Artificial Intelligence
TopoMamba: A Load-Support Relation-Guided Multi-Directional State-Space Model for Topology Optimization
Bin Lou, Yuxuan Cheng, Huaizhi Zong et al. (+2 more)
Deep learning has emerged as an efficient alternative for predicting high-performance material distributions in
topology optimization. Existing methods struggle to accurately capture load-transfer information, limiting out-of-distribution generalization, while their model architectures often incur high computational costs. To address these challenges, this paper proposes TopoMamba, a
topology prediction framework incorporating a load-support relation-guided multi-directional state-space model. Coupling physical fields with load-support relations enables more effective modeling of mechanical dependencies. A load-support relation-guided spatially adaptive fusion mechanism dynamically adjusts multi-directional scan features according to spatial conditions. Mamba is coupled with the solid isotropic material with penalty method to enhance structural mechanical performance while maintaining computational efficiency. Results on two-dimensional
topology optimization
benchmarks demonstrate that TopoMamba achieves superior
topology prediction accuracy, out-of-distribution generalization, and computational efficiency over state-of-the-art models. The proposed load-support physics-guided framework enables efficient optimization of more complex structural systems.
Read the full abstract ▾
All authors Bin Lou, Yuxuan Cheng, Huaizhi Zong, Junhui Zhang, Bing Xu
Artificial Intelligence
SWE-Game: Can Coding Agents Build the Games We Want?
Xiaoyu Chen, Lai Wei, Jin Wang et al. (+8 more)
We introduce SWE-Game, a
benchmark of 247 tasks grounded in 41 executable reference Godot games spanning 13 gameplay categories in 2D and 3D. Five task types cover development from a brief, implementation from a game design document, skeleton completion, repair of 83 injected-fault cases, and Godot-to-Unity porting. Reference materials specify the intended gameplay, while a shared instrumentation interface lets evaluator-owned drivers and probes execute actions and observe independently implemented games. Evaluation combines engine-state checks, certified reference-input replay, and
agent-authored feature demonstrations to assess mechanic correctness, demonstrated playability, and behavioral restoration and preservation after repairs. Game-specific
vision-
language rubrics separately assess presentation. Across six models, Opus5 achieves the highest overall score in all five task types. Best overall scores remain below 60 out of 100 across the three construction tasks, with Brief-to-Game reaching 50.38. Analysis of reviewed submissions identifies requirement omissions and gameplay logic errors as predominant implementation problems. On human-labeled behaviors from 100
agent-built games, executable checks achieve 92.59% balanced accuracy, compared with 78.41% for a
video-based VLM judge. Rubric-based visual scores reach a Spearman correlation of 0.829 with human ratings of 200 gameplay clips. Together, these results characterize current
agent capabilities across game-development activities and support combining runtime evidence with visual assessment.
Read the full abstract ▾
All authors Xiaoyu Chen, Lai Wei, Jin Wang, Xiangyu Zou, Ruochen Fan, Enze Luo, Mingzhe Yao, Jiahui Zhu, Yuhua Wen, Linghe Kong, Weiran Huang
Artificial Intelligence
Auditing Agent Actions through Query-Conditioned Attribution
Yifan Liu, Praveen Venkateswaran, Abdulhamid Adebayo et al. (+1 more)
LLM
agents increasingly take consequential actions through interactions with users, policies, and external tools.
Auditing these
agents requires automated attribution of realized actions to their historical basis. However, existing attribution formulations do not provide question-specific traces for diverse
auditing objectives. Additionally, when access to the acting model is limited (e.g., in API-only deployments), applicable methods commonly rely on costly input perturbations or external LLM analysis of complete trajectories. We therefore formulate query-conditioned
agent action attribution, a new task that takes a natural-
language auditing query as input and recovers the source and ordered intermediate evidence for the query-specified aspect of an action. We instantiate this task with $A^3Bench$, a
benchmark comprising 1,396
auditing queries across policy basis, parameter provenance, failure propagation, and unsafe-behavior tracing. To enable efficient, query-specific attribution, we use small open-weight models as attribution proposers that combine query-conditioned gradient saliency with query-semantic relevance to rank history units. Our proposer consistently achieves stronger source and evidence rankings at lower inference cost than open-weight baselines, improving source MRR by up to 40.9% and evidence MAP by 42.1% with only two forward passes and one backward pass. Controlled evaluations confirm that our proposer improves attribution specificity by adapting its rankings to fine-grained changes in the
auditing query. Building on a proposer ensemble, our end-to-end system surpasses the strongest frontier-model baseline in source accuracy (64.5% vs.\ 60.4%) while reducing empirical deployment latency by 29.9% relative to the fastest frontier API baseline. Code and data will be released after the initial review period following final validation and cleanup.
Read the full abstract ▾
All authors Yifan Liu, Praveen Venkateswaran, Abdulhamid Adebayo, Dong Wang
Artificial Intelligence
RSD-Poker: Structure-Adaptive and Shift-Robust Risk-Utility Certification for Residual Policies in Imperfect-Information Games
Miaobo Hu, Shuhao Hu, Xiaobo Guo et al. (+4 more)
Residual policy adaptation provides a lightweight way to modify a strong reference policy, but a shared scale and a fixed subgroup partition can hide heterogeneous degradation and become fragile when the deployment mixture of information states changes. We introduce RSD-Poker, a structure-adaptive and shift-robust certification framework that freezes a bank of residual families and scales, learns a policy-visible partition on an independent structure split, and freezes that partition before calibration labels are joined. Each candidate-group pair receives a weighted simultaneous upper certificate for anchor-relative risk and a lower certificate for weak-response utility. A robust group-to-candidate map is then selected over a predeclared uncertainty set of deployment group proportions. Under independent calibration units drawn from each frozen group's law, a candidate bank and partition fixed before calibration, and invariant within-group conditionals, the selected map satisfies its declared mixture-robust risk budget and utility certificate with probability at least $1-\zeta_{risk}-\zeta_{util}$. The information contract supports both a teacher-backed transform and a teacher-free observation-only student. The retained deterministic 24-state audit remains an exact replay diagnostic: empirical-zero selects $\alpha=0.08$, raising the weak-response proxy from 4.2082 to 4.2889 with $0/12$ held-out threshold crossings. On stratified held-out states, the learned-partition dual selector raises weak utility from 4.4074 under global dual certification to 4.4936 and lowers held-out violation from 0.0215 to 0.0078; its mixture-robust variant reaches violation 0.0059. Across five observation-only checkpoints, risk-calibrated residuals attain weak utility $4.3659\pm0.0177$ and violation rate $0.0178\pm0.0057$.
