Looped Transformers increase effective depth by re-executing shared layers, but three limitations hinder their adoption: memory grows with the loop count, compute can only be adjusted in whole-block steps, and the loop count is hard to change after training. We propose LooM (Loop-invariant Memory), which addresses each in turn. In a causal encoder-decoder (CED), LooM loops only the decoder layers after the first, which read a global memory written once per token, and each of them publishes the key-value (KV) entry for a token only on its first visit, so the cache does not grow with the loop count. These layers loop independently, providing every budget from 3 to 21 layer executions per token, and one model trained on randomly sampled budgets covers all of them without a router. With enough loops, LooM outperforms a single-pass baseline trained on the same data on language modeling, zero-shot accuracy and long-context perplexity, while using the same cache size. Our analysis further shows that the training budget distribution decides what extra depth buys. These results suggest that a CED is a natural place to loop: memory is written once, and depth becomes a budget chosen at deployment.
Deep learning-based super-resolution (SR) can reconstruct fine-scale Earth-observation fields from coarse observations, but reconstruction accuracy alone does not provide a calibrated rule for identifying reliable spatial regions. Conformal Mask Calibration (CMC), built on conformal risk control, converts a spatial uncertainty score into a trust mask and controls the expected worst-case local distortion under exchangeability. However, its fixed threshold can become miscalibrated in Earth-observation streams affected by seasonality and episodic events. We propose $\textit{CARM}$ (Conformal Adaptive Risk Masking), a statistical framework for adaptive spatial risk control under temporal distribution shift. CARM maintains experts with heterogeneous update rates and aggregates their threshold proposals online using an asymmetric surrogate loss, balancing rapid adaptation to distribution changes against stability during relatively stationary periods. All updates are causal and use only mature feedback available after a fixed delay, allowing CARM to operate with any SR model that provides a spatial uncertainty score. We prove that the time-averaged mask-conditioned risk converges to at most $α$ at an $O(1/T)$ rate, without distributional assumptions and for any choice of aggregation weights across experts. On a daily South China Sea chlorophyll-$\textit{a}$ SR stream, CARM reduces the empirical violation rate from $43.49\%$ to $9.38\%$ and the moving-average exceedance frequency from $47.29\%$ to $1.22\%$ at $α=0.10$, while retaining a non-trivial trusted region. Experiments on ERA5 wind and OSTIA sea-surface temperature further show consistent relative improvements across multiple SR backbones.
Hanqing Wang, Zhaotian Cai, Ruichuan An, Bohan Zeng, Tao Zhang, Yilin Chen, Xu Jiang, Kaiquan Chen 等 16 位作者
Vision--Language--Action (VLA) models generate robot actions from visual observations and language instructions, but their understanding of physical dynamics remains limited. Video world models can capture scene dynamics, yet generating future videos introduces high latency into the control loop. We introduce PDRVLA, whose lightweight Physical Dynamics Module extracts physical tokens from vision--language features to condition action generation without online video generation. The module learns through direct prediction of future RGB, depth, and optical-flow features, with auxiliary supervision through a frozen pretrained video world model. Training relies entirely on publicly available data, expanded through human-to-robot synthesis, subtask annotation, and embodied chain-of-thought (ECoT) annotation. Across four simulation benchmarks, PDRVLA achieves success rates of 99.3% on LIBERO, 89.9% on LIBERO-Plus, 93.6% on RoboTwin~2.0, and 81.5% on SimplerEnv. Ablations show improved future prediction with world-model supervision and evaluate how subtask conditioning, future object-pose supervision, and ECoT training affect action success.
Shu Zhou, Ziyang He, Yuxin Rao, Yudong Fang, Jiali Qian, Dongyuan Chen, Juntao Zhang, Yong Hu
Financial agents are becoming an important class of real-world AI systems. Financial tasks vary widely in type and difficulty, and many are open-ended with no ground-truth answers. However, existing benchmarks neither capture this breadth and open-endedness nor separate grounding from correctness. To bridge this gap, we introduce $\textbf{AgenticFinBench}$, a benchmark of 230 real-world financial tasks spanning 8 categories, 2 languages, and 4 complexity levels. We also propose a reference-free evaluation framework that combines question-specific rubrics with a two-stage claim audit that detects hallucinations, defined as claims absent from the agent's trace and refuted by external evidence. This framework better matches how financial work is assessed in practice. Experiments across 18 agent configurations reveal three key findings: (1) Ignoring hallucinations can overstate agent performance: hallucination auditing lowers the baseline leader's score by 7.58 points and moves it to fourth place. (2) Harness differences explain more variation in evidence grounding than model differences (28.6% vs 8.8%). (3) Quality scores fall from 89.44 on direct retrieval to 79.18 on the most complex tasks. Case studies show that agents struggle to explain how events affect company profits or stock prices, compare financial data on a consistent basis, and justify their conclusions. By releasing AgenticFinBench, we aim to advance financial reasoning, factual verification, and agent design for more reliable responses to diverse real-world financial requests.
