跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1471新增论文
+1164其中 AI 相关
+159已有论文修订
+97新增 AI 导读

arXiv 最近完成扫描:2026-11-20 08:48 · 全站最近入库:2026-11-20 12:52各信源进度 →

统计口径与数据新鲜度

统计 2026-11-19 14:31 — 2026-11-20 14:31(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-20 08:48最近发现新增版本:2026-11-20 12:52库内论文最新更新时间:2026-11-20 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

28,342 已收录论文23,539 AI 相关8,682 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 51 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 08:46(北京时间)
新论文 · v1arXiv:2611.26444

Mind2Act World: A Diagnostic Benchmark for Embodied Mind, Physical Action, and Mind-Action Composition in Robotic Manipulation

Yuzhi Huang, Jie Wu, Fanding Huang, Junchao Lin, Weichen Zhang, Ziyi Xiong, Yang Li, Zhengwei Xie 等 43 位作者

原文摘要

Embodied intelligence aims to let robots perform complex physical tasks with human-like adaptability and reliability, which requires three complementary capabilities: history-based cognitive reasoning, precise and timely physical execution, and the composition of reasoning and execution through environmental feedback. Yet existing benchmarks either evaluate reasoning and execution within the same tasks or assess them separately without their composition, so they reveal little about whether a failure comes from reasoning, execution, or their composition. We introduce Mind2Act World, a diagnostic benchmark of 30 simulated manipulation tasks from five real-world application domains. Each task has three difficulty levels and two scene settings (Clean and Random), yielding 180 configurations. The tasks form three views: Mind tests decisions based on past observations, Act tests precise and timely execution, and Mind2Act combines both in closed-loop tasks where action outcomes guide later decisions. Comparing the three views shows whether a system lacks a capability or fails to compose capabilities it already has. A diagnosis harness further attributes the failed episodes of three representative systems to Mind, Act, or their composition and summarizes each system in a profile card. Our evaluation of multimodal agents, vision-language-action models (VLAs), and world-action models (WAMs) shows that competence in a single view does not carry over to Mind2Act tasks. Even the strongest agent succeeds in 52.7% of Mind and 39.0% of Act episodes but in only 12.0% of Mind2Act episodes. The strongest agent retains task state but struggles with sustained contact, whereas end-to-end policies execute practiced motions but retain little task state. These findings point to composing reasoning and execution through environmental feedback as the main open problem.

cs.RO · cs.AI · cs.CV

新论文 · v1arXiv:2611.24915

PrismRestore:面向智能体图像恢复的紧凑恢复工具箱

PrismRestore: A Compact Restoration Toolbox for Agentic Image Restoration

Zhaocheng Yu, Kui Jiang, Jing Cao, Yiang Chen, Xiaocheng Feng, Junjun Jiang, Xianming Liu

AI 速读 基于摘要

PrismRestore 从单个冻结的全能模型中构建紧凑的可调用恢复动作库,并用状态条件策略组合动作,以单骨干实现智能体图像恢复。

cs.CV

查看原文摘要

Agentic image restoration composes operations to handle mixed degradations, yet its toolbox often requires storing multiple restoration networks. We propose PrismRestore, which constructs a compact bank of callable restoration actions from a single frozen all-in-one model. Our approach builds on task-dependent yet overlapping channel responses in the shared model. An offline task-prior search uses activation and gradient statistics to group channels with similar response profiles, then searches task-specific modulation coefficients over non-representative channels while leaving representative channels unmodulated. The resulting prior bank enables explicit action selection and composition without additional restoration backbones or task-specific adapter modules. A state-conditioned policy learns to compose these actions using Group Relative Policy Optimization. Its objective separately normalizes fidelity and perceptual feedback within groups of trajectories sampled for the same input, and combines terminal evaluation with return-to-go derived from stepwise quality changes. Experiments on synthetic composite-degradation and real-world multi-task benchmarks show improvements over the evaluated all-in-one baselines and restoration quality competitive with multi-model agents. PrismRestore achieves these results with a single restoration backbone and faster inference than the evaluated agentic baselines.

新论文 · v1arXiv:2611.24193

WM^MLLM: Turning MLLMs into World Models

Baiang Li, Enze Xie, Jincheng Yu, Jin Wang, Haozhe Liu, Yitong Li, Juanxi Tian, Felix Heide

原文摘要

Video world models keep the world in the context of a generator, so a revisit is synthesized again and earlier edits can drift or disappear. We present WM^MLLM, the first interactive world model built on multimodal large language models (MLLMs), for persistent, editable world generation from a single image. WM^MLLM keeps the world state outside every generator, as a panorama with a revision history, and lets the MLLMs write it: they turn each request into operations on this state, select where a local edit is written, and check every candidate before it becomes the next state. Image generators only propose views, and video only presents them. Users can walk to new places and return, edit objects through text or a box, place subjects, and change lighting, weather or season. By construction, a revisit at the same revision reproduces the earlier view exactly, a local edit leaves every panorama pixel outside its region unchanged, and each request starts from the result of the previous one. Against six world model baselines on MBench-A, WM^MLLM has the highest mean on all four environment-recovery metrics (Epipolar 91.5 versus 0.1 to 74.0) and completes the most camera round trips (85.3% versus at most 50.9%). It has the best value in all 15 CompBench columns against 15 baselines. On 112 local edits judged blind, selecting the region to write after generation raises completion from 34.8% to 83.0%. On 258 WBench and MBench-A items, all 46 revisits recover their earlier views, and all 97 local edits that pass the check leave panorama pixels outside their region unchanged.

cs.CV

版本更新 · v2arXiv:2411.02871

Survival of the Fittest Perturbations: Uncertainty-Aware Evolution of Adversarial Distributions for Robust Generalization