Read the full abstract ▾
All authors Miaobo Hu, Shuhao Hu, Xiaobo Guo, Xin Wang, Bokun Wang, Peng Zhang, Daren Zha
Artificial Intelligence · Cross-listed from cs.CV
When Noise Meets Long-Tail: Feature-Threshold Dual Calibration for Robust Pseudo-Labeling
Ping Guo, Zhiqi Huang and Xinran Li
Pseudo-labeling has become a cornerstone of learning from unlabeled data in semantic
segmentation. Yet its effectiveness drops sharply in real-world scenarios where strong imaging noise and long-tailed class distributions occur together. We trace this failure to a vicious cycle of pseudo-label degradation. Imaging noise entangles foreground and background features, lowering prediction confidence across all classes, while long-tailed distributions leave tail classes with far fewer training samples and inherently lower confidence. Under fixed high-threshold filtering, these tail-class predictions are systematically filtered out, so they receive no supervision from unlabeled data and thus features keep degrading in subsequent iterations. Critically, noise and long-tail are not independent obstacles but mutually amplifying ones, and addressing either alone is insufficient. To break this cycle, we propose FTC-Seg, a Feature-Threshold dual-Calibration framework built on a standard teacher-student framework. At the feature level, Orthogonal Prototype Reconstruction (OPR) uses a set of learnable orthogonal prototypes to residually purify pixel-wise features, widening the margin between weak foreground targets and noisy backgrounds. At the threshold level, Adaptive Threshold Calibration (ATC) dynamically adjusts class-specific thresholds based on learning difficulty and prediction-distribution bias, rescuing low-confidence pseudo-labels of tail classes from systematic exclusion. Extensive experiments on four public
benchmarks spanning three distinct noise modalities show that FTC-Seg achieves strong performance against state-of-the-art methods, with particularly substantial gains on tail classes. Our results establish that jointly calibrating features and thresholds is essential for robust pseudo-labeling under compounded noise and class imbalance.
Read the full abstract ▾
Artificial Intelligence
CompoWorld: Compositional Environment Scaling for General Agents
Xiao-Wen Yang, Weiyi Xu, Wen Da et al. (+9 more)
Automatically generated environments provide a scalable source of interaction data for training general
agents. However, existing approaches mainly generate tasks within a single environment, while real-world workflows require
agents to connect information and actions across multiple services. We introduce Compositional Environment Scaling (CompoWorld), which expands the task space by composing a finite library of reusable services. Coding
agents turn tool specifications into verified services with typed states and shared interfaces, while a world model handles tools that cannot be reliably implemented. A random-walk procedure connects services through dependency graphs, enabling the generation and verification of tasks that require information to flow across services. Verified trajectories support supervised fine-tuning (SFT), while our Completion-Focused Rubric Reward guides reinforcement learning (RL) toward full task completion by emphasizing criteria with lower pass rates within each rollout group. We construct 448 services exposing 10,130 tools and use 3K SFT trajectories and 1K RL tasks to train Qwen3.6-35B-A3B. Experimental results show that CompoWorld improves on its backbone by 9.17 points on average across eight
benchmarks. On AutomationBench, it surpasses frontier models such as Claude Opus 4.6 and leads all compared
agent-specialized 35B-A3B models.
Read the full abstract ▾
All authors Xiao-Wen Yang, Weiyi Xu, Wen Da, Hang Xu, Canwei Li, Hong-Jie You, Pusen Dong, Yucheng Zeng, Zhaokai Luo, Yu-Feng Li, Yao Hu, Mu Chuan
Artificial Intelligence
Audit-First VAPO: Risk-Certified Selective Updates under Imperfect Verification
Miaobo Hu, Shuhao Hu, Xiaobo Guo et al. (+4 more)
Imperfect verifiers can assign a harmful update direction even when clipping and regularization bound its magnitude. We introduce Audit-First VAPO, which separates discrete directional admission from continuous magnitude control. An observation-only accept-appeal-abstain policy uses a finite secondary-verification budget; its action trace is frozen before clean labels are joined. Simultaneous finite-sample bounds then certify selected harmful risk, coverage, and verifier-call rate over a predeclared policy family. Conditional Hoeffding-Azuma bounds account for the dependence induced by shared budgets, and rollout or verifier changes initiate a new certification stage. After admission, a bounded trust-clip-KL actuator controls magnitude. We evaluate two models on two
reasoning benchmarks against static RLVR, matched-random selection, confidence thresholding, noise correction, and verifier augmentation. On Qwen3.5-0.8B and GSM8K at target risk $\rho=0.08$, RC-VAPO achieves 74.1% accuracy, selected harmful risk 0.0697, coverage 0.4125, and relative verifier cost $1.16\times$. At matched coverage and update magnitude, its selected-risk difference from matched random is -0.0260 with paired 95% interval $[-0.0364,-0.0157]$. Across asymmetric, confidence-dependent, and correlated-verifier noise, the certificate is satisfied on 57 of 60 independent runs. These comparisons isolate informative directional selection from proposal suppression, update shrinkage, and additional verifier computation.