Domain-specific knowledge graphs (DKGs) are critical yet often suffer from limited coverage compared to General Knowledge Graphs (GKGs). Existing tasks to enrich DKGs rely primarily on extracting knowledge from external unstructured data or completing KGs through internal reasoning, but the scope and quality of such integration remain limited. This highlights a critical gap: little systematic exploration has been conducted on how comprehensive, high-quality GKGs can be effectively leveraged to supplement DKGs. To address this gap, we propose a new and practical task: domain-specific knowledge graph fusion (DKGF), which aims to mine and integrate relevant facts from general knowledge graphs into domain-specific knowledge graphs to enhance their completeness and utility. Unlike previous research, this new task faces two key challenges: (1) high ambiguity of domain relevance, i.e., difficulty in determining whether knowledge from a GKG is truly relevant to the target domain , and (2) cross-domain knowledge granularity misalignment, i.e., GKG facts are typically abstract and coarse-grained, whereas DKGs frequently require more contextualized, fine-grained representations aligned with particular domain scenarios. To address these, we present ExeFuse, a neuro-symbolic framework based on a novel Fact-as-Program paradigm. ExeFuse treats fusion as an executable process, utilizing neuro-symbolic execution to infer logical relevance beyond surface similarity and employing target space grounding to calibrate granularity. We construct new datasets to establish the first standardized evaluation suite for this task. Extensive experiments demonstrate that ExeFuse effectively overcomes domain barriers to achieve superior fusion performance.
Andrey Ignatov, Georgy Perevozchikov, Radu Timofte, Yuhong He, Yuxuan Qiu, Tianyu Hao, Ruoqi Li, Yueqi Yang 等 22 位作者
With the increasing importance of mobile camera quality in modern smartphones, growing attention has been directed toward computational photography and advanced image signal processing (ISP) algorithms aimed at enhancing various perceptual attributes of captured images. This creates a need for efficient deep learning models for this problem that are not only performant but can also be deployed on constrained mobile hardware. In this Mobile AI challenge, we address this problem and propose the participants to design fast solutions that can reconstruct RGB photos from RAW Bayer camera data while running on popular smartphone GPUs from Qualcomm and Arm. For this, the participants were provided with a large-scale Fujifilm UltraISP dataset consisting of RAW-RGB image pairs captured with the Sony IMX586 Quad Bayer mobile sensor and a professional 102MP medium format FujiFilm GFX100 camera. The runtime of all models was evaluated on the Snapdragon 8 Elite Gen 5 and Dimensity 9500 chipsets with the Adreno and Mali GPUs, respectively. Top solutions proposed in this challenge are able to reconstruct high-quality 5MP RGB image from raw data on both platforms under 100 milliseconds. A comprehensive description of the models developed in the challenge is provided in this paper.
Graphical user interface (GUI) agents can reuse past interaction experience. We study how illustrated procedures support action prediction and students deployed without retrieval. We introduce SkillLens, which represents procedures, applicability cues, and interface views in a shared Visual Skill Card (VSC) schema. Retrieved cards provide a frozen executor with reference evidence alongside the current screen. CardDistill uses this schema to construct privileged teacher context from labeled training steps for on-policy distillation; the student learns from native inputs and requires no retrieval at deployment. With matched training data and update counts, students trained with full-card teachers improve step success rate by an average of 5.04 percentage points over those trained with compact-text teachers across three training seeds on 119 tasks from ten websites absent from training. An independent runtime control uses training-source memory and pre-action retrieval queries: full cards achieve 12/64 correct actions (18.75%) versus 4/64 (6.25%) for text-only cards. These results establish the value of the complete VSC teacher-context package for retrieval-free students and provide evidence for pre-action retrieval of illustrated procedures.
Shenghao Ye, Yuxiang Wang, Yu Guo, Tao Zhang, Shuangwu Chen, Zijian Wen, Qihui Zhu, Mengjie Zhang 等 11 位作者
Large Reasoning Models (LRMs) achieve strong performance on table reasoning tasks but incur substantial inference cost due to long reasoning traces. Stepwise model routing mitigates this issue by dynamically assigning reasoning steps to smaller or larger models. However, stepwise model routing for table reasoning remains underexplored. Through empirical analysis, we find that reasoning steps involving tables contain two types of tokens with distinct uncertainty distributions: table tokens grounded in table structure, such as cell values and headers, and text tokens representing surrounding natural-language reasoning. The uncertainty of both token types is correlated with the risk that the model makes an error in the next reasoning step. However, existing methods fail to model them separately, leading to suboptimal routing decisions. To address this, we propose EcoTab, a table-aware stepwise routing framework for efficient table reasoning. At each reasoning step, EcoTab separately estimates the uncertainties of table tokens and text tokens, maps them to next-step failure risks for the small model, and combines the two risks for routing. Experiments on multiple table reasoning benchmarks show that EcoTab consistently outperforms strong baselines and achieves a better balance between accuracy and efficiency.
Shenghao Ye, Yu Guo, Zhengheng Li, Qiang Huang, Shuangwu Chen, Wang Luo, Qian Rui, Jie Zhang 等 13 位作者
Stepwise model routing improves the efficiency of Large Reasoning Models (LRMs) by assigning each reasoning step to a suitable model. Recent methods formulate routing as a sequential decision process and train the router with reinforcement learning. However, although they model routing as a process, they still supervise the router with outcome rewards. Such rewards only reflect final answer correctness and fail to evaluate intermediate routing decisions, which can weaken performance and generalization. To address this gap, we propose RoRo, a rubric-guided process reward framework for stepwise model routing. RoRo first collects diverse routing trajectories and constructs preference pairs based on outcome, cost, and process quality. It then trains a Rubricor to generate a query-specific evaluation rubric and a Judge to score routing trajectories under this rubric through alternating optimization. The resulting process rewards are combined with outcome rewards to optimize the routing policy via GRPO. Experiments on five reasoning benchmarks under both same-family and cross-family settings show that RoRo consistently outperforms strong baselines and achieves better accuracy and cost trade-offs.
One-step and few-step text-to-image generation must accurately render the details specified in the prompt despite limited opportunities for refinement. Distribution matching distillation (DMD) uses score differences to bring the generated distribution closer to a reference distribution. Following prior work, we estimate this difference with internal velocity branches, avoiding a separate fake-score network. We ask whether an explicit moment constraint improves this learned score supervision. A decomposition of the reverse-KL field into a Gaussian moment component and a non-Gaussian residual identifies statistics that can be constrained explicitly. We introduce Intrinsic Distribution Matching (IDM), which retains the full DMD correction and matches feature means and per-coordinate standard deviations using the generator's exponential-moving-average (EMA) copy, requiring no external feature encoder. Experiments use full-parameter and low-rank adaptation (LoRA) tuning on Z-Image-Turbo 6B and Qwen-Image 20B. At two network evaluations, IDM reaches 94.25% and 90.20% on Chinese and English LongText-Bench, the highest scores among the compared methods at this budget. Controlled ablations show gains from the added moment loss, while generator EMA features perform competitively with an external DINOv2 encoder across the five reported metrics. Code is available at https://github.com/inclusionAI/IDM.
Hailong Yan, Yongrui Zhang, Xiangtao Zhang, Le Zhang
We propose MorphSIG, a training-free framework that reformulates subject-driven image generation (SIG) as pseudo-video feature transport. MorphSIG contains two core modules: Progressive Decoupled Anchoring, which uses frequency-domain decoupling and structural scrambling during early denoising to break structural locking and enable a gradual transition from free composition to identity alignment; and Pseudo-flow Guided Feature Transport, which constructs a latent-space pseudo-flow field to mimic Image-to-Video temporal coherence and transport subject semantics precisely. To address stylistic homogeneity and the lack of ground truth in existing benchmarks, we further introduce a benchmark with diverse stylized subjects. Extensive experiments show that MorphSIG significantly improves pose diversity and subject fidelity over baselines without additional training. Overall, MorphSIG bridges static generation and dynamic propagation, providing a cost-effective paradigm for high-fidelity subject consistency.
Recent vision-language navigation (VLN) systems increasingly adapt pretrained vision-language models (VLMs) into vision-language-action (VLA) policies that map egocentric observations and language instructions directly to navigation actions. Although semantically capable, such action-centric training does not explicitly model how the agent's visual observations evolve under its predicted motion. Generative world-action models (WAMs) jointly predict future observations and actions, yet existing WAMs for continuous VLN do not condition joint future-view and action generation on geometry-aware representations inferred from the observation history. We present WNM-3D, a generative World Navigation Model with 3D scene conditioning for continuous VLN. A frozen feed-forward geometry encoder extracts cross-view representations from monocular RGB history, and a trainable 3D Scene-to-Token Adapter converts them into a fixed-length scene prefix for the world-action Diffusion Transformer. Through block-causal attention, this prefix remains visible to every future video-action block throughout joint denoising, providing persistent geometric context. We train WNM-3D with supervised world-action learning, DAgger-style adaptation on policy-visited states, and Counterfactual DanceGRPO refinement. Across GN-Bench and VLN-CE, WNM-3D consistently outperforms the backbone-matched WNM-2D counterpart, demonstrating gains from 3D scene conditioning across distinct visual domains. WNM-3D further outperforms strong VLN baselines on GN-Bench and demonstrates closed-loop deployment on a physical robot. Component and stage-wise ablations support the Adapter design and the complementary roles of DAgger-SFT and subsequent reward-guided refinement.
Long-horizon robotic tasks are commonly decomposed into semantic subgoals to simplify planning. However, subgoal progress in LLM-based planning is typically inferred implicitly from interaction histories. Inaccurate estimates can misguide execution and allow local errors to propagate. To address this, we propose ProLoop, a Progress-Aware Closed-Loop framework that derives explicit subgoal progress from structured relations between desired and execution states. A learned State-Relation Monitor assesses these relations, which are then aggregated into subgoal progress as ongoing, deviated, or completed. The resulting progress guides execution adaptation, enabling reliable progress-aware control throughout execution. Experiments on AgentBoard ALFWorld and a real-world robotic platform show that ProLoop improves success rate by 12.94% overall and by 15.46% on Hard tasks, while reducing environment interactions by 32.3%.
Wentao Zhang, Yilei Zhao, Guangyan Gan, Shuo Sun, Lin William Cong
Public disclosure repositories such as SEC EDGAR support informed investment through web access to corporate filings. Supporting their review with language model agents requires discovering unstated deficiencies across related documents, acquiring missing company facts, and verifying that requested revisions satisfy evidence-backed requirements. Existing financial question-answering evaluations provide limited evidence of these interactive capabilities. We introduce \textbf{FilingLoop}, an interactive benchmark and a self-evolving agent framework for corporate disclosure review and revision. Grounded in historical U.S.\ Securities and Exchange Commission correspondence, FilingLoop reconstructs 380 predominantly IPO review tasks from 96 companies under distinct information constraints. An evaluator separate from the acting agents scores final filings and responses against 6,099 eligible requirements and audits unsupported claims and harmful revisions. Our framework couples iterative review and revision within each case with procedural learning across cases, converting requirement-level evaluation feedback into role-specific guidance without updating model weights. Updates affect only subsequent cases, allowing procedural adaptation to be assessed without retrying scored tasks. On the evaluated stream, evolution increases requirement fulfillment from 24.28\% to 27.96\% and full comment resolution from 16.90\% to 20.75\%, with a 5.8\% increase in total cost over the fixed-policy variant. FilingLoop connects the concerns an agent discovers with the company facts it obtains and the revisions it commits, providing requirement-level feedback for procedures used in later review tasks.
Sihan Yang, Weichen Bai, Ruichuan An, Yiming Cheng, Zhiyuan Feng, Tianyi Jiang, Renye Yan, Ning Ding 等 12 位作者
As executable environments for language agents scale, generating and verifying their rollouts becomes increasingly expensive. Under finite rollout budgets, this raises an important question: can data management at the environment level make agentic reinforcement learning (RL) more efficient by organizing, evaluating, and scheduling task instances together with the environments that determine their tools, states, transitions, and verification? To address this question, we introduce EnvSched (Environment-aware Scheduling), an online scheduler that learns from rollout history. EnvSched assigns scheduling value through two complementary modeling choices: exploitation prioritizes tasks likely to provide informative reward differences, while coverage spreads each batch across underobserved environments and interaction patterns. EnvSched organizes environment--task pairs as nodes in a dual-relation graph, with within-environment edges capturing task semantics and shared tool, state, and verifier structure, and cross-environment edges capturing abstract execution and reward topology. By propagating historical rollout statistics along both edge types, it predicts within-task reward variance. These predictions guide a scheduler that allocates each batch to tasks with high predicted reward variance and underobserved environments and tasks. Environment quotas and a similarity penalty further limit concentration and redundancy, yielding informative and diverse batches without additional pilot rollouts. In RL on Qwen3-8B, EnvSched achieves an average score of 48.81 across BFCL-v3, tau-Bench, and ACEBench-Agent after 40 training steps, exceeding the highest score attained by random task selection after 120 steps. It also improves downstream performance across model sizes at the same training budget.
Diffusion video models produce striking clips, but they cannot reliably render an exact formula, a correct chart, a rule-consistent game or narration synchronized to on-screen events. A different route is emerging: multimodal agents that write code to render every frame and synthesize every sound. We introduce VibeVideoBench, a benchmark for evaluating agents on code-driven video generation. Its 239 self-contained tasks in English and Chinese span 12 categories, from data stories and music-driven pieces to classroom lessons and paper explainers; each asks an agent, running in its native harness inside a sandbox with no image or video generation model, to deliver a finished MP4 with sound within one hour. Evaluation is hierarchical and evidence-based: program checks of the delivery spec, about 13k task-specific rubric checks traced to the requirements they enforce, and five quality dimensions anchored per task, scored by three VLM judge panels. Across nine frontier agent systems and 2,151 scored rollouts, GPT-6 Astra and Claude Opus 5.5 rank first and second with both the judges and human annotators, and the strongest system satisfies every core requirement on 76.3% of tasks. Delivery is a second axis: counting missing videos as zero changes the ranking, and three quarters of the lost videos are final renders that started too late, ran too slowly or never started, a failure of how agents plan their hour. Agents build their own rendering pipelines and inspect their own frames, yet how much they look does not predict quality. The judges' ranking of the systems closely matches blind human preferences.
Large Language Models (LLMs) are widely adopted for reflective error correction in task planning; however, existing approaches primarily rely on autonomous exploration, rendering them prone to accumulating erroneous experiences during early interactions with new environments. To address this limitation, we propose the Flexible Instructional Scaffolding Reflection Framework (FISRF), an agent--mentor architecture that estimates the robot's Zone of Proximal Development (ZPD) in task planning and adaptively selects reflection strategies and mentor guidance, thereby facilitating the accumulation of effective error-correction experience. Experiments in ALFWorld and on real-world robotic platforms demonstrate that FISRF reduces the average number of error-correction rounds by 37% and redundant reasoning by 25.1%, while improving the overall task success rate by 8%. Project webpage : https://fisrfplanning.github.io/
Jinhu Qi, Minda Hu, Wentao Zhang, Zixing Song, Irwin King
AI assistants are increasingly asked to reason over a user's own web traces: group chats, community threads, activity logs and revision histories. On CL-bench Life, a benchmark of such real-life context learning, frontier LLMs solve fewer than one task in five. We find that the request is not the specification: over 80% of the benchmark's rubrics share less than 60% of their content words with the final request, as for a rule set two turns earlier or every record that meets the user's criterion, and LLMs answering directly pass only 67% of these implicit rubrics against 81% of the others. We propose QERA, a Question-driven Evidence Reasoning Architecture that asks before it answers. QERA first turns the request into a requirement checklist and typed information needs, filtered by code for faithfulness to the user's words; it then answers from the whole conversation, asks the same questions again with quotes verified by code, and applies a guarded local repair. It needs no training or rubrics and makes about four LLM calls per task. On all 405 tasks with four frontier LLMs, QERA attains the highest solving rate on every LLM (21.0% on average, against 18.2% for the strongest of three inference-time baselines and 14.6% for direct answering) and leads every baseline significantly when pooled across LLMs, while using fewer tokens than PSCI and 4-5% of the tokens of Ctx2Skill. Ablations on GPT-6-Luna show that the gain is settled before the answer, by a fixed answer protocol (+3.8 rubric points) and the request-specific questions (+1.6), and that it is concentrated on implicit rubrics, with checking afterwards refining mainly numeric requirements.
Hesong Li, Ying Fu, Ziqi Wu, Ruiwen Shao, Tao Zhang
Scanning Transmission Electron Microscopy (STEM) enables the observation of atomic arrangements at sub-angstrom resolution and plays a key role in the discovery and characterization of advanced materials. Raw STEM images are often noisy and blurred due to multiple degradations. Although recent deep learning methods improve STEM images, their performance remains limited under severe degradations. In this work, we propose a spatial-frequency learning framework for STEM image enhancement. Specifically, we design a spatial-frequency fusion network that exploits periodic atomic arrangements in the frequency domain and restores local atomic details in the spatial domain. Spatial- and frequency-domain features are enhanced separately and then fused. We also present a STEM noise calibration method for synthesizing more realistic STEM images. The parameters of scan noise, pointwise noise, and background noise are estimated through statistical analysis and fitting of real STEM images. Using these calibrated parameters, we construct a diverse dataset containing a wider range of atomic arrangements, imaging modes, and degradations. Random masks combine different atomic arrangements to simulate interfaces between multiple materials. Experimental results demonstrate that our method achieves state-of-the-art enhancement performance on synthetic datasets and real images of advanced materials while improving atomic localization accuracy.
Jianyi Hu, Hangtao Zhang, Yi Liu, Yeqi Zeng, Li Zeng, Xianlong Wang, Rui Wang, Leo Yu Zhang
Typed decision models (TDMs), such as Jev, answer a question about an input with a probability, an option, or an ordinal level. Web services execute these decisions automatically above a confidence threshold. An attacker who writes part of the input can change a decision that the service then executes. Current adversarial benchmarks cannot measure this risk, because they judge generated text. A TDM writes no text, and its wrong decisions have a valid format. We present JevAdvBench, to our knowledge the first unified benchmark for the adversarial robustness of TDMs. It contains 862 questions with audited answers and twelve black-box attack methods that edit the input or the options by adaptive search. Because a changed decision is not always wrong, a review keeps only 5,586 answer-preserving variants, and we attack only correct decisions. The attacks flip 46.3% of Jev's correct decisions, while identical re-runs flip only 0.17%. A flawed argument without a command flips 77.2%, close to direct prompt injection at 92.0%. The same variants flip 34.0% to 51.7% of correct decisions on eight open TDMs. At a 0.8 threshold, 23.5% of the decisions that the service still executes are wrong. On Agentgateway, the Jev guardrail rejects a jailbreak request but accepts it with an inserted argument. Web services should therefore treat TDM inputs as untrusted and should not act on confidence alone. Project website: https://JevAdvBench.github.io/JevAdvBench/
Hongcheng Gao, Zelin Zheng, Alex Zhou, Jay Zhu, Shijia Ge, Yazhe Wang, Xiping Li, Jianshu Zeng 等 21 位作者
Embodied agents are expected to accomplish real-world goals by deciding for themselves how and when to interact with their surroundings. For many such goals, changing the physical state of the world is the means rather than the end: the agent changes the state of a system through interaction, observes the feedback, and explores until it either achieves the goal itself (e.g., discovering physical laws) or learns what the goal requires; it acts to know. Manipulation benchmarks stop at acting to change, with the target state given; scientific discovery benchmarks evaluate knowing but replace physical experimentation with symbolic actions or numerical queries. We introduce EmbodiedLab, a benchmark in which a robot must act to know. Quantitative science experiments make this setting controllable: the parameters of the system are resampled for every instance, so the result cannot be known in advance, yet it can be scored exactly. Across 30 experiments in five disciplines on 14 apparatus platforms, the agent receives an objective and the apparatus, chooses its own procedure, and operates a physics-based simulated laboratory, reading the instruments through its cameras. Evaluation checks what the agent came to know, grounded in readings recorded during the episode, as well as the physical state the task requires; every experiment is verified to be solvable. We evaluate six frontier models in their developers' coding agents with native observation and control, with added perception and motion planning, and with manipulation skills distilled from the strongest agents. With native control, even the strongest agent succeeds less than half the time; for every agent, most failures arise in interacting with the apparatus, and manipulation skills help weaker agents more than perception and planning. The benchmark and its evaluation code are available at https://github.com/HexaFuture/EmbodiedLab.
Web agents reuse skills whose stored code, selected version, and loaded implementation can diverge across tasks and updates. SkillLifeBench links these states to task outcomes in 388 paired scenarios spanning implementation, interface, runtime, composition, and version changes. We evaluate 14 models on two paired decision tracks: 89 runtime tasks and 60 autonomous lifecycle tasks spanning 12 templates derived from introduced cases. Lifecycle tasks allow agents to inspect, select, and reconfigure skills while completing verifiable user requests. Joint success requires task completion without the registered attack goal. GPT-5.6-Sol and Sonnet 4.6 both achieve 82.0% on runtime tasks, but reach 96.7% and 56.7% on lifecycle tasks. Across lifecycle evaluations, challenged task success is 77.5%, while joint success is 65.2%; 103 runs complete the task and the attack goal. Adding execution provenance in a matched recovery study raises utility joint success from 49.35% with logs and metadata to 65.58%. A deterministic execution-consistency rule reaches 64.94% with higher benign utility, while full restoration reaches 69.48%. Lifecycle tasks distinguish models with similar runtime scores, and execution evidence improves recovery.
Yijun Zhou, Minghao Shao, Ke Zhang, Renkai Yuan, Hongbo Yuan, Bin Hu, Bozhao Qian, Hongxia Shen 等 23 位作者
Game development stresses coding agents in ways general software engineering does not: correctness depends on how engine APIs, serialized scene state, and runtime behavior interact, not on source code alone. Existing benchmarks mainly target platforms such as Godot and heavily rely on LLM judges or coarse task-level outcomes. We present UnityBench-Mini3D, a benchmark of 77 project-level Unity tasks organized around seven expert-defined skill categories rather than tutorials or genres, with three difficulty tiers. Each task pairs a complete Unity project with natural-language requirements and is evaluated using 1,178 held-out, human-authored milestone tests covering scene structure, component configuration, and runtime behavior. This in-engine evaluation provides deterministic partial credit, localizes failures, and distinguishes partial implementations from complete solutions without relying on subjective judges. Across 21 models and 9 coding harnesses, the average pass rate reaches 80.9% on easy tasks but falls to 35.2% on hard tasks, with just 57.7% overall. UnityBench-Mini3D provides a reproducible, diagnostic testbed distinguishing systems across difficulty levels.
Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He 等 59 位作者
We introduce MinerU2.5, a 1.2B-parameter document parsing vision-language model that achieves state-of-the-art recognition accuracy while maintaining exceptional computational efficiency. Our approach employs a coarse-to-fine, two-stage parsing strategy that decouples global layout analysis from local content recognition. In the first stage, the model performs efficient layout analysis on downsampled images to identify structural elements, circumventing the computational overhead of processing high-resolution inputs. In the second stage, guided by the global layout, it performs targeted content recognition on native-resolution crops extracted from the original image, preserving fine-grained details in dense text, complex formulas, and tables. To support this strategy, we developed a comprehensive data engine that generates diverse, large-scale training corpora for both pretraining and fine-tuning. Ultimately, MinerU2.5 demonstrates strong document parsing ability, achieving state-of-the-art performance on multiple benchmarks, surpassing both general-purpose and domain-specific models across various recognition tasks, while maintaining significantly lower computational overhead.
尚无 AI 解读，展示原文摘要
cs.CL · cs.CV
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track) · 2026 · 正式发表
Information-seeking (IS) agents have achieved strong performance across a range of wide and deep search tasks, yet their tool use remains largely restricted to API-level snippet retrieval and URL-based page fetching, limiting access to the richer information available through real browsing. While full browser interaction could unlock deeper capabilities, its fine-grained control and verbose page content returns introduce substantial complexity for ReAct-style function-calling agents. To bridge this gap, we propose Nested Browser-Use Learning (NestBrowse), which introduces a minimal and complete browser-action framework that decouples interaction control from page exploration through a nested structure. This design simplifies agentic reasoning while enabling effective deep-web information acquisition. Empirical results on challenging deep IS benchmarks demonstrate that NestBrowse offers clear benefits in practice. Further in-depth analyses underscore its efficiency.
尚无 AI 解读，展示原文摘要
cs.CL · cs.AI
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Tao Feng Zhejiang University, Xinke Jiang, Xinyan Hu, Yonggang Zhang, Zhen Tao Harbin Institute of Technology, Shenzhen, Wentao Zhang, Boyang Liu, Wenhao Jiang Harbin Institute of Technology 等 9 位作者
Agentic search augments large language models (LLMs) with external knowledge through reinforcement learning. However, existing approaches suffer from blind reliance on noisy retrieval and hallucination when both parametric and external knowledge fail—reflecting a lack of calibration regarding the model’s knowledge boundary. We propose Knowledge boundary Policy Optimization (KbPO), a reinforcement learning framework that explicitly aligns retrieval decisions with quantified knowledge states. KbPO introduces: (1) a semantic stability metric to delineate reliable parametric knowledge; (2) a four-quadrant taxonomy synthesising internal certainty with retrieval quality; and (3) a quadrant-based reward mechanism incentivising calibrated behaviour. We further adopt an iterative query evolution pipeline to construct boundary-probing training samples. Experiments on ten benchmarks demonstrate that KbPO outperforms strong baselines while exhibiting reduced hallucination rates.
尚无 AI 解读，展示原文摘要
cs.CL · cs.AI
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Yanhao Li, Lu Ma, Jiaran Zhang Harbin Institute of Technology, Lexiang Tang, Wentao Zhang, Guibo Luo Peking University
Large Language Models (LLMs) often produce unnecessarily lengthy reasoning traces, which significantly increase computational cost and latency. Existing approaches typically rely on fixed length penalties, but such penalties are hard to tune and fail to adapt to the evolving reasoning abilities of LLMs, leading to suboptimal trade-offs between accuracy and conciseness. To address this challenge, we propose LEASH (adaptive LEngth penAlty and reward SHaping), a reinforcement learning framework for efficient reasoning in LLMs. We formulate length control as a constrained optimization problem and employ a Lagrangian primal–dual method to dynamically adjust the penalty coefficient. When generations exceed the target length, the penalty is intensified; when they are shorter, it is relaxed. This adaptive mechanism guides models toward producing concise reasoning without sacrificing task performance. Experiments on Deepseek-R1-Distill-Qwen-1.5B and Qwen3-4B-Thinking-2507 show that LEASH reduces the average reasoning length by 60% across diverse tasks—including in-distribution mathematical reasoning and out-of-distribution domains such as coding and instruction following—while maintaining competitive performance. Our work thus presents a practical and effective paradigm for developing controllable and efficient LLMs that balance reasoning capabilities with computational budgets.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Wentao Zhang, Yan Zhuang Tencent, ZhuHang Zheng, Mingfei Zhang, Jiawen Deng University of Electronic Science and Technology of China, Fuji Ren University of Electronic Science and Technology of China
Existing jamming attacks on Retrieval-Augmented Generation (RAG) systems typically induce explicit refusals or denial-of-service behaviors, which are conspicuous and easy to detect. In this work, we formalize a subtler availability threat, termed soft failure, which degrades system utility by inducing fluent and coherent yet non-informative responses rather than overt failures. We propose Deceptive Evolutionary Jamming Attack (DEJA), an automated black-box attack framework that generates adversarial documents to trigger such soft failures by exploiting safety-aligned behaviors of large language models. DEJA employs an evolutionary optimization process guided by a fine-grained Answer Utility Score (AUS), computed via an LLM-based evaluator, to systematically undermine the certainty of answers while maintaining high retrieval success.Extensive experiments across multiple RAG configurations and benchmark datasets show that DEJA consistently drives responses toward low-utility soft failures and that the resulting adversarial documents maintain high stealth and effectiveness, proving resilient against common mitigation strategies including perplexity-based detection and input perturbations.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Han Weng, Zhou Liu, Yuanfeng Song ByteDance Inc., Xiaoming Yin ByteDance Inc., Xing Chen ByteDance, Wentao Zhang
In real-world business environments, data is stored in a variety of sources, including structured relational databases, semi-structured databases, and unstructured files. The ability to extract reasonable insights across these diverse sources is integral to data-driven decision-making. Existing benchmarks, however, are limited in assessing agents’ capabilities across these diverse data types. To address this gap, we introduce UniDataBench, a multi-source benchmark designed to evaluate the performance of data analytics agents in handling diverse data sources. Specifically, UniDataBench is constructed based on real-life industry analysis reports, employing a pipeline to synthesize data that aligns with authentic analytical trends. It encompasses diverse datasets spanning relational databases, CSV files, and NoSQL stores to reflect real-world business settings, and provides a unified framework for evaluating how effectively agents can explore multiple data formats, extract insights, and generate meaningful summaries and recommendations. Based on UniDataBench, we propose a novel LLM-based agent named ReActInsight, an autonomous agent that performs end-to-end analysis over diverse data sources by automatically discovering cross-source linkages, decomposing goals, and generating robust, self-correcting code to extract actionable insights. Our benchmark and agent together provide a framework for facilitating the development of data analytics agents in real-world applications.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Jiawen Deng University of Electronic Science and Technology of China, Wei Li, Wentao Zhang, Ziyun Jiao, Fuji Ren University of Electronic Science and Technology of China
Intelligent dialogue systems are increasingly deployed in emotionally and ethically sensitive settings, where failures in either emotional attunement or ethical judgment can cause significant harm. Existing dialogue models typically address empathy and ethical safety in isolation, and often fail to adapt their behavior as ethical risk and user emotion evolve across multi-turn interactions. We formulate ethical-emotional alignment in dialogue as an explicit turn-level decision problem, and propose EthicMind, a risk-aware framework that implements this formulation in multi-turn dialogue at inference time. At each turn, EthicMind jointly analyzes ethical risk signals and user emotion, plans a high-level response strategy, and generates context-sensitive replies that balance ethical guidance with emotional engagement, without requiring additional model training. To evaluate alignment behavior under ethically complex interactions, we introduce a risk-stratified, multi-turn evaluation protocol with a context-aware user simulation procedure. Experimental results show that EthicMind achieves more consistent ethical guidance and emotional engagement than competitive baselines, particularly in high-risk and morally ambiguous scenarios.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表