Junhao Dong, Zicheng Yu, Xinghua Qu, Z. Jane Wang, Yew-Soon Ong

原文摘要

Despite deep learning's broad successes across diverse scenarios, its vulnerability to adversarial examples impedes deployment, making adversarial training a leading approach to improve robustness. However, pointwise adversarial training maps each clean sample to a single adversary, overlooking surrounding adversarial variability and the associated shifts in feature statistics. To address these issues, we propose Evolutionary Uncertainty-Aware Distributional Adversarial Training (EvoUAD-AT). Specifically, we design an evolutionary adversarial uncertainty modeling module that maintains an instance-wise search distribution over adversarial feature statistics around an adversarially generated anchor. Candidates are evaluated under the current model, selected by their threat to a benign reference, and used to adapt the distribution; strategy parameters are retained across epochs. To avoid anchoring on misclassified clean samples, we refine the alignment reference and match benign and adversarial distributions. Introspective gradient matching further regularizes input gradients without external supervision. Our analysis characterizes the elite fitness surrogate and gives a conditional certificate for latent adversarial features. Extensive evaluations across multiple benchmarks demonstrate that our approach consistently outperforms existing state-of-the-art methods in both clean accuracy and robustness, with thorough analyses confirming the effectiveness of each proposed component.

cs.LG · cs.CV

版本更新 · v2arXiv:2601.13304

CausalSpatial: A Benchmark for Object-Centric Causal Spatial Reasoning

Wenxin Ma, Chenlong Wang, Ruisheng Yuan, Hao Chen, Nanru Dai, S. Kevin Zhou, Yijun Yang, Alan Yuille 等 9 位作者

原文摘要

Humans can look at a static scene and instantly predict what happens next -- will moving this object cause a collision? We call this ability Causal Spatial Reasoning. However, current multimodal large language models (MLLMs) cannot do this, as they remain largely restricted to static spatial perception, struggling to answer "what-if" questions in a 3D scene. We introduce CausalSpatial, a diagnostic benchmark evaluating whether models can anticipate consequences of object motions across four tasks: Collision, Compatibility, Occlusion, and Trajectory. Results expose a severe gap: humans score 84% while GPT-5 achieves only 54%. Why do MLLMs fail? Our analysis uncovers a fundamental deficiency: models over-rely on textual chain-of-thought reasoning that drifts from visual evidence, producing fluent but spatially ungrounded hallucinations. To address this, we propose the Causal Object World model (COW), a framework that externalizes the simulation process by generating videos of hypothetical dynamics. With explicit visual cues of causality, COW enables models to ground their reasoning in physical reality rather than linguistic priors. We make the dataset and code publicly available here: https://github.com/CausalSpatial/CausalSpatial

cs.CV

版本更新 · v2arXiv:2611.01543

GSExplorer: Interactive World Generation with a Persistent 3DGS World State

Sicheng Yu, Liu Liu, Xinjie Wang, Xinjiang Wang, Taojun Ding, Wenhao Hu, Beizhen Zhao, Puxin Yan 等 10 位作者

原文摘要

Interactive world generation requires both accurate local control and stable scene consistency over long rollouts. Existing methods improve local generation through camera or geometry conditioning and extend historical context with memory mechanisms. However, long-horizon exploration remains challenging due to incomplete target-view guidance and inconsistencies accumulated during scene updates. We present \textbf{GSExplorer}, a generation--reconstruction framework built around a persistent 3D Gaussian world state. At each step, the current 3DGS scene provides multimodal rendering conditions for a video generator, while camera geometry is injected through a separate Relative Ray Encoding branch. Generated videos are then fed back to a SLAM-based reconstruction backend, where appearance and geometric consistency checks produce a shared support mask for selective scene updates and cross-chunk pose refinement. We further design a data-construction pipeline that reproduces realistic 3DGS degradation during scene extrapolation, yielding 293K training pairs of degraded multimodal renderings and real target videos. GSExplorer achieves the best overall performance among the compared methods on both single-step and three-step WorldScore evaluation, including a Camera Control score of 99.07 in single-step extrapolation. On 481-frame leave-and-return rollouts, it also shows strong revisit consistency.

cs.CV · cs.AI

版本更新 · v2arXiv:2611.14808

OverServe: Resource Amplification Attacks on SaaS Agents via Tool--Prompt Co-Design

Ruiheng Yu, Oteo Mamo, Siyu Gan, Weikuan Yu, Mulong Luo

原文摘要

Advances in large language models (LLMs) are enabling software-as-a-service (SaaS) providers to automate longer business workflows with agents. In subscription-based SaaS deployments, model and tool calls consume provider resources without additional customer payments. Because the agent autonomously decides when to stop, a malicious tenant can send a prompt to the agent, exploiting its completion decisions to extend execution and waste provider resources. In this paper, we present OverServe, a multi-agent framework for constructing such attacks against SaaS agents. OverServe co-designs Model Context Protocol (MCP) status tools and completion-confirmation prompts for the attacker. Each tool call returns accurate status and terminates normally, yet the agent may repeatedly check an unfinished condition to satisfy the prompt. This consumes the SaaS provider's resources even after the original business task is completed. OverServe constructs service-specific tool--prompt pairs and uses separate tool and prompt reviews to guide candidate pair selection. Tested tool specifications trigger no alerts in the evaluated MCP scanners. We evaluate Qwen, Nemotron, DeepSeek, and Sonnet on selected tasks from nine benchmarks. All OverServe runs pass the original task checks. OverServe can reach a maximal amplification of API requests by $93.88\times$ while preserving the original task goal and collateral checks.

cs.CR · cs.AI · cs.SE

版本更新 · v2arXiv:2610.40349

TouchBridge: Tactile-Conditioned Human-to-Robot Transfer for Dexterous Manipulation

Haozhe Zhang, Gu Zhang, Zirui Zou, Yuzheng Chen, Jinlong Wu, Zixuan Hu, Jianke Zhang, Yucheng Hu 等 10 位作者

原文摘要

Human demonstrations offer an efficient and scalable source of data for dexterous robot manipulation, but differences in sensing and hand morphology complicate the transfer of contact-rich interactions. We present TouchBridge, a hardware--software co-designed framework for human-to-robot data transformation. A wearable human demonstration interface and a corresponding robot interface establish cross-embodiment correspondence in visual and fingertip tactile sensing. We introduce Tac-Retarget, a tactile-conditioned retargeting method that uses measured contact to align fingertip contact patches and preserve their spatial relations within and across hands. Unlike object-aware or simulation-based transfer pipelines, Tac-Retarget requires no object mesh, object-pose estimate, or physics simulation for retargeting, enabling direct and scalable conversion of human demonstrations into robot-domain training data. Combined with visual synthesis and camera-anchored action conversion, TouchBridge produces robot-domain demonstrations for fine-tuning a pretrained vision-language-action (VLA) model. Across four real-world contact-rich tasks, policies fine-tuned solely on TouchBridge-converted human demonstrations achieve a 72.5% average success rate, compared with 77.5% using an equal number of teleoperated robot demonstrations, while human demonstration collection is 7.0x faster. Under the same policy and training setup, Tac-Retarget outperforms DexPilot and UniDex by 25.0 and 42.5 percentage points, respectively.

cs.RO

版本更新 · v2arXiv:2610.42012

3SUM Made Simpler (Without Matrix Multiplication), $k$-SUM Hypothesis Refuted for Odd $k$, and Real 3SUM/APSP Derandomized

Timothy M. Chan, Reina Itakura, Zhiyuan Ma, Yuancheng Yu

原文摘要

Recently, a truly subquadratic algorithm for the 3SUM problem and a truly subcubic algorithm for the all-pairs shortest paths (APSP) problem were found by Anthropic, as reported by Alman and Vassilevska Williams (2026). These algorithms relied on a new subroutine for rectangular matrix multiplication with selected output entries, which was obtained by modifying known matrix multiplication techniques of Schönhage (1981) and Coppersmith (1982). 1. We present a different truly subquadratic randomized algorithm for 3SUM for integer inputs. It completely avoids the use of matrix multiplication but instead modifies known dynamic programming algorithms for subset convolution and the zeta transform, which rely only on simple subtraction tricks via inclusion--exclusion (and does not even require fast Fourier transform), and so is conceptually easier to understand (the whole solution is about 5 pages long). 2. Following a similar approach, we obtain a randomized algorithm for $k$-SUM for integer inputs for odd constant $k$ in $O(n^{\lceil k/2\rceil-\varepsilon_k})$ time for some constant $\varepsilon_k>0$, disproving the $k$-SUM Hypothesis for all odd $k$. 3. Existing reductions from 3SUM and APSP to selected-entries rectangular matrix multiplication were randomized in the case of real-valued input. We present new deterministic reductions, yielding a truly subquadratic deterministic algorithm for Real 3SUM and a truly subcubic deterministic algorithm for Real APSP.

cs.DS

新论文 · v1arXiv:2611.18067

Agent-as-a-Judge

Runyang You, Hongru Cai, Caiqi Zhang, Qiancheng Xu, Meng Liu, Tiezheng Yu, Yongqi Li, Wenjie Li

原文摘要

Artificial intelligence has progressed from task-specific systems toward general models spanning perception, generation, reasoning, and autonomous interaction, making reliable evaluation essential for comparison, deployment, and post-training feedback. At scale, modern evaluation pipelines increasingly rely on LLM-as-a-Judge to produce scores, preferences, and critiques; in its fixed-context setting, the judge relies on the supplied evaluand and evaluation materials. Yet a reliable verdict may require evidence beyond the supplied evaluand and context---either because critical environmental states remain unrecorded in the static execution log, or because controversial factual claims require external verification. Passive judges cannot obtain that missing evidence before deciding, especially when evaluating agent trajectories, executable artifacts, or domain-specific reports. Recent work therefore develops active evaluators that seek missing evidence and update their grounds for judgment before deciding. We bring these advances together through Agent-as-a-Judge, focusing on how evaluators construct and control checking processes within the broader LLM-based judging landscape. We define the scope through evaluation-directed checks and the use of their results, covering both structured workflows and observation-driven control. We organize the design space by multi-agent collaboration, tool integration, memory, and planning, and show how these mechanisms supply the checks and evidence on which a verdict rests. We consolidate published scores and reproduce missing entries for key agentic judges; the comparison reveals uneven agentic gains and motivates dedicated agentic evaluation. We conclude by characterizing application demands and open challenges in cost, reliability, safety, and governance that condition trusted deployment of agentic judges at scale.

cs.CL

版本更新 · v5arXiv:2603.28590

MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Models

Han Wang, Yifan Sun, Brian Ko, Mann Talati, Jiawen Gong, Zimeng Li, Naicheng Yu, Xucheng Yu 等 11 位作者

原文摘要

Large language models (LLMs) can generate chains of thought (CoTs) that are not always causally responsible for their final outputs. When such a mismatch occurs, the CoT no longer faithfully reflects the actual reasons (i.e., decision-critical factors) driving the model's behavior, leading to the reduced CoT monitorability problem. This limits the use of CoTs for reliable oversight. However, a comprehensive and fully open-source benchmark for thoroughly evaluating CoT monitorability remains lacking. To address this gap, we propose MonitorBench, a systematic benchmark for evaluating CoT monitorability in LLMs. MonitorBench provides: (1) a diverse set of 1,540 test instances with carefully designed decision-critical factors across 19 tasks spanning 7 categories to characterize when CoTs can be used to monitor the factors driving LLM behavior; and (2) two prompting stress-test settings to quantify the extent to which CoT monitorability can be degraded. Extensive experiments show that CoT monitorability is a conditional property affected by the evaluated LLM, monitor LLM, and task characteristics. Across these factors, monitorability is higher when decision-critical factors shape the intermediate reasoning process, rather than merely influencing the final answer. Under stress-test prompting, most evaluated LLMs can intentionally reduce monitorability, mainly on tasks where decision-critical factors are not structurally required by the reasoning process. Overall, MonitorBench provides a basis for further research on AI control, reasoning faithfulness, stress-test monitorability, and monitoring scaffords. The code is available at https://github.com/ASTRAL-Group/MonitorBench.

cs.AI

版本更新 · v2arXiv:2609.39118

Diagnosing On-Policy Self-Distillation for Reasoning Language Models

Yang Li, Gongle Xue, Yuheng Yuan, Yijia Guo, Shizhe Zhang, Liwen Hu, Lei Ma

原文摘要

On-policy self-distillation (OPSD) has attracted growing interest as a promising approach to improve the reasoning ability of language models. Without external rewards nor a separate stronger teacher, the self-teacher with privileged information could provide dense signals on student's trajectories. However, its behavior in language reasoning remains unclear, with reported outcomes ranging from modest gains to behavioral collapse. In this work, we diagnose OPSD for mathematical reasoning across models spanning 0.6B--8B parameters. We conduct controlled experiments and token-level analyses to fully delve into OPSD. We point out that teacher's signal is shaped by reasoning-mode alignment and the complete teacher prefix, rather than by privileged semantics alone. OPSD improves reasoning only in narrow compatibility regimes. Otherwise, it produces ineffective length growth, stable degradation, or behavioral collapse. Token-level analysis shows that teacher's signal is not stable and does not predict downstream performance. Based on these results, we argue that OPSD is a sensitive algorithm rather than a generally reliable reasoning-improvement post-training method.

cs.CL

新论文 · v1arXiv:2611.14257

Elastic-WAM:面向高效机器人控制的自适应时空想象

Elastic-WAM: Adaptive Spatiotemporal Imagination for Efficient Robot Control

Haitian Li, Tianfu Li, Xuxi Zhao, Zizheng Liu, Yangcheng Yu, Yiwen Hou, Zeyu Xiao, Mutian Xu 等 11 位作者

AI 速读 基于摘要

提出 Elastic-WAM,用统一时空细化需求场自适应分配世界模型的计算,在降低推理开销的同时提升机器人控制表现。

cs.RO · cs.CV

查看原文摘要

World-Action Models improve robot control by predicting future visual dynamics, but iterative video denoising incurs substantial inference overhead. Recent approaches reduce this cost through partial future denoising, yet typically rely on fixed refinement budgets. Our empirical observations reveal that preferred refinement depths vary across tasks and states, while different future regions exhibit varying relevance to action generation. Motivated by these findings, we propose Elastic-WAM, which adaptively allocates world refinement computation across temporal denoising time and spatial future space. A unified spatiotemporal refinement demand field governs when to stop world refinement, how far to advance each denoising step, and which regions to refresh. We parameterize this field with a shared temporal basis and spatial amplitudes, and learn it through a three-stage action-grounded supervised procedure. At inference, the learned field guides recurrent sparse world refinement to improve task success while reducing inference overhead. Evaluations across diverse simulation benchmarks and real-world long-horizon manipulation demonstrate state-of-the-art control performance with reduced inference latency.

版本更新 · v2arXiv:2610.02274

Awomo-SimDataEngine: Agentic Simulation-ReadyWorld Generation

Awomo-PhysicalRSI Team, Danjiao Ma, Enhui Ma, Haohan Liu, Heng Jia, Hui Shan, Jianhua Xu, Jiahuan Zhang 等 24 位作者

原文摘要

Generating useful robot-training data requires more than visually plausiblescenes: objects must support interaction, placements must remain physicallyvalid, and tasks must admit repeatable execution. We present\textbf{Awomo-SimDataEngine}, an agentic system that connects asset and scenegeneration to robot demonstration synthesis. Shared asset services providerigid and articulated objects, including structure-grounded part and jointgeneration with ISArt. Scene generation supports two complementary routes:Unravel reconstructs editable scenes from images, while SimForge buildssingle-room and multi-room environments from text. A graph-native harnesscoordinates construction, validation, andbounded repair, routing failures to the responsible module while retainingunaffected scene state. PolicyForge binds validated worlds to tasks and robotembodiments to produce replayable demonstrations. Evaluations cover assetgeometry, scene quality, and downstream policy learning. On MuJoCo-basedLIBERO-Plus, co-training with Isaac Sim demonstrations improves the overallsuccess rate of a World-Action Model (WAM) from $77.17\%$ to $89.43\%$. Goal and spatialsuccess improve by $31.66$ and $6.25$ percentage points, respectively . These results support the utility of the generated data for cross-simulatorpolicy training, with more limited gains on long-horizon tasks.

cs.RO

新论文 · v1arXiv:2611.13613

Megrez: A Knowledge-Guided Agent for Formal Mathematics over MK Set Theory

Tiancheng Xu, Wensheng Yu

原文摘要

General-purpose coding agents equipped with proof-assistant tools have shown strong performance on standalone competition problems, yet cumulative textbook formalization inside a low-resource mathematical library still faces three obstacles: aligning textbook concepts with library declarations, keeping long-horizon search synchronized with live proof states, and integrating locally verified proofs reliably into a growing codebase. We present Megrez, a knowledge-guided formalization agent for Rocq libraries built on Morse--Kelley (MK) set theory. Megrez coordinates a general coding agent through three mechanisms: (1) a source-rebuildable knowledge graph merging formal declarations, compiler references, and curated metadata to support retrieval via Chinese aliases, concept clusters, proof dependencies, and multi-lane full-text ranking; (2) a feedback-driven 1--5 tactic short-burst proving loop paired with a goal-local branch ledger and exponential-interval structured reflection; and (3) a three-check acceptance pipeline (statement fidelity, axiom auditing, and full builds) coupled with a multi-corpus Provider stack and a candidate-bound recoverable batch state machine. Deployment and evaluation on a point-set topology corpus demonstrate effective cross-chapter formalization and scalable premise retrieval.

cs.AI

版本更新 · v2arXiv:2607.04689

RCT-AD: Reliability-Aware Context and Temporal BEV Reasoning for End-to-End Autonomous Driving

Argho Dey, Yunfei Yin, Swachha Ray, Md Minhazul Islam, Zheng Yuan, Sijing Xiong, Hongyu Liu, Zhiqiu Huang

原文摘要

Reliable temporal representation learning is important for end-to-end autonomous driving, particularly when visual observations are degraded by occlusion, motion blur, illumination variation, and sensor noise. Existing Bird's-Eye-View (BEV) approaches provide a unified representation for perception and planning; however, temporal features are commonly aggregated across frames without explicitly accounting for the reliability of individual observations. Consequently, low-quality or inconsistent features may propagate through temporal representations and degrade downstream perception, prediction, and planning. To address this problem, we propose RCT-AD, a Reliability-Aware Context and Temporal BEV Reasoning framework for end-to-end autonomous driving that explicitly models feature reliability and temporal consistency within a shared BEV representation. RCT-AD introduces a Reliable Context Awareness (RCA) module that estimates frame-level reliability using spatial, semantic, temporal, and visual-quality cues, and selectively preserves trustworthy information through a reliability-guided temporal memory mechanism. When the current observation is unreliable, historical high-reliability features are aligned and integrated to construct a more stable temporal BEV representation. A Temporal Trajectory Planner models long-term temporal dependencies and multi-agent interactions, while semantic segmentation and motion-guided detection provide complementary supervision for refining the shared BEV representation. Experiments on the nuScenes benchmark demonstrate consistent improvements across perception, motion prediction, and trajectory planning. RCT-AD achieves 61.5 NDS, 52.9 mAP, and 52.3 mIoU while maintaining competitive computational efficiency. These results demonstrate the effectiveness of reliability-aware temporal BEV reasoning for unified perception, prediction, and planning.

cs.RO · cs.CV

版本更新 · v3arXiv:2603.23994

Understanding the Challenges in Iterative Generative Optimization with LLMs

Allen Nie, Xavier Daull, Zhiyi Kuang, Abhinav Akkiraju, Anish Chaudhuri, Max Piasevoli, Ryan Rong, YuCheng Yuan 等 13 位作者

原文摘要

Generative optimization uses large language models (LLMs) to iteratively improve artifacts (such as code, workflows or prompts) using execution feedback. It is a promising approach to building self-improving agents, yet in practice remains brittle: despite active research, only 9% of surveyed agents used any automated optimization. We argue that this brittleness arises because, to set up a learning loop, an engineer must make "hidden" design choices: What can the optimizer edit and what is the ``right'' learning evidence to provide at each update? We investigate three factors that affect most applications: the starting artifact, the credit horizon for execution traces, and batching trials and errors into learning evidence. Through case studies in MLAgentBench, Atari, and BigBench Extra Hard, we find that these design decisions can determine whether generative optimization succeeds, yet they are rarely made explicit in prior work. Different starting artifacts determine which solutions are reachable in MLAgentBench, truncated traces can still improve Atari agents, and larger minibatches do not monotonically improve generalization on BBEH. We then study these factors jointly in harness optimization on TBLite, evaluated on Terminal-Bench 2.0. We also propose a batch-size and credit-horizon rule that, calibrated on TBLite, transfers to DeepSWE after adjusting to its token costs and comes within 1% of the best configuration tested at each context budget.

cs.LG · cs.AI

版本更新 · v2arXiv:2610.29027

Beyond Tokens: NumAnchor for Address-Grounded Numeric Operand Representation in Assembly Language Models

Kun Liu, Keith Mitchell, Xin Hu, Jiangcheng Yu, Chenke Luo, Zhengming Ding, Haotian Zhang, Jiang Ming

原文摘要

Assembly language models (ALMs) are becoming important for automated binary analysis, yet their token-level interfaces often obscure numeric-like operands. In two corpora, such operands account for 45.7% and 40.9% of operand occurrences and may denote branch targets, global data, stack slots, constants, or unresolved pointer-derived values. Existing normalization strategies often lose their identities and structural relationships. We present NumAnchor, an input-boundary adapter that represents recoverable numeric-like operands as typed, canonicalized program entities. NumAnchor encodes code, data, and stack context in compact structural side descriptors, preserving entity identity and locality without increasing the host sequence length. These descriptors are fused into input embeddings before the first Transformer layer, while the host architecture, pretraining objectives, and downstream protocols remain unchanged. Probing frozen instruction-level embeddings yields 98.7% hierarchical-location accuracy and AUROC scores of 0.932 and 0.907 for jump and call target alignment, respectively, showing that the encoded structural information remains recoverable. Across multiple ALM families, NumAnchor achieves relative improvements of up to 35.0% in Recall@1 and 31.7% in MRR on 10k-candidate function retrieval, and improves execution-aware type recovery by up to 5.2 F1 points. Ablations show complementary gains from code, data, and stack descriptors with modest overhead.

cs.CR

新论文 · v1arXiv:2611.10356

SepLRM: A Foundation Model Paradigm for Recommendation

Di Chen, Xijun Xiao, Qin Ren, Weijiang Lai, Zhijian Pan, Zhentao Pan, Pengfei Nie, Cheng Yuan 等 26 位作者

原文摘要

Large recommendation models (LRMs) improve recommendation performance by scaling behavior sequence length, model capacity, and training compute. However, the return on investment (ROI) of continued scaling deteriorates as marginal gains diminish and long-sequence encoding costs rise, especially when this computation is repeatedly executed by distinct models for diverse recommendation stages and business scenarios. To address this issue, we propose SepLRM, a recommendation foundation model (RFM) paradigm that identifies reusable sequence encoding and reorganizes multiple end-to-end (E2E) LRMs into one RFM and multiple independently optimized vertical models (VMs). The RFM adopts an encoder-decoder architecture and exports its final-layer encoder state as the shared key-value (KV) cache that is independent of downstream task-offered candidates. Unlike candidate-specific logits or aggregated user embeddings, the KV cache preserves fine-grained behavioral information. Separation at this native KV interface also allows each VM to construct candidate-conditioned queries while retaining the same query-KV interaction as its E2E counterpart, enabling high-fidelity capability transfer. To ensure both transfer effectiveness and system efficiency, we co-design cache compression, the training and serving workflows, and LG-Store, a distributed storage system for KV caches. Experiments on three large-scale datasets show that SepLRM achieves state-of-the-art offline performance with a transfer rate of approximately 100%. It also demonstrates strong transferability across model iterations, recommendation stages, and business scenarios. Deployment in two large-scale industrial scenarios substantially improves the ROI of sequence scaling and delivers consistent gains in online A/B tests at ByteDance.

cs.IR

新论文 · v1arXiv:2611.09597

RuACT: Recovering Inactive Rubrics as Adaptive Critics and Teachers

Yijun Li, Zhengxi Lu, Zhipiao Liu, Jinzheng Yu, Xutao Weng, Jian Shao, Yongliang Shen

原文摘要

Rubric-based reinforcement learning (RL) extends RL with verifiable rewards to open-ended tasks by scoring each response against query-specific rubrics. Under group-relative optimization, however, a rubric that every sampled response fails (unreachable) or passes (saturated) gives all responses the same outcome and no learning signal; in Qwen3-4B medical training, 60.88% of query-rubric observations are inactive. We find that the two states lack different supervision: stating an unreachable rubric in the prompt raises its satisfaction from 1.13% to 91.25%, whereas responses that all pass a saturated rubric still differ in quality. We therefore propose RuACT (Rubrics as Adaptive Critics and Teachers), which assigns each inactive rubric the role that supplies what it lacks. Rubric as Teacher uses unreachable rubrics as privileged information for reward-gated on-policy self-distillation, and Rubric as Critic decomposes saturated rubrics into child rubrics that separate current responses while sharing the parent's weight. RuACT outperforms GRPO, rubric reweighting, and rubric-guided exploration on all four medical and scientific benchmarks with Qwen3-4B and achieves the best average with Qwen3-1.7B. On initially unreachable rubrics, unguided recovery rises from 35.02% to 42.86%, while child refinement improves reward-quality alignment on independent rollouts from 57.74% to 60.77%. Code is available at https://github.com/ZJU-REAL/RuACT.

cs.CL

版本更新 · v3arXiv:2606.01869

WorldCoder-Bench: Benchmarking Physically Grounded 3D World Synthesis

Shuo Lu, Yinuo Xu, Kecheng Yu, Siru Jiang, Yongcan Yu, Yubin Wang, Haitao Yang, Yuxiang Zhang 等 11 位作者

原文摘要

Large language models (LLMs) are increasingly asked not only to write static interfaces, but to construct executable interactive worlds from natural language. Browser-native 3D, commonly built with Three.js, is a natural next frontier: generated programs must integrate assets, obey spatial and physical constraints, and keep user-facing controls synchronized with hidden runtime state. Existing web-generation benchmarks and evaluators, however, largely observe only pixels or DOM nodes, while the mechanics of a Three.js world unfold inside an opaque <canvas>. We introduce WorldCoder-Bench, a benchmark for autonomous, physically grounded 3D world synthesis. WorldCoder-Bench contains 2,026 expert-curated tasks across Simulation, Rendering, and Application scenarios, with optional .glb assets and hidden behavioral contracts. We further propose StateProbe, an execution-based protocol that probes generated programs in a controlled browser and verifies hidden, mutation-hardened contracts over runtime states and transitions. Beyond verification coverage, we report Return on Automation and Time Efficiency Multiplier to estimate quality-adjusted cost and time utility. The best verification coverage is 27.8% across nine models on WorldCoder-Benchcore and 19.9% across five on WorldCoder-Benchrob, with failures dominated by state-schema drift and broken interaction chains rather than missing scene elements. Utility metrics further show that cheap or fast models can still provide substantial value on easier domains. WorldCoder-Bench is available at https://github.com/shuolucs/WorldCoder-Bench.

cs.AI

新论文 · v1arXiv:2611.08699

Adaptive Data Analysis and Adversarial Robustness on Insertion-Deletion Streams

Elena Gribelyuk, Honghao Lin, Xin Lyu, Mahbod Majid, David P. Woodruff, Huacheng Yu, Samson Zhou

原文摘要

Classical streaming algorithms and statistical mechanisms frequently fail when future inputs or queries depend adaptively on prior outputs. In this work, we resolve central open questions in both adaptive data analysis (ADA) and adversarially robust turnstile streaming by introducing a unified hierarchical estimator-corrector-learner framework. For adaptive data analysis over an unrestricted domain, we design a randomized mechanism that answers $k$ adaptively chosen statistical queries to within additive error $α$ using $\tilde{O}(\frac{\sqrt{k}}α + \frac{1}{α^2})$ samples, nearly matching the lower bounds of Hardt and Ullman [FOCS 2014] and Steinke and Ullman [COLT 2015] while improving upon the classic $\tilde{O}(\frac{\sqrt{k}}{α^2})$ bound of Dwork et al. [STOC 2015] and Bassily et al. [STOC 2016]. For known finite domains $U$, we combine our mechanism with private multiplicative weights to improve the sample complexity to $\tilde{O}\left(\frac{1}{α^2}+ \min\left(\frac{\sqrt{k}}α, \frac{\sqrt{\log |U|}}{α^2}\right)\right)$. Building on our ADA mechanism, we construct a fixed linear sketch with a stateful decoder that answers $\tilde{O}(\frac{1}{ε^2})$ adaptive $F_2$ moment estimation queries to within a $(1\pmε)$-multiplicative factor using $\tilde{O}(\frac{1}{ε^2})$ bits of space. Finally, by embedding this sketch into a binary-tree recursion, we obtain the first nearly space-optimal adversarially robust algorithm for $F_2$ estimation on insertion-deletion streams. Our algorithm uses $\tilde O(\frac{1}{ε^2})$ bits of space, improving upon the $\tilde{O}(\frac{1}{ε^4})$ bound of Gribelyuk et al. [STOC 2026] and matching the insertion-only bound of Woodruff and Zhou [FOCS 2021]. This demonstrates that no asymptotic space overhead in $ε$ is required to achieve adversarial robustness in the turnstile model.

cs.DS

新论文 · v1arXiv:2611.07931

How Generative AI Redefines Personalization and Diversity in the Newsroom

Cheng Yu, Jim Chi, Aaron J. Snoswell, Orestis Papakyriakopoulos

原文摘要

The tension between news personalization and information diversity has traditionally been understood as a matter of different content reaching different people, with diversity evaluated by the range of sources, topics, and perspectives to which audiences are exposed. Generative AI outdates this understanding, since it transforms personalization in two ways: how journalists adapt news to audiences and how the AI tools journalists use personalize content production to their own preferences. Drawing on 16 semi-structured interviews with media professionals across public service, commercial, and state-affiliated news settings, we examine how these practices reshape editorial judgment and the conditions under which news diversity is produced. We find that participants negotiate AI integration by maintaining authority over meaning while delegating aspects of content presentation. Yet the tools they adapt for their own work also mediate which sources and perspectives become available, introducing diversity-relevant decisions that remain largely invisible to organizational oversight. While participants anticipate diversity risks in audience-facing personalization, they predominantly interpret diversity-imposed limitations in their own tools as technical problems. As a result, decisions that shape news diversity increasingly occur before publication and across multiple versions of a story, where neither evaluation of published items nor human approval can readily observe them. Journalists thus remain formally responsible for outcomes shaped by decisions they cannot fully see or control. Our findings highlight that safeguarding news diversity requires looking beyond published content to the professional practices, infrastructures, and distributions of control that shape it.

cs.CY

新论文 · v1arXiv:2611.07874

Responsible GenAI Use During Active Armed Conflict: Evidence from Sudan's Emergency Response Rooms

Dalia Ali, Yearin Lee, Cheng Yu, Ro Encarnación, Alsanosi Adam, Danaé Metaxa, Ingmar Weber, Orestis Papakyriakopoulos

原文摘要

Armed conflict can increase the value of Generative AI (GenAI) while undermining the conditions required for its responsible use. Yet the perspectives of community-based humanitarian responders working under these conditions remain underrepresented in responsible AI research. We examine GenAI use in Sudan's Emergency Response Rooms (ERRs), a community-led humanitarian network, through an exploratory survey of 89 respondents and 15 semi-structured interviews with GenAI users and non-users. War reconfigures GenAI's role, making it most useful where its outputs are hardest to verify. ERR responders turned to GenAI when conflict made human expertise difficult or dangerous to reach. However, participants cautioned that GenAI could not independently establish rapidly changing local conditions, and that relying on its outputs could lead to harmful decisions when human verification was difficult. Risks arose before GenAI was used. For some volunteers, carrying a phone or accessing the internet could expose them to danger. Others were concerned that sharing sensitive beneficiary or operational information with GenAI could put people at risk. Participants feared that AI-assisted reports could undermine their credibility with donors, whose funding sustains the food and medical aid ERRs provide. Access to GenAI was uneven, and volunteers using it sometimes relied on colleagues with relevant expertise or local knowledge to verify its results. Our findings show that responsible use of GenAI during conflict depends not only on model performance or individual adoption, but also on whether responders can safely access these tools, verify their outputs against local conditions, and recognize when limiting or avoiding GenAI is the more responsible choice.

cs.AI · cs.HC

新论文 · v1arXiv:2611.07461

The Last Mile to the Real World: Agent-Native Primitives as Reusable Building Blocks for Solving Real-World Tasks

Haibo Jin, Peng Kuang, Xiaopeng Yuan, Lucheng Fu, Jerry Wang, Xucheng Yu, Yaoning Yu, Dehao Wu 等 14 位作者

原文摘要

How can an agent handle a real-world task end to end? Frontier models with their own harnesses still fall short on real-world benchmarks: on Terminal-Bench 4.0, GPT-5.6 Sol with Codex resolves 37.3% of the tasks and Claude Opus 5 with Claude Code 51.8%. These tasks fail at the step from reaching a resource to applying it, which we call the last mile to the real world. Existing approaches put the resource within reach but leave the competence to apply it with the caller, so each harness rebuilds that competence. We introduce agent-native primitives, reusable units that equip a resource with a resident LLM that applies it in context and communicates with other primitives, and HEELO (Harness Engineering around Evolving Agent-Native Primitives for the Last Mile to Real-WOrld Tasks), a harness engineering framework that builds each task's harness from a library of such primitives. HEELO composes the primitives a task needs into a task-specific graph, verifies the result against evidence from the environment, revises the primitives a failure implicates, and admits new or improved primitives after validation. We instantiate HEELO with eight primitive families, each built for one kind of task, and evaluate them on more than twenty benchmarks. Dev-Primitives raise Terminal-Bench 4.0 resolution from 37.3% under Codex to 55.5% on the same backbone, Harness Primitives composed per task raise Terminal-Bench 2.0 Pass@1 from 60.0% for the seed harness to 72.2%, Tool Primitives raise ToolBench pass rate from 55.8% to 75.1%, and Navigation Primitives raise GAIA-Text-103 accuracy from 45.6% to 58.3%. On the 46 real-world tasks of our heelo.dev platform, Claude Opus 5.5 with Claude Code and GPT-6.1 Sol with Codex complete 9 each on their own and 39 and 35 when connected to HEELO through our MCP server, with 1.9$\times$ and 2.3$\times$ less time and 1.55$\times$ lower cost per completed task.

cs.CL · cs.AI · cs.LG · cs.MA · cs.SE

新论文 · v1arXiv:2611.06813

3-一致超团假设为假

The 3-Uniform Hyperclique Hypothesis is False

Timothy M. Chan, Reina Itakura, Zhiyuan Ma, Yuancheng Yu

AI 速读 基于摘要

作者给出检测或计数3-一致超图中4-超团的真正次四次算法,从而否证细粒度复杂性中一个流行假设。

cs.DS

查看原文摘要

We present truly subquartic algorithms for detecting or counting 4-hypercliques in a 3-uniform hypergraph with $n$ vertices, disproving a popular hypothesis in fine-grained complexity. The result immediately implies a faster algorithm for finding a $k$-hyperclique in a 3-uniform hypergraph for all constant $k\ge 4$, and a faster exponential-time algorithm for Max-3-SAT.

新论文 · v1arXiv:2611.06270

NextGAN: Towards Simple and Scalable GAN Training for Image and Video Generation

Xinhao Lou, Dongye Xie, Peng Sun, Chenyi Zhuang, Kaicheng Yu, Tao Lin

原文摘要

Adversarial training enables one- and few-step image and video generation, but conventional adversarial losses supervise critic values without directly specifying the gradients used to update the generator. We present NEXTGAN, which trains a scalar critic by regressing its input gradient onto displacements between independently paired reference and generated features at interpolated locations in frozen representation spaces. For a fixed generator, this regression is equivalent to an adversarial objective with a gradient-energy penalty, while the generator retains the standard potential-based GAN update. The same objective adapts pre-trained image and video generators with up to 14B parameters, without auxiliary losses, online teacher scores, or trajectories. On ImageNet $256 \times 256$, NEXTGAN achieves one-step FIDs of 2.87 with pixel-space JiT-B and 1.54 with latent-space DiT-XL/1; its adversarial form further reaches 1.36. For text-to-video generation, a single trained Wan2.1-1.3B model supports one-, two-, and four-step sampling, achieving the highest VBench total scores among the compared 1.3B methods at one and two steps. At two steps, NEXTGAN scores 83.13, exceeding rCM and AnyFlow by 1.25 and 0.47 points, respectively. Code is available at https://github.com/LINs-lab/NextGAN.git.

cs.CV · cs.AI

版本更新 · v2arXiv:2609.37969

SoL-Refiner: Speed-of-Light One-Step Refinement for High-Resolution Video

Haozhe Liu, Tian Ye, Shuchen Xue, Sensen Gao, Yitong Li, Junsong Chen, Haopeng Li, Jincheng Yu 等 14 位作者

原文摘要

High-resolution video generation is expensive, as its cost grows rapidly with the number of spatiotemporal tokens. A practical alternative first generates a lower-resolution video and then applies a refiner, but conventional multi-step refinement introduces a second sampling bottleneck. We present SoL-Refiner, a one-step video refiner that transforms low-resolution model outputs into 4K videos with a single denoising step. Our three-stage recipe combines high-resolution continual training, reinforcement learning (RL) post-training, and a final one-step distillation. We introduce Refiner-Bench, a video refinement benchmark constructed from the outputs of different video generators, and use a shared-input protocol to compare refiners at approximately 2K output resolution. With LTX-2.3 Refiner as the base model, the one-step SoL-Refiner outperforms all external refiners at 2K on the VBench and UniPercept averages, while at $3840\!\times\!2176$ it improves both metrics over the three-step LTX-2.3 Refiner. With the complete acceleration stack, SoL-Refiner achieves an $8.91\times$ speedup in refinement latency over the same baseline in our 2K latency setting. With MiniMax H3 as the base model, SoL-Refiner produces 2K videos in three refinement steps and is preferred over the official MiniMax H3 2K API in 87% of user-study judgments.

cs.CV

版本更新 · v4arXiv:2603.13275

PREBA: Surgical Duration Prediction via PCA-Weighted Retrieval-Augmented LLMs and Bayesian Averaging Aggregation

Wanyin Wu, Kanxue Li, Baosheng Yu, Haoyun Zhao, Yibing Zhan, Dapeng Tao, Hua Jin

原文摘要

Accurate prediction of surgical duration is pivotal for hospital resource management. Although recent supervised learning approaches, from machine learning (ML) to fine-tuned large language models (LLMs), have shown strong performance, they remain constrained by the need for high-quality labeled data and computationally intensive training. In contrast, zero-shot LLM inference offers a promising training-free alternative, but it lacks grounding in institution-specific clinical evidence, making its predictions clinically misaligned and prone to instability. To address these limitations, we present PREBA, a retrieval-augmented framework that integrates PCA-weighted retrieval and Bayesian averaging to ground LLM reasoning in institution-specific evidence without requiring task-specific fine-tuning. Specifically, PREBA first encodes heterogeneous clinical features into a unified representation. It then performs PCA-weighted retrieval, weighting each dimension by its contribution to the variation across institutional cases, instead of treating them as equally informative, and conditions the LLM to generate multiple candidate predictions. Finally, Bayesian averaging consolidates these predictions with population-level statistical priors, yielding a calibrated estimate that remains stable and clinically plausible. We evaluate PREBA on four real-world datasets spanning different institutions and languages, using three state-of-the-art LLMs, including Qwen3, DeepSeek-R1, and HuatuoGPT-o1. PREBA consistently outperforms zero-shot inference, reducing MAE by up to 64.9% and raising R2 to as high as 0.63. It further attains accuracy competitive with, and on several datasets superior to, fully supervised ML methods, while offering greater interpretability through retrieved exemplars and explicit priors. The code is available at https://github.com/kanxueli/PREBA.

cs.LG · cs.AI

版本更新 · v2arXiv:2603.04743

DARE: Aligning LLM Agents with the R Statistical Ecosystem via Distribution-Aware Retrieval

Maojun Sun, Yue Wu, Yifei Xie, Ruijian Han, Binyan Jiang, Defeng Sun, Yancheng Yuan, Jian Huang

原文摘要

Large Language Model (LLM) agents excel at automating data science workflows, yet often underutilize rigorous statistical methods in R. Existing Retrieval-Augmented Generation (RAG) approaches rely on semantic similarity, ignoring the data-distribution and structural characteristics crucial for determining a statistical method's applicability. To address this, we propose DARE (Distribution-Aware Retrieval Embedding), a representation learning framework incorporating these data characteristics into R function retrieval. Our contributions are fourfold: (i) RPKB, a curated knowledge base of 8,191 high-quality R functions; (ii) DARE, the distribution-aware retrieval framework; (iii) RCodingAgent, an R-oriented agent integrating DARE for end-to-end analysis; and (iv) RStatBench, a comprehensive benchmark of 100 statistical tasks. Experiments demonstrate that DARE improves NDCG@10 by 13.43 to 32.65 percentage points across evaluated embedding models, with a MiniLM-based DARE achieving 93.92% NDCG@10 alongside high efficiency. Furthermore, integrating DARE into RCodingAgent nearly doubles mean downstream accuracy on RStatBench, increasing from 31.8% to 62.2% across ten LLMs. This work helps bridge modern LLM automation with R's established statistical computing ecosystem.

cs.IR · cs.AI · cs.CL