Read the full abstract ▾
All authors Miaobo Hu, Shuhao Hu, Xiaobo Guo, Xin Wang, Bokun Wang, Rui Chen, Daren Zha
Artificial Intelligence
AgentBoundary: Counterfactual Evaluation of Safety in Tool-Using LLM Agents
Tianzhuo Yang, Zirui Mi, Yantao Huang et al. (+4 more)
Safety
alignment for large
language models (LLMs) in conversational settings is largely framed around whether to answer or refuse a request. In agentic settings, however, the same models must decide whether to act as permission-critical evidence emerges during execution. This creates a distinct challenge: apparent risk, action permissibility, and task competence are easily confounded, making agentic over-refusal difficult to distinguish from ordinary task failure. To address this, we introduce AgentBound, the first four-way counterfactual generation-and-evaluation framework for tool-using
agent safety. AgentBound transforms the same executable workflow by independently varying apparent risk and action permissibility, enabling controlled comparisons of risky-looking but authorized tasks and routine-looking but unauthorized tasks. These comparisons jointly diagnose over-refusal and unsafe compliance while controlling for task competence. We instantiate AgentBound as a human-validated 4,000-task evaluation suite with trajectory-based and post-state-based judgments. Across 17 model and harness configurations, high safety frequently coexists with poor authorized-task completion: GPT-5.5 blocks 99.5% of routine-looking unauthorized actions yet completes only 28.7% of risky-looking authorized tasks. We further train a lightweight runtime calibration module that improves authorized-task completion by 18.2% on average across 10 evaluated configurations, while improving unsafe-action blocking by 5.4% on average. These show that effective agentic
alignment requires action decisions to track permission-relevant execution evidence, rather than refusal strength alone.
Read the full abstract ▾
All authors Tianzhuo Yang, Zirui Mi, Yantao Huang, Guoxi Zhang, Jiawei Chen, Yaodong Yang, Jingwei Yi
Artificial Intelligence · Cross-listed from cs.RO
Demonstration-Free Success-Probability Reward Learning for Generalist Robot Policies
Duo Wu, Haifeng Wang, Rongwei Lu et al. (+6 more)
Reinforcement learning (RL) enables generalist
robot policies to improve through trial-and-error interaction, yet its effectiveness is fundamentally constrained by sparse task rewards. Existing general-purpose reward models typically alleviate this issue by learning task progress from expert demonstrations, but introduce a distribution mismatch with the mixed-quality rollouts encountered during policy optimization, making their estimates unreliable on suboptimal and failed behaviors from which the policy must learn. In this work, we introduce a demonstration-free reward learning paradigm where dense reward feedback can be learned directly from sparse task outcomes and policy experience. We theoretically show that terminal task outcomes implicitly define dense success-probability feedback at intermediate timesteps, which can be recursively learned through bootstrapping. Based on this insight, we introduce eVTA$_0$, which learns success probabilities from mixed-quality policy rollouts through temporal-difference-style bootstrapping, without expert demonstrations or intermediate annotations. We further introduce RL with Evolving Rewards (RLER), a closed-loop framework that adapts eVTA$_0$ using newly collected rollouts as the policy evolves. Experiments show that eVTA$_0$ provides more informative rewards than state-of-the-art reward models and achieves the best average policy performance across all LIBERO task suites under the same RL training budget, improving success rates by 5.4%-13.8% over the initial policy. In real-world manipulation, RLER further improves overall success rates by 20%-26%, with 35%-36% gains under out-of-distribution conditions. These results demonstrate the effectiveness of demonstration-free reward learning and adapting rewards as the policy evolves. Project webpage: https://duowuyms.github.io/evta0.
Read the full abstract ▾
All authors Duo Wu, Haifeng Wang, Rongwei Lu, Jinghe Wang, Tianyi Xiong, Zhimin Wang, Chao Yu, Shuai Ma, Zhi Wang
Artificial Intelligence · Cross-listed from cs.CL
Tsubame: Tree Replay for Diffusion-Based Speculative Decoding
Yepeng Weng, Qiao Hu and Takehisa Yairi
Context-aware dynamic trees allocate the speculative decoding budget according to draft path probabilities, adapting their depth and branching to the current context. Under
stochastic decoding, however, we find that this structural advantage does not always compensate for the acceptance gains of random sampling paired with advanced verification, and such dynamic trees can fall behind sampled chains in some settings. These trees grow their
topology from the candidates themselves, so the
tokens submitted for verification are typically the deterministic high-score
tokens selected during construction. This coupling is not inherent: once the
topology is fixed, its nodes can be repopulated by sampling, allowing dynamic trees to retain their structural advantage while also benefiting from random sampling and advanced verification.
Diffusion-based drafters make this practical, as their parallel outputs or lightweight conditional corrections allow candidates to be regenerated cheaply after the complete
topology is known. We introduce Tsubame, a two-pass tree speculative decoding framework for
diffusion-based drafters. The first pass plans and freezes a context-aware
topology using draft path scores; the second replays the fixed
topology, sampling the
tokens that populate its nodes to form the candidate tree for verification. We prove that Tsubame is lossless under compatible sampling and verification strategies. Experiments across three
diffusion-based drafters, six
datasets, and multiple candidate budgets show that Tsubame improves acceptance length and throughput over deterministic trees, including settings where it reverses their disadvantage against sampled chains.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
From Distributions to Stochastic Processes: Neural Approximation of Measure-Valued Maps
Yichen Wang, Ziyi Wang, Wenlian Lu et al. (+5 more)
Learning mappings between probability distributions arises naturally when inputs and outputs are represented by populations of samples rather than individual observations. We develop an approximation-theoretic framework for distribution-to-distribution learning and extend it to mappings between
stochastic processes. For continuous operators on $W_2$-compact families of finite-dimensional probability laws, we establish uniform neural approximation in the 2-Wasserstein metric using finite law statistics, a simplex-valued neural map, and a shared atomic output support that guarantees valid probability measures. We further extend this principle to probability laws on separable
Hilbert spaces through finite-rank orthogonal projections. These results establish the representational feasibility of learning transformations between probability laws rather than deterministic vectors or functions. To demonstrate practical relevance, we study two problems naturally defined at the distribution level: prediction of first-passage-time distributions for an Ornstein–Uhlenbeck process and nonlinear response-path laws of a Duffing oscillator. Because the theory is model-agnostic and broader than any single practical architecture, the experiments use task-adapted neural models rather than reproducing the theoretical construction exactly. In both problems, the proposed models outperform a fixed-feature MLP baseline and distribution-space kernel regression. These experiments complement the theory by demonstrating the practical learnability of distribution-to-distribution transformations in random systems.
Read the full abstract ▾
All authors Yichen Wang, Ziyi Wang, Wenlian Lu, Chenghuang Shen, Jianfeng Liu, Zhengdong Xiao, Longjiu Luo, Qianrong Wang
Artificial Intelligence
Probe to Act: Elevating Browser-Use Agent via Active Visual Probing
Keliang Li, Heng Wang, Chen Hu et al. (+3 more)
Browser-use
agents require seamless
alignment between structured web metadata and visual information, while preserving relevant context across long interactions. Existing interfaces often rely on either screenshot-level action prediction or static Set-of-Marks overlays, leaving the model to resolve dense DOM-pixel
alignment before every operation. We introduce Probe to Act (P2A), an active probing framework for the browser-
agent loop that moves this
alignment into decision time. P2A addresses an asymmetric bridge between symbolic DOM hypotheses and screenshot layout by rendering on-demand symbolic DOM structure back into pixels. Before committing a state-changing browser operation, the
agent can issue lightweight probes to translate DOM handles into pixel evidence, map screen regions back to DOM candidates, register visual-only targets, and commit verified notes. These interleaved processes naturally produce evidence-based
memory: only probed, acted-on, or explicitly committed observations are kept across steps, preserving only decision-critical evidence in long-horizon contexts. P2A can be used as a prompting strategy for proprietary models under the standard DOM+SoM interface, and can be distilled into open-weight models through cold-start synthesis and self-bootstrapped SFT. Across three browser-use
benchmarks, P2A shows clear gains on task success rate for both proprietary and fine-tuned models; on VisualWebArena, for example, it improves Gemini-3-Pro from 54.1% to 61.2% and Qwen3-VL-8B from 24.6% to 32.9%, while matching the costly full-observation history ($\sim$3$\times$) at only $\sim$1.2$\times$ the peak retained input context of action-only history.
Read the full abstract ▾
All authors Keliang Li, Heng Wang, Chen Hu, Daxin Jiang, Hong Chang, Shiguang Shan
Artificial Intelligence · Cross-listed from cs.CL
Learning to Learn from Context: Synthetic Training from Perturbed Public Documents
Haoyi Wu, Yang Xiao, Yusong Sun et al. (+4 more)
Real-world tasks often require large
language models (LLMs) to learn from complex task-specific context rather than pretrained parametric knowledge. This capability remains a weakness of LLMs, while human annotation for such task contexts is expensive and difficult to scale. Public high-quality documents are an abundant alternative, but much of the public web has already been consumed during pretraining: training on such documents naively would reward memorization rather than context learning. In this work, we attempt to make use of high-quality public documents with small perturbations and empirically find that LLMs can successfully generate context-dependent
reasoning traces and answers, which are then used to train a student model. Specifically, we construct a synthesis pipeline that (i) rewrites source documents to reduce memorization risk, (ii) generates questions and rubrics that require
reasoning over the document, (iii) answers the questions with the document as context, and (iv) admits only samples that genuinely depend on the document. Without any human annotators, our pipeline generates about 10k samples from 3.5k documents, and the resulting student model substantially improves the performance on CL-bench. SFT raises a Qwen3.6-35B-A3B student from 13.7% to 22.8%, and a subsequent rubric-reward RL stage reaches 24.6%, on CL-bench comparable with a frontier model of over a trillion parameters, Qwen3.8-2.4T (23.9%). We also observe a broad transfer of improvements to long-context understanding, instruction following, and
reasoning, while code generation and knowledge remain mostly flat. We hope this work provides a reproducible and scalable way to improve the ability of LLMs to learn from context, and to facilitate further research on context-grounded
reasoning.
Read the full abstract ▾
All authors Haoyi Wu, Yang Xiao, Yusong Sun, Wenyang Hui, Zhaokai Luo, Chengyue Jiang, Mu Chuan
Artificial Intelligence
Scalable and Data-Driven Decision Support in the Maintenance, Repair, and Overhaul Process
Houkun Zhu, Helena Ebel, Dominik Scheinert et al. (+3 more)
Several businesses apply maintenance, repair, and overhaul (MRO) principles to the life-cycle of their existing products. In cases like casted gas turbine component Product Lifecycle Management (PLM), repairing components in frequent intervals can extend the lifetime expectation of the product, provide higher cost efficiency compared to newly produced components, and even improve the part design during the repair cycle. Another aspect of repair concerns sustainability, as products often contain rare materials. The emissions produced by the repair process are usually smaller than mining materials and casting new components. To optimize the repair process further, we propose the Smart Expert System (SES), which assists engineering experts with machine learning-based decision support throughout the repair process. We elaborate on its IT architecture and present machine learning models employed for representative MRO use cases. The SES is evaluated using actual industry data from a leading gas turbine company and demonstrably fulfills formulated requirements concerning the suitability of the overall decision support and the stability of the enclosing IT architecture.
Read the full abstract ▾
All authors Houkun Zhu, Helena Ebel, Dominik Scheinert, Florian Schmidt, Jens Altenkirch, Odej Kao
Artificial Intelligence
Trajectory Unlearning on LLM-based Agents
Yingdan Shi and Ren Wang
Existing large
language model (LLM) unlearning has focused primarily on removing specific knowledge, such as harmful facts, private data, or copyrighted content. However, as LLMs are increasingly deployed as autonomous
agents, a fundamental yet overlooked problem emerges: beyond suppressing what an
agent knows, an
agent should not reproduce undesired behaviors through its action trajectories. In this work, we introduce trajectory-level unlearning, a new problem formulation that targets the removal of specific action trajectories in long-horizon agentic tasks, rather than factual knowledge. We identify two fundamental challenges that distinguish trajectory unlearning from knowledge unlearning: (1) our unlearning target is what the
agent does, not what it says; and (2) trajectories are sequentially dependent action sequences that cannot be decomposed into isolated
prompt-response pairs without losing inter-step structure. To address these challenges, we propose Group-injected Relative Policy Optimization (GiRPO), which injects forget trajectories into the policy rollout group with penalized rewards and isolates the normalization statistics, yielding a stable and bounded unlearning signal that does not corrupt gradient updates for normal task trajectories. We construct trajectory unlearning
benchmarks from two application scenarios, household tasks (ALFWorld) and online shopping (WebShop), and design three complementary metrics for evaluating forgetting quality and model utility. Experiments on ALFWorld and WebShop demonstrate that GiRPO effectively unlearns target trajectories while preserving task success rates, outperforming existing knowledge-unlearning baselines on both forgetting quality and task utility.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Safety Reconstructed: Generative Modeling via Masked Diffusion Builds Strong Safety Guardrails
Gert Lek, Abele Malan, Chaoyi Zhu et al. (+3 more)
Guard models are the last line of defense between a
language model and a harmful output, yet their training objective is surprisingly narrow. Existing guards learn to predict a single verdict
token from a conversational context, concentrating supervision on a single target. The consequences are structural: models latch onto shortcut features, are overconfident, and remain sensitive to where safety evidence appears in the sequence rather than its role in the full context. We propose a different framing. Rather than predicting a label from text, our LLaDA-Guard asks which label better explains the text: scoring the
prompt or response under each label hypothesis and classifying based on their difference. This shifts supervision to every
token in the moderated region, forcing the model to account for full content rather than its most discriminative fragments. We instantiate this idea with a masked
diffusion language model, fine-tuning LLaDA-8B-Instruct with a class-conditional reconstruction objective using LoRA and requiring no architectural changes beyond the base model. LLaDA-Guard leads on average rank against discriminative baselines trained on stronger backbones across seven held-out safety
benchmarks, while exhibiting substantially better confidence calibration (ECE 0.0875 vs. 0.1384 for Qwen3Guard), less over-defense on benign
prompts with unsafe-looking cues, and less
prompt leakage when moderating responses. Its generative nature further enables
token-level risk localization as a natural byproduct, yielding a pipeline for rewriting unsafe
prompts into safe equivalents without additional training and achieving a 60.7% average conversion-to-safe rate.
Read the full abstract ▾
All authors Gert Lek, Abele Malan, Chaoyi Zhu, Pin-Yu Chen, Robert Birke, Lydia Chen
Artificial Intelligence · Cross-listed from cs.CV
StoryEngine: A State-Grounded Agentic Framework for Video Storytelling
Yingrui Wang, Zeqing Wang and Yeying Jin
Despite recent progress in agentic multi-shot
video generation, producing coherent and consistent long-form stories remains challenging. Existing agentic pipelines typically rely on textual shot plans or previously generated pixels, yet lack an explicit mechanism for propagating the consequences of story events and maintaining the
video world state across shots. As a result, missing visual details may be reconstructed inaccurately, while visual drift may propagate across subsequent shots, undermining both narrative coherence and visual consistency. To address these challenges, we propose StoryEngine, a state-grounded agentic framework for
video storytelling. StoryEngine establishes a separation between authoritative semantic plans and unreliable visual observations. Specifically, StoryEngine maintains a structured representation of entity placement and story-relevant states, and propagates event-induced changes to define the intended start and end states of each shot. To visually realize these states, StoryEngine constructs canonical references for recurring entities and environments, and compiles state and visual constraints into executable render plans. Meanwhile, to realize these states correctly, a bounded evaluation-guided repair loop further corrects local state inconsistencies. Together, these mechanisms preserve causal story progression and prevent local visual errors from propagating across shots. To comprehensively evaluate long-form storytelling, we construct a
benchmark across diverse scenarios and visual styles, with metrics assessing storytelling quality, narrative coherence, and visual consistency. Experimental results demonstrate that StoryEngine consistently outperforms state-of-the-art methods across all evaluation dimensions, validating its effectiveness for coherent and consistent
video storytelling.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Learning Dynamics of Continual Learning: A Unified View of Data Attribution, Forgetting, and Plasticity Loss
Yi Ren, Wenlong Deng, Guanzhe Hong et al. (+2 more)
Modern
language models are likely to be updated throughout their lifetime rather than trained once and frozen. Each update therefore participates in a recurring cycle: decide which experience to learn from, understand what that update changes, and remain capable of learning from what comes next. We show that these challenges are governed by the same evolving update–behavior interaction. We derive a
token- and layer-wise decomposition of how learning from one
token changes another prediction. By separating the softmax force, shared readout geometry, and residual connections, it exposes two interaction channels and yields a forward-computable approximation. Following this interaction through time reveals a unified picture of continual adaptation. Positive interaction identifies useful experience; negative interaction produces either concentrated collision or accumulated erosion; over longer horizons, updates reshape the shared geometry mediating future learning signals, reducing their transmission. These predictions lead to effective data selection, mechanism-specific controls for interference, and a readout-based diagnostic of future learnability whose degradation predicts the benefit of restoring the readout. Across models and training regimes, the same local interaction thus explains both what an update changes now and how learning today changes what can be learned tomorrow. This view connects data attribution, forgetting, and plasticity loss as distinct regimes of the same evolving learning dynamics.
Read the full abstract ▾
All authors Yi Ren, Wenlong Deng, Guanzhe Hong, Clare Lyle, Yarin Gal
Artificial Intelligence
ParaAgent: Reinforcing Parallel Acting in Open-World Tool Environments
Shengbin Yue, Hongru Wang, Siyuan Wang et al. (+3 more)
Language model
agents are increasingly deployed in open-world tool environments, which require balancing exploring unknown capabilities and exploiting known ones. Existing methods face a performance-efficiency tradeoff: they either rigidly decouple exploration and execution or interleave them without coordination. We argue that the key lies not in whether to decouple or interleave them, but in how to coordinate them across granularities. We introduce ParaAct, a structured parallel-action loop that combines phase-level Exploration $\rightleftharpoons$ Execution with action-level parallelism. To learn this loop, ParaAgent combines multi-
agent cold-start demonstrations with reinforcement learning under multi-level advantage decoupling, making planning structure explicit and supervising it with step-, phase-, and trajectory-level rewards. Learning is supported by our ToolEnv, a scalable simulator grounded in 50,011 realistic tool interfaces. On two open-world tool
benchmarks, ParaAgent-4B achieves the best average success among all baselines, including GPT-4.1 systems, with the largest gains on multi-tool tasks. Behavioral analyses show that these gains stem from this action organization, highlighting its importance for capable and efficient open-world
agents.
Read the full abstract ▾
All authors Shengbin Yue, Hongru Wang, Siyuan Wang, Xiaoxin Chen, Wei Chen, Zhongyu Wei
Artificial Intelligence · Cross-listed from cs.CV
SpatialSpeak: QA-Native Reconstruction with Local and Global Context for Spatial Chain-of-Thought Reasoning
Yang Cao, Jiaxin Zhang, Dave Zhenyu Chen et al. (+4 more)
Vision-
language models (VLMs) can benefit from
geometric priors for multi-view spatial
reasoning, yet answer-only training does not directly supervise the intermediate
geometric estimates and their use in deriving quantitative spatial answers. We hypothesize that spatial chain-of-thought (CoT) supervision becomes more effective when the VLM first jointly learns complementary local geometry and global scene context through multi-view reconstruction. We introduce SpatialSpeak, a two-stage framework that connects QA-native reconstruction pretraining with spatial CoT learning. In Stage I, QA-Native Reconstruction Pretraining (QA-RP) combines marked-point 3D queries for fine-grained local geometry with object-center queries for global scene context across views. Both tasks are formulated as text-based question answering, allowing
geometric estimation and subsequent
reasoning to share the same autoregressive output interface. In Stage II, spatial CoT with Visual Compensation (CoT-VC) trains the model to express question-relevant
geometric estimates and use them to derive answers, with reliability assessment and visual compensation supporting answer refinement when needed. On ReVSI, QA-RP increases the gain from CoT-VC from 2.6 to 6.9 points, and ablations show that both local and global reconstruction supervision are beneficial. SpatialSpeak achieves state-of-the-art results on ReVSI, VSI-Bench, and SPAR-Bench, with a ReVSI score of 62.8 that exceeds the strongest compared baseline by 8.7 points.
Read the full abstract ▾
All authors Yang Cao, Jiaxin Zhang, Dave Zhenyu Chen, Yingji Zhong, Ruiyuan Gao, Lanqing Hong, Dan Xu
Artificial Intelligence
EAT: Expert Account Tracker for Efficient MoE Inference
Yuexian Li, Yifei Yang, Zouying Cao et al. (+1 more)
Mixture-of-Experts (MoE) models have emerged as a revolutionary method to scale
Transformer models. However, traditional MoE architecture still suffers from inefficiency since a large number of experts are unnecessarily activated. Existing approaches for reducing the number of activated experts often overlook the historical performance of each expert. In this paper, we propose EAT, a novel method called Expert Account Tracker (EAT), which utilizes history-awareness metrics and adaptive thresholding to dynamically select the most important experts, thereby reducing the activated expert number while effectively maintaining the model performance. Experiments show that EAT outperforms the existing baseline Top-P method across multiple models and
datasets, achieving over 25% an average reduction compared to the vanilla method in the number of activated experts and performing better
token generation speed compared to the baseline. Furthermore, the performance of pruned models can be efficiently recovered via OPD using only 9K data. Additionally, through ablation studies, we find that excessively reducing the number of activated experts can significantly harm model performance, and the importance of experts varies across layers, with higher-level experts being generally more critical.
Read the full abstract ▾
All authors Yuexian Li, Yifei Yang, Zouying Cao, Hai Zhao
Artificial Intelligence · Cross-listed from cs.CL
Quizzing the Translation: A Prover-Grounded Evaluation Metric for NL$\rightarrow$FOL
Pu Suo and Ali Emami
A standard pipeline for symbolic
reasoning over natural-
language problems translates them into first-order logic and invokes a
theorem prover. The translation step is the bottleneck: swap "every" for "some" and every inference that follows is corrupted. Yet today's metrics often score more broken translations higher than less broken ones, because BLEU, BERTScore, and Smatch++ reward surface overlap that the worst errors happen to preserve. We introduce SIV, which derives two kinds of probes from the target formula and uses a
theorem prover to verify the candidate translation against each. Positive probes are statements the candidate must entail, which detect translations that drop content; contrastive probes are statements the candidate must not entail, which detect translations that assert more than the original. On a controlled pool of perturbed FOLIO translations, the severity of the error accounts for 80% of SIV's score variance, compared with at most 17% for any prior metric. Across six error classes on a disjoint pool, SIV scores the reference above the perturbed candidate in over 99% of pairs. Because each probe is labeled with what it tests, the failure pattern also supplies a labeled error trace, recovering the perturbation class at macro-F1 0.638, nearly double the score-only baseline. On 434 expert-audited real LLM translations, SIV attains the top AUC, uniquely detects and grades expert-labeled major errors, and abstains, rather than mis-scoring, on out-of-vocabulary translations.
Read the full abstract ▾
Artificial Intelligence
Supervision Recovery for Time Series Anomaly Detection via Context-Anchored Pairing
Yifei Gao, Tian Lan, Yimeng Lu et al. (+5 more)
Time series anomaly detection (TSAD) remains challenging not only because anomaly labels are scarce, but also because temporal anomalies are highly context-dependent. Existing methods often rely on unsupervised objectives or surrogate abnormal patterns, providing limited supervision for context-dependent normal–anomalous distinctions. We propose Context-Anchored Pair Supervision (CAPS), a supervision-recovery framework for TSAD. CAPS views ideal anomaly supervision as a matched comparison between normal and anomalous outcomes under the same temporal context, and seeks to recover such supervision without target-domain anomaly labels. Using simulated normal–anomalous pairs, CAPS learns structure and anomaly-semantic representations through reconstruction, background consistency, and within-pair counterfactual recombination. The resulting anomaly representations form a continuous semantic space with coarse modes and induce a sampleable
multimodal prior. CAPS conditionally realizes sampled semantics as residual-form effects on target reference trajectories. The resulting context-anchored normal–anomalous counterparts provide temporal supervision for discriminative detector learning. Experiments on nine
datasets show that CAPS achieves the strongest aggregate performance across all four evaluation metrics among the compared methods, while complementary ablations and transfer analyses support the roles of context anchoring, semantic disentanglement, and conditional realization.
Read the full abstract ▾
All authors Yifei Gao, Tian Lan, Yimeng Lu, Xuming An, Meng Wang, Wenjun He, Yijie Li, Chen Zhang
Artificial Intelligence · Cross-listed from cs.CE
Learning Transferable Reaction Mechanisms from Visual Chemical Knowledge
Yujian Yuan, Jiaxin Xu, Xin Cai et al. (+4 more)
Reaction mechanisms describe the step-by-step transformations underlying chemical reactions and are central to reaction analysis and synthesis. Learning-based models have achieved strong performance on established mechanism-prediction
benchmarks, but transferring them to unseen chemistry remains challenging. Such transfer is difficult because familiar mechanisms must be applied to unfamiliar molecular structures, and some target mechanisms may be poorly covered by the training data. To address these challenges, we introduce MechaVLM, a visual framework that combines transferable chemical representations with external mechanistic knowledge. It learns reusable visual features through multiscale chemical grounding and cross-rendering contrastive learning. For open-book prediction, MechaVLM retrieves a fixed set of precedents from 70,384 literature mechanism figures and re-reads relevant visual evidence as the molecular state evolves, directly using the figures without symbolic mechanism parsing. An atom-indexed
language decoder then recursively generates executable electron edits to construct the complete mechanism. We further introduce MechBench, a challenging literature-derived
benchmark with 2,184 mechanisms and 9,146 elementary steps. Across cross-
dataset and literature-derived
benchmarks, MechaVLM establishes strong zero-shot mechanism prediction. Its closed-book model alone improves Step/Pathway Top-1 by 12.50/13.93 percentage points on FlowER-to-ReactMech transfer, while external visual precedents unlock further gains on challenging OOD reactions. The learned representation also generalizes beyond mechanism prediction to atom mapping and reaction center prediction.
Read the full abstract ▾
All authors Yujian Yuan, Jiaxin Xu, Xin Cai, Yufan Chen, Zhichao Tan, Ziqi Zhou, Hanyu Gao
Artificial Intelligence · Cross-listed from cs.CV
ViCoR: Reliable Molecular Structure Extraction via Spatially Aligned Verification and Executable Revision
Yujian Yuan, Xin Cai, Yufan Chen et al. (+5 more)
Reliable optical chemical structure recognition (OCSR) is essential for building high-quality chemical data from scientific literature, yet even small recognition errors can propagate into chemical databases and downstream models. In practice, recognized structures often require manual inspection and correction before use, making large-scale data curation costly and difficult to scale. We therefore study Selective Structure Recognition (SSR), a post-recognition setting that automatically produces reliable structured outputs while rejecting unresolved cases. Selection-only approaches can improve reliability by rejection, but cannot create additional correct outputs beyond those produced by the base recognizer. We propose ViCoR, a repair-before-rejection framework for iterative VerIfiCatiOn and Revision. Its key idea is to make observation-prediction correspondence explicit: coordinate-preserving rendering establishes spatial correspondence between the source image and predicted structure, while index anchoring maps localized visual discrepancies to executable graph edits without full-structure regeneration. A shared VLM is progressively trained from verification to revision. On two real-world OCSR
benchmarks, ViCoR improves overall accuracy from 73.53% to 88.26% and from 61.83% to 84.32%, while achieving over 97% accepted accuracy at 85–89% coverage. The resulting molecular data further improve reaction-extraction F1 by 15.5 points and literature-sourced reaction prediction accuracy by 7.7 and 5.8 points, demonstrating the value of automated reliability control for scientific data curation and downstream chemical learning.
Read the full abstract ▾
All authors Yujian Yuan, Xin Cai, Yufan Chen, Jiaxin Xu, Mengdi Liu, Zhichao Tan, Long Chen, Hanyu Gao
Artificial Intelligence
JustQuant: You Don't Need Smoothing, SVD, or Rotation for 4-Bit Activation Quantization
Kaicheng Yang, Kaisen Yang, Chunyu Liu et al. (+8 more)
Recent generative models have become increasingly powerful, but their inference cost continues to grow. Model quantization offers a promising way to compress these models and accelerate inference. However, at 4 bits, activation quantization is substantially more challenging than weight quantization. Recent post-training quantization (PTQ) and quantization-aware training (QAT) methods have made progress in 4-bit activation quantization by introducing smoothing, SVD branches, rotations, mixed precision, or advanced formats such as NVFP4. These additional operators and data types impose demanding requirements on inference engines and hardware, limiting the broad adoption of low-precision models. Can quantization be achieved using only plain low-bit operators? To answer this question, we propose JustQuant, a simple yet effective framework that moves the complexity of low-bit quantization from deployment-time operators into the training process. We first revisit model quantization from the perspective of knowledge
distillation and show that a key reason existing PTQ and QAT methods fail is that they typically exploit supervision at only a single level. We then introduce Theseus QAD, a quantization-aware
distillation method that progressively applies multi-level supervision, analogous to the gradual replacement process in the Ship of Theseus. Extensive experiments on DiT and
diffusion large
language models show two distinct regimes. For smaller models, Theseus QAD can serve as a lightweight warm-up stage that substantially improves subsequent QAT with plain operators, while naive QAD may collapse in the same setting. For larger models, Theseus QAD provides a stronger
distillation training path than ordinary QAD. Across both regimes, JustQuant improves low-bit quantization quality while avoiding the complex operators required by many existing PTQ methods.
