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

+1112新增论文
+875其中 AI 相关
+133已有论文修订
+94新增 AI 导读

arXiv 最近完成扫描:2026-11-19 20:16 · 全站最近入库:2026-11-19 19:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-18 21:25 — 2026-11-19 21:25(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:2026-11-19 20:16最近发现新增版本:2026-11-19 19:09库内论文最新更新时间:2026-11-19 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。

27,982 已收录论文23,249 AI 相关8,559 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 35 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-19 20:10(北京时间)
版本更新 · v2arXiv:2609.32495

Hearsay: Who Can Audit the Record a Deployed Agent Harness Writes?

Jiahong Dai, Zhuochen Yang, Pengyang Shao, Kelvin Ng, Zhongyi Liu, Chengquan Ju, Yuting He, Bo Hu

原文摘要

The record of an agent's run is written by the harness that drives the agent. When the run is later disputed, the auditor was not there and has only this record. We ask whether someone who was not there can check the record, and what decides the answer. It depends on who wrote what a check can rely on: if the harness wrote all of it, the record is only the harness's own word, and we call it hearsay. We build Hearsay, a benchmark that examines the record and not the task: five harnesses run fourteen tasks, model examiners from three vendors and a human panel read the records and answer questions about the runs, and every passage they cite is labelled mechanically by who wrote it. We also audit what is deployed: in all sixteen frameworks, the harness is the only writer. With one writer, readers can name the fault from the record, in up to nine runs in ten, but they cannot check the record. The model examiners claim corroboration for 18 to 55 points more of their evidence than the labels support, a gap we then predicted for runs driven by another vendor's model and found again. And the best of them notices only half of the alterations we make to a record, while the two that name the fault most often cannot tell what a harness left out. With a second writer, the record can be checked. Our sandbox keeps a ledger of what passes between harness and model, and reading the ledger against the record in both directions shows what the record leaves out and what it adds. We test this as an auditor would use it, on one unseen record at a time. On runs driven by a third vendor's model, with every rule committed before the records existed, it reports 64 of 66 alterations and flags none of 84 clean records. On held-out records in five formats it reports 109 of 115. What makes a record evidence is a second writer, not a better reader.

cs.CR · cs.AI · cs.CE · cs.SE

新论文 · v1arXiv:2611.22506

EfficientVPR: Toward Efficient Visual Place Recognition via Scene-Aware Prompt Tuning and Adaptive Feature Enhancement

Wenjing Tang, Chuanguang Yang, Zhulin An, Libo Huang, Yongjun Xu

原文摘要

Visual place recognition (VPR) faces critical challenges in handling extreme environmental variations while meeting the computational constraints of practical applications. Current methods predominantly address these challenges by either scaling up model capacity or employing computationally intensive reranking stages, creating a significant efficiency bottleneck. To overcome this limitation, we propose EfficientVPR, a lightweight one-stage framework that achieves speed-accuracy trade-offs through two key innovations: i) a scene-aware visual prompt tuning method which adapts pretrained features with less parameters while dynamically adjusting to sample-specific characteristics, and ii) an instance-dependent key local feature enhancement module that further reinforces discriminative regions. Comprehensive evaