Research

• Real-time request execution in streaming video generation1 paper raises it · 0 address it

  Models struggle to reliably follow incremental user requests while maintaining state consistency in interactive video generation.

  • StreamEval: Evaluating Interactive Streaming Video Generation Modelsraises
• Brain-body mismatch in recursive self-improving agents1 paper raises it · 1 addresses it

  Evolving execution scaffolds (harnesses) can outpace or restrict the capabilities of the underlying model, leading to misalignment.

  • CoEvo-RSI: When Harnesses Evolve, Which Models Should Follow?raises · addresses
• End-to-end deep search in open web environments1 paper raises it · 1 addresses it

  Agents fail to autonomously explore, integrate, and verify evidence from diverse, interactive, and heterogeneous web sources.

  • Deep Search in Real-World Web Environmentsraises · addresses
• Length generalization in state tracking1 paper raises it · 1 addresses it

  Models trained on short sequences often fail to generalize to much longer sequences without explicit progress alignment.

  • PAR: Progress-Aligned Recurrence for Length Generalization in State Trackingraises · addresses
• Fine-grained geometry and appearance recovery in 3D Gaussian Splatting1 paper raises it · 1 addresses it

  Feed-forward models struggle to capture detailed structures and textures in 3D scene reconstruction.

  • FineSplat: Fine Patches, Local Groups, Detailed Splatsraises · addresses

Named by an AI from these papers' abstracts.

• arXiv cs.AIOct 13

  Encounter-Driven City-Scale Human Mobility Generation with Large Language Models

  Chao Li, Renhe Jiang, Chuan Xiao, Jiawei Wang

  Large language models (LLMs) have shown strong potential for human mobility generation by modeling individual routines, activities, and mobility preferences. However, existing approaches remain largely resident-centric: generating realistic individual trajectories does not necessarily recover the encounters that emerge when multiple residents co-occur at the same place and time. To this end, we study encounter-aware human mobility generation, which jointly preserves individual mobility and population-level interaction structure. We propose EncounterMob, an encounter-driven LLM framework consisting of a coarse-to-fine Encounter Generator and an Iterative Coupling Framework. The Encounter Generator first captures city-level encounter rhythms and then instantiates participant-time-venue encounters, while the Iterative Coupling Framework coordinates these encounters with personal mobility behavior through successive refinement. We further introduce an encounter recovery protocol covering encounter marginal and joint distributions over residents, times, and venues. Experiments on the Japan and NYC datasets show that EncounterMob outperforms all external baselines on all seven…

  PDF

  Summarize this
• arXiv cs.GROct 13

  Integrating 3D Posture Neutralization with Statistical Shape Modeling for Head-Neck-Shoulder Ergonomic Design

  Jinbo Luo, Hang Ren, Yadie Yang, Jie Zhang

  The design of ergonomic products and workspaces requires a deep understanding of human anatomy and posture. In particular, the head-neck-shoulder region is critical for many applications such as cervical orthoses, helmets, and other head-worn or neck-worn devices. This paper presents a framework that integrates posture neutralization with statistical shape modeling (SSM) for the head-neck-shoulder (HNS) region. We acquire a single three-dimensional (3D) scan of the head-neck-shoulder region from each of 200 Chinese adults in a natural posture for each subject. Every scan is then posture-neutralized before SSM. We fit a parametric head-neck model to each scan to separate cervical pose from anatomy, and reset the cervical pose to a common neutral configuration, so that the resulting model captures anatomical shape variation rather than posture-induced deformation. The resulting shape space yields a standardized template and population-wide modes of variation, providing baselines for parametric ergonomic design. We further discuss how the model supports population coverage analysis and the design of products that accommodate anatomical diversity while maintaining neutral cervical…

  PDF

  Summarize this
• arXiv cs.AIOct 13▲ 8

  Cowork-Gym: Synthesizing Interactive Work Environments at Scale

  Anni Zou, Cheng Chen, Jiaji Deng, Weikang Zhou, Xinji Mai +16

  Cowork agents navigate dependencies across tools and files while adapting to changing user requirements and edits to shared workspaces. Scaling such environments requires maintaining consistency among task objectives, executable resources, user behavior, and success criteria. We introduce Cowork-Gym, a framework that synthesizes Cowork environments through a build-execute-revise loop that uses execution evidence and review feedback to validate and repair generated environments. To capture realistic Cowork dynamics, a stateful user simulator responds to the agent's actions through dialogue and direct edits to the shared workspace. We synthesize 64.9K environments across 14 application scenarios and use them to post-train 9B, 27B, and 35B-A3B Qwen models with supervised fine-tuning, reinforcement learning, and on-policy distillation. Averaged across six agentic benchmarks, these models outperform their corresponding base checkpoints by 8.7, 6.4, and 4.1 points, respectively. Ours-27B ranks second overall among the evaluated models and achieves the highest average scores on PawBench and ClawEval, outperforming models with over 100B total parameters on both benchmarks.

  PDF

  Summarize this
• arXiv cs.ROOct 13

  PrT-Flow: Probability-Tractable Flow Matching for Reinforcement Learning

  Congzhong Sun, Ning Tan

  Diffusion models and Flow Matching can represent flexible distributions over robot actions, but many reinforcement learning algorithms also require the probability of each action. We introduce PrT-Flow (Probability-Tractable Flow Matching), which computes probability density while retaining multimodal, multi-step action generation. Its Jacobian-Tractable Transformer (JTT) makes each sampling step invertible and enables efficient computation of its Jacobian determinant. We train these finite steps with Conditional Euler-step Training (CET), which supervises their displacement over one step during sampling rather than their instantaneous velocity. We prove that, under certain assumptions, CET has the same minimizers as fitting the Euler-solver updates of Flow Matching. PrT-Flow achieves 96% success on Robomimic Lift after 300 epochs of imitation learning, matching the diffusion policy reference, and 96% success on OGBench Cube-Triple after 600k online steps. These results demonstrate that invertible networks with tractable probability densities can learn effective robot policies and support SAC-style actor-critic training. Our code is available at…

  PDF

  Summarize this
• arXiv cs.LGOct 13▲ 34

  DeltaTTG: Training Multi-Turn Agents with a Token-to-Go Progress Meter

  Xuyan Ye, Xiyan Fu, Shengda Fan, Jiawei Cui, Yankai Lin +1

  Reinforcement learning with verifiable rewards (RLVR) for multi-turn agents relies on sparse terminal rewards that say little about individual steps. Within-group step comparisons depend on reliable state matching and sufficiently diverse sampled outcomes, while direct step scoring may require costly external evaluators, human annotations, or task-specific heuristics. We introduce DeltaTTG to learn a reusable progress signal through a shared progress meter, using low-cost supervision from diverse policies' recorded trajectories without task-specific progress rules. Its supervision target, Token-to-Go (TTG), the number of tokens remaining to be generated until task completion, serves as an observable proxy for remaining completion effort. During actor training, changes in the frozen meter's estimates redistribute outcome-derived advantages across steps without altering the reward, preserving each trajectory's advantage sign and token-average scale. On ALFWorld, PaperSearchQA, and BFCLv3, DeltaTTG improves the average score over GRPO by 5.7 and 7.2 points with Qwen3-4B and Llama-3.1-8B-Instruct, respectively, outperforms all compared RL baselines on average, and keeps…

  Code
• arXiv cs.AIOct 13▲ 202

  RoTA-Bench: Evaluating 3D Spatial Reasoning through Interactive Projection Alignment

  Qingchuan Ma, Yuexiao Ma, Xiang Meng, Yixuan Zou, Tianyu Xie +5

  Can vision-language models turn 2D observations into 3D understanding that supports precise action? This requires inferring object geometry, anticipating the effects of rotation, and refining actions through visual feedback. We introduce RoTA-Bench to evaluate these abilities through interactive 3D-to-2D projection alignment. Given a target silhouette, a model observes a rotated object and chooses successive rotations to recover the target projection within a limited action budget. Our automated pipeline constructs silhouette-preserving 3D objects from 2D icons and uses reversible initialization to guarantee solvability, yielding 674 tasks and a stratified 100-task test set. Empirically, we find that (i) a substantial human-model gap persists: GPT-5.6-Sol succeeds on only 17% of tasks, whereas 20 undergraduate participants collectively complete the test set four times with a 100% success rate; (ii) image-space and pose-space progress can diverge: at matched states, the model more often improves silhouette overlap while worsening pose alignment than humans (19.4% vs. 10.9%); and (iii) fine-grained control is sensitive to interaction history: removing it leaves 96.8% of the model's…

  Code
• arXiv cs.CLOct 13

  The Image Still Has a Say: Final-Answer Repair for Multimodal Chain-of-Thought

  Yulan Pan, Xiaoyu Xu, Zhihong Shen

  Although chain-of-thought prompting has improved multimodal reasoning, it is still difficult to produce correct final answers, as the reasoning can drift away from the image. Besides, the trace is already fixed when the answer is generated, leaving no room for self-correction. Considering the image is still available at the final-answer step, we think it is reasonable to fix the answer there without rewriting the reasoning. As such, the problem becomes to correct the final answer using the image under fixed reasoning. Unlike methods that improve trace generation through training, resampling, or decoding-time grounding, we repair the final-answer readout while keeping the reasoning trace fixed. The motivation is based on our finding that a wrong option can become prematurely committed in the reasoning while the correct option still has stronger image support in middle-to-deep layers. Thus, we propose Text-to-Visual Evidence Reallocation (TVER), a training-free method for final-answer repair. Specifically, TVER selects answer-related text and question-matched image patches, and moves bounded attention from text to patches. Furthermore, the patches are chosen in a middle-to-deep…

  PDF

  Summarize this
• arXiv cs.CVOct 13

  ScenePercept: Scenario-Conditioned Perceptual Assessment of Real-World User-Generated Content Images

  Shuhan Xia, Yu Chen, Xiang Wang, Shuai Li, Peipie Li +1

  The rapid development of mobile imaging and social platforms has led to explosive growth in user-generated content images, making their systematic and comprehensive perceptual assessment increasingly important. Existing image perception benchmarks are typically task-oriented, curating specific scenarios for quality or aesthetic assessment and applying a uniform perceptual criterion across diverse scenarios. This limits their ability to capture the scene diversity and perceptual complexity of real-world UGC images. To address these limitations, we introduce ScenePercept-Bench, a benchmark designed to reflect the distribution of real-world UGC images, comprising 23,100 images across 21 categories and 105 fine-grained scenes. To account for the influence of scene context on human perception, we design a hierarchical, scene-aware annotation protocol, covering visual quality, aesthetic perception, and scene semantics, with 15 attributes in total. Each image is annotated with an overall score, 15 attribute-level scores, and structured explanatory reasoning. Building on this benchmark, we further introduce Scenario-Conditioned Perceptual Alignment, a training framework that tackles the…

  PDF

  Summarize this
• arXiv cs.AIOct 13

  Can Agents Truly Forget? Explore Machine Unlearning for LLM Agents

  Junkai Lin, Ge Xu, Zheng Xu, Junkai Chen, Xiangyuan Lan

  Large language model (LLM) agents have shown strong capabilities in interactive problem solving, tool use, and long-horizon task execution. However, they may also acquire sensitive or private knowledge during training and expose it during deployment. Retraining a model from scratch to remove such knowledge is prohibitively costly, making machine unlearning a more practical approach. Machine unlearning aims to remove targeted undesirable knowledge from trained models without retraining from scratch while preserving general utility. When language models are deployed as agents, parameter-level unlearning becomes insufficient: forgotten information may still persist in memory artifacts or be reacquired via tool calls. In this paper, we formulate the problem of agent unlearning as removing private information from an LLM-based agent across three information channels: parametric knowledge, persistent memory, and tool-call acquisition. To study this problem, we introduce we introduce Agent Unlearning Benchmark (AUBench), a controlled benchmark that extends the fictitious-author setting of TOFU into an agent environment with persistent memory, an offline web snapshot, tool-accessible…

  PDF

  Summarize this
• arXiv cs.CLOct 13

  Worth Their Weights? Evaluating Generative Models for Discourse Parsing

  Luke Gessler, Amir Zeldes

  Rhetorical Structure Theory (RST) parsing has historically been dominated by discriminative models based on pretrained encoder-only language models. The recent availability of high-quality generative language models has made it unclear whether RST parsing is better approached as a generative task. In this work, we investigate whether generative language models are better at parsing RST than traditional discriminative ones. We find that at matched parameter counts, discriminative parsers perform much better than generative ones, though much larger generative models sometimes outperform them. Generative models hold a particular advantage in elementary discourse unit (EDU) segmentation, and we report new state-of-the-art results on the RST-DT benchmark in end-to-end parsing as well as segmentation.

  PDF

  Summarize this
• arXiv cs.CVOct 13▲ 28

  Open-o3-Video-v2: Seek, Ground, and Reason with Verifiable Spatio-Temporal Evidence

  Jiahao Meng, Zhongyuan Bao, Yue Tan, Haiquan Wen, Renrui Zhang +5

  Reliable video reasoning requires models to produce correct answers and expose supporting visual evidence. Open-o3-Video enables verifiable reasoning by embedding timestamps and object-level bounding boxes into reasoning traces, but is restricted to frames from an initial sparse sampler. We introduce Open-o3-Video-v2, which formulates video reasoning as a unified agentic evidencegrounded process. The model identifies missing information, acquires additional observations, grounds the moments and objects supporting its reasoning, and writes this evidence into the trajectory before continuing or answering. To support this behavior, we construct STGR-v2-CoT135K, including 52K multi-turn agentic grounded reasoning trajectories, and STGR-v2-RL-13K for reinforcement learning. We further propose Clue-Seek GRPO (CS-GRPO), which tracks how tool calls change accumulated evidence, rewards clue coverage and step-wise gains, and penalizes excessive, repetitive, or uninformative retrieval. On V-STaR, Open-o3-Video-v2-4B achieves 40.4% mAM and 56.3% mLGM, outperforming its Qwen3-VL-4B backbone by 8.5% and 12.6%, respectively. It also delivers consistent gains across general video understanding,…

  Code
• arXiv stat.MLOct 13

  textGrain watermarking is harder to detect: can sum-tests still do it optimally?

  Swapnaneel Bhattacharyya, Soham Bonnerjee

  Watermarking embeds an imperceptible signal in text from large language models that is statistically detectable with a secret key. The recent textGrain watermark (Li et. al. (2026b)) calibrates this signal against the model's sampling entropy through an explicit entropy budget, combining the stochasticity of Red-Green and the unbiasedness of Gumbel-max watermarks, and its accompanying report proposes a detector that sums pivotal statistics. We study when, and how efficiently, textGrain can be detected after human edits, modeled as a sparse mixture in which a fraction $\varepsilon_n\asymp n^{-p}$ of positions retain the watermark and token uncertainty decays as $n^{-q}$. First, entropy calibration comes at a cost: the minimax detection boundary of textGrain is $p+q=1/2$, so its detectable region is strictly smaller than that of Gumbel-max and maximal-coupling watermarks, whose boundary is $2p+q=1$. This cost stems from textGrain's construction rather than from entropy calibration itself: an unbiased scheme with the same entropy loss remains detectable where textGrain is not. Second, perhaps surprisingly, this loss makes the sum detector optimal at the boundary when the number of…

  PDF

  Summarize this
• arXiv cs.CLOct 13

  Decouple to Forget: Semantic Mediation for Sensitive Unlearning in Large Language Models

  Jingyue Cong, Andy Song, Yang Yu, Tabinda Sarwar, Xinshu Li +5

  Machine unlearning for large language models seeks to remove specified knowledge while preserving general capability, yet current methods often treat an entire response as the unit of forgetting. This coarse granularity causes unnecessary utility loss when the forget target is only a small set of sensitive facts embedded within otherwise benign explanations. In this paper, we introduce Decouple to Forget (D2F), a targeted unlearning method inspired by semantic mediation that separates sensitive factual content from non-sensitive meaning and surface expression. For each example to be forgotten, D2F extracts a fact-level "mediator" representation from the answer, identifies which parts are sensitive, and removes only those parts while leaving the rest of the structure intact. We then generate counterfactual answers grounded in this mediator that preserve non-sensitive content but exclude sensitive facts, employing preference-based contrastive optimization to reduce the likelihood of information leakage while maintaining helpfulness and fluency. Experiments across various benchmark datasets show that D2F achieves a better balance between forgetting and retention than strong baseline…

  PDF

  Summarize this
• arXiv cs.ROOct 13

  Code2Worlds-2: Physically Plausible Agent Harness for Embodied World Simulation

  Haoyu Zhang, Siming Li, Zeyu Zhang, Yi Zhang, Tat-Seng Chua +1

  Recent coding large language models (LLMs) can synthesize dynamic 4D worlds from natural language, but the resulting content remains a visual artifact. It lacks physical semantics such as the collision geometry, mass, friction, inertia, and joint structure, required to enable it to simulate the physical world, and its dynamics are scripted to look plausible rather than designed to execute. What is needed is an executable world: one that a physics engine can load and step, resolving contact physically. We present Code2Worlds-2, an extension of Code2Worlds that turns 4D world generation into an embodied world simulation. We keep the original dual-stream generation pipeline intact and append two modules. First, a SimReady Scene Compiler that turns a generated visual scene into a simulator-compatible representation: it assigns collision meshes via convex decomposition, estimates physical attributes with a vision-language model, infers a lightweight support graph, instantiates the engine's contact, friction, and dynamics constraints, and applies a gravity settling pass, before exporting the scene as MuJoCo MJCF. Second, a Simulator-in-the-Loop 4D Refiner that implements an automated…

  PDF

  Summarize this
• arXiv cs.LGOct 13▲ 2

  DisaggKD: Efficient Knowledge Distillation through Teacher-Student Disaggregation and a Fused Loss

  Ruixuan Tu, Yuyang Dong

  Knowledge distillation (KD) frameworks place teacher and student on the same GPUs, so per-GPU memory limits the teachers that fit. DisaggKD separates them across nodes: teacher replicas stream hidden states to the student, a KD loss over row windows and vocabulary shards equals the full-vocabulary loss in exact arithmetic without forming the full-vocabulary logits, and a prefetch ring paces producer and trainer. Closed-form memory and traffic models locate the memory limits of each layout. On the Qwen3.5-35B-A3B to 9B pair, the disaggregated layout matches the LM loss of the colocated run with the same loss and is faster than that run; our fused loss also lets a colocated run train on as few nodes at faster speed, while the split is memory efficient when the student spans several nodes. On the larger pairs, colocated runs with a fused loss still run OOM where the split trains, because teacher weights and student states fill the budget.

  PDF

  Summarize this
• arXiv cs.AIOct 13

  When Should Enterprise Policy Decisions Be Learned, and When Should They Be Reasoned?

  Hyojung Han, Ryangkyung Kang, Youngeun Kim, Seung-Hun Jeon

  An enterprise agent that answers under a written policy must choose an action before it says anything: answer, ask for a missing fact, ask for confirmation, call one or several tools, escalate, or refuse. Holding one 27B Korean enterprise model fixed, we vary whether the decision is a generated JSON object or a single constrained token, and whether the model may reason first. On 2800 in-distribution items we did not detect an accuracy difference between the two deployed paths (93.46% vs 94.14%), while they differ about tenfold in restart stability (3.00% of actions flip vs 0.29%); they also differ in reasoning, so this is an operational comparison. On a sealed benchmark of 300 items whose labels come from a hidden executable policy, reasoning is worth +17.3 points [+12.3, +23.0] on exact action. With reasoning off, the format difference was 0.0 points [-4.3, +4.0], a failure to detect an advantage for either interface, not equivalence; with reasoning on it is unresolved. Against a token-matched random control, boundary-targeted supervision moves the two covered boundaries by +17.5 and +20.0 points and leaves a held-out boundary unchanged. In a 3-seed training x reasoning…

  PDF

  Summarize this
• arXiv cs.AIOct 13

  Beyond Bias Scores: Answerability Confounds in Activation Steering with Gradient-Constrained Direction Design (GCD)

  Weitong Li, Donglin Song, Junkai Lin, Xi Xuan

  Bias scores in language-model evaluations often conflate what a model prefers with whether it answers at all. We identify this confound in \textsc{BBQ}, whose ambiguous score factorizes into answerability and signed preference. Across 11 categories, 28,}824 items, and five models, contrastive steering lowers the signed ambiguous score in 11/11 categories but lowers the signed disambiguated preference score in only 8/11. Across 99 configurations, the answerability channel exceeds half of the observed score change in 17\% and accounts for the entire change in 11%. In a six-category disambiguated evaluation, 20.8\% of 1,500 items flip to the unknown option, where abstention is incorrect; \textsc{StereoSet} shows no analogous answer-rate shift. The effect reflects selection and near-orthogonality between the contrastive and preference-gradient directions. We introduce Gradient-Constrained Direction Design (\textsc{GCD}), an option-gradient construction with a first-order unknown-logit constraint. Under a matched Qwen-7B protocol, GCD reduces answer-rate distortion 14-fold and yields a 4-fold larger preference change, while ablations show similar gains for alternative and…

  PDF

  Summarize this
• arXiv cs.CVOct 13

  MemAct: Streaming Spatial Understanding with Memory and Active Exploration

  Yuxi Wei, Wei Huang, Qirui Chen, Lu Hou, Xiaojuan Qi

  Spatial understanding is essential for embodied agents navigating and interacting with the physical world. As observations arrive incrementally, agents must reason in a streaming manner. Yet streaming understanding must also be closed-loop: task-relevant evidence may require both recalling past observations and actively acquiring new views. Existing streaming approaches largely emphasize processing incoming observations, leaving task-driven active exploration underexplored. We introduce MemAct, a framework for streaming spatial understanding with memory and action. A shared vision--language model incrementally writes structured historical memory, retrieves records and past frames on demand, and acquires additional evidence through movement and turning. Retrieved evidence and action observations inform subsequent decisions, enabling the agent to continue exploring or answer within a unified reasoning loop. We develop the MemAct suite, a data generation pipeline and collection across real and simulated environments, with approximately 1M training examples for spatial reasoning, memory writing, retrieval, and exploration. Its MemAct-bench comprises 20,000 main QA pairs evaluating…

  PDF

  Summarize this
• arXiv cs.CVOct 13

  FrameLite: Decision-Oriented Aesthetic Cropping with a Compact Vision-Language Model

  Jianze Li, Kai Liu, Ziqing Zhang, Weihang Zhang, Yong Guo +2

  Aesthetic image cropping improves composition by balancing subjects, context, and image boundaries. Large vision-language models bring semantic knowledge to this task, but their scale limits lightweight photography assistance. We propose FrameLite, a compact cropping model built on Qwen3.5-0.8B. Our approach is motivated by the observation that a small model can generate better crops than its first answer suggests. We develop three-stage training to turn this potential into stronger direct predictions. Spatial and composition training establishes localization and framing preferences. Quality-Guided Online Supervision (QOS) then learns the highest-quality complete answers among the current policy's generated candidates. Greedy-Referenced Optimization (GRO) further refines the policy using positive and negative quality differences relative to its current greedy answer. Both online stages use annotation-derived feedback, while inference returns one coordinate answer without search or an external scorer. Experiments show that FrameLite outperforms the compared large-VLM croppers across public benchmarks with a substantially smaller backbone. Controlled studies confirm that selecting…

  PDF

  Summarize this
• arXiv cs.LGOct 13

  Mixed Precision Scaling Laws for Quantized Pretraining

  Jinuk Kim, Rajarshi Saha, Muhammed Fatih Balin, Youngsuk Park

  Since scaling laws were introduced for modern LLMs (Kaplan et al., 2020), several works have extended them to account for quantization, tracking the emerging low-precision data types supported on AI accelerators. We develop a more accurate scaling law for quantized pretraining with mixed precision across the forward and backward passes, grounded in optimization theory and validated empirically. Our formulation separates the effects of quantization on model capacity and on optimization efficiency, and explicitly models the persistent optimization error from forward and backward quantization identified through convergence analysis. To select the regimes for fitting and evaluating our law, we first decompose existing 4-bit training recipes into their forward and backward components, isolating those that most affect loss. Our Qwen3 experiments under selected 4-bit regimes, together with published Llama-style experiments, show that our law predicts loss with up to $11\times$ lower MSE than existing laws as model size and token count scale. Finally, we extend our law to layer-wise mixed precision and identify the optimal quantized-pretraining recipe, i.e., model size, training tokens,…

  PDF

  Summarize this

• Adversarial training42−10.6%
• Anomaly detectors28−20.0%
• Forecasting time61−21.8%
• Federated learning36−23.4%
• CAD models12−25.0%
• Frontier LLMs361−29.8%
• Inference & serving205−29.8%
• Teacher policy distillation45−30.8%