Read the full abstract ▾
All authors Kaicheng Yang, Kaisen Yang, Chunyu Liu, Xianglong Yan, Haotong Qin, Junyi Wu, Tianao Zhang, Xun Zhang, Shaoqiu Zhang, Youbang Sun, Yulun Zhang
Artificial Intelligence · Cross-listed from cs.LG
Compressing Value Predictions for Learning-Augmented Metrical Task Systems
Sizhe Li, Yecheng Li and Kun He
Learning-augmented
algorithms for metrical task systems (MTS) can exploit predictions of canonical dual values, but existing formulations typically require a prediction for every state. We study whether these predictions can be compressed to a small set of representative states while retaining their algorithmic value. We introduce landmark-compressed value predictions, in which the predictor reports predicted dual values only at $m$ landmarks and the remaining values are reconstructed by a Lipschitz extension. Our
algorithm achieves additive excess cost $O(T\,r(L) + \sum_t \delta_t)$, where $r(L)$ is the covering radius of the landmarks and $\delta_t$ measures prediction error up to additive shifts; local and value-dependent bounds refine this guarantee. For sparse landmark sets on unit-spaced finite lines, we prove a matching $\Omega(T r_m)$ lower bound for every randomized
algorithm using fixed landmarks, even with advance access to their entire exact absolute-value table. The prediction interface also matters: on two states with one landmark, exact absolute values permit horizon-independent excess, whereas exact relative values force worst-case expected excess linear in $T$. We give PAC guarantees for learning compressed prediction tables, with efficient empirical-risk minimization for fixed landmarks. Our results connect metric coverage, prediction interfaces, and learning guarantees for compressed predictions in online MTS.
Read the full abstract ▾
Artificial Intelligence
OpenFC: Learning Verification Policies towards Open-Search Fact Checking
Xinming Wang, Kaixiang Qiu, Yansong Lin et al. (+5 more)
Open-search fact checking is not merely
retrieval followed by classification, but a sequential decision problem in which every query, source visit, and stopping decision reshapes the evidence available for verification. Yet existing systems often distribute these decisions across predefined pipelines or separately prompted modules rather than learning them as a unified task-specific policy. We introduce OpenFC, a unified verification-policy training framework that post-trains Qwen3-8B as a compact next-action controller over
reasoning, evidence acquisition, and stopping. OpenFC learns this policy in two stages. Stepwise-Calibrated Cold Start (SCCS) uses a strong training-time supervisor to review post-initial
reasoning, tool-use, and stopping proposals before execution, producing reliable trajectories for supervised fine-tuning without access to gold verdicts. Verification-Aware Reinforcement Learning (VA-RL) then improves the cold-start policy on unresolved claims through budget-aware tool rewards, label-aware advantage reweighting, and localized response masking. Across six fact-checking
benchmarks, OpenFC achieves 70.39% average accuracy and 63.30% macro-F1, the highest overall averages among the evaluated methods. Stage-wise ablations further show that SCCS and VA-RL provide complementary gains, supporting the design of the two-stage training framework. These results position OpenFC as a strong and effective framework for open-search fact-checking. We will open-source our code and release the model checkpoints to support reproducibility.
Read the full abstract ▾
All authors Xinming Wang, Kaixiang Qiu, Yansong Lin, Chunji Lv, Yi Chen, Boran Wang, Hong-Ming Yang, Xu-Yao Zhang
Artificial Intelligence
Dr. Free: You Don't Need Difficulty Rewards for Self-Evolving Search Agents
Zhipeng Qian, Zihan Liang, Yufei Ma et al. (+10 more)
A central limitation of current data-free self-
evolution methods for training search
agents is their reliance on difficulty-based proposer rewards. These methods reward a proposer for generating questions that challenge a co-evolving solver, using solver difficulty as a proxy for question quality. Yet difficulty alone is insufficient to distinguish questions that require cross-passage evidence from those that are answerable via simpler shortcuts. In addition, measuring difficulty demands repeated solver rollouts for every candidate question, leading to substantial computational costs. In this paper, we introduce \methodname, the first self-evolving search framework that eliminates difficulty-based proposer rewards and directly optimizes for evidence necessity relative to shortcut contexts. Dr. Free samples relational chains from a knowledge graph and pairs them with aligned passages, giving question generation an explicit multi-hop structure. A generated question receives a positive information-gain reward only when the likelihood of the target answer under the complete evidence passages exceeds the maximum likelihood under all evaluated shortcut contexts. Because this signal is computed from teacher-forced likelihoods, it removes the need for pass-rate estimation and reduces proposer training time by over $7\times$. Experiments on seven open-domain QA
benchmarks show that Dr. Free outperforms prior data-free search
agents and the supervised baseline, with large improvements on multi-hop QA
benchmarks.
Read the full abstract ▾
All authors Zhipeng Qian, Zihan Liang, Yufei Ma, Jie Ma, Ben Chen, Huangyu Dai, Lingtao Mao, Xinyu Sun, Tong zhao, Xuxin Zhang, Qingpeng Cai, Peng Jiang, Qibin Hou
Artificial Intelligence · Cross-listed from cs.LG
MA-JEPA: Joint-Embedding World Models for Multi-Agent Reinforcement Learning
Brandon Gary Kaplowitz, Osaze James Obahor and Christian Schroeder de Witt
World models improve sample efficiency by training policies on imagined trajectories, but their usefulness depends on learning representations that capture the information needed for future control. We study whether self-supervised joint-
embedding prediction (JEPA) can provide this learning signal for multi-
agent reinforcement learning. We introduce MA-JEPA, a
stochastic world model that replaces observation reconstruction with prediction of target representations, enabling model-based multi-
agent reinforcement learning with centralized training and decentralized execution. A categorical latent state and a causal
Transformer are trained with posterior and action-conditioned dynamics prediction objectives and are then used for actor-critic learning from latent imagination. A training-only joint predictor conditions on all
agents' local states and actions to predict each
agent's next local observation
embedding. These predictions are passed through the same local posterior used during real interaction with a centralized critic that is used only for value learning, with execution remaining decentralized. Our experiments show that this architecture performs strongly on SMAC, matching or exceeding the strongest reported comparator mean win rate on four of eight evaluated maps.
Read the full abstract ▾