardware evaluation. Its composable stages capture how agents coordinate and exchange context in documented MAS workflows, enabling native executions to generate different workloads even when task inputs and tools remain unchanged. Hierarchical Semantic Traces preserve realized operations and dependencies for reproducible comparisons of legal release constraints at fixed work. Task-linked measurements connect these workloads to serving execution and GPU/NPU hardware behavior, revealing why serving efficiency does not always translate into timely task completion. The benchmark code is available at https://github.com/ShengxuanQiu/MAServeBench. Ecosystem Updates Tue, 03 Nov 2026 03:16:57 GMT https://daiviet.dev/ai-news/paper-diagnosing-the-reference-gap-what-visual-scaffolds-can-and-cannot-fix-in-multimodal-reasoning https://daiviet.dev/ai-news/paper-diagnosing-the-reference-gap-what-visual-scaffolds-can-and-cannot-fix-in-multimodal-reasoning Multimodal large language models can recognize visual content yet struggle to reason reliably over it across multiple steps. In counting, a model may see all objects but lose track of which ones it has counted. We argue that such failures, commonly attributed to perception, reveal a reference gap: the failure to bind language to the relevant visual entities, regions, or locations. Motivated by the theory of visual routines, we test whether external references such as numbering can narrow this gap. We introduce ReGap-Bench, a paired benchmark of five visual reasoning tasks in which the scene, question, and answer are fixed and only the reference varies. Results show that task-matched references improve accuracy by up to 25\%, while mismatched references provide little benefit or even hurt performance. These findings identify the reference gap as a bottleneck distinct from visual perception and show that constructing task-appropriate visual references can serve as a training-free visual skill for improving multimodal reasoning. Ecosystem Updates Tue, 03 Nov 2026 03:16:57 GMT https://daiviet.dev/ai-news/preparing-our-next-security-sprint-to-harden-openai https://daiviet.dev/ai-news/preparing-our-next-security-sprint-to-harden-openai OpenAI is preparing its next internal security sprint with Cathedral Systems to test and strengthen its defenses using AI. Ecosystem Updates Tue, 03 Nov 2026 03:02:00 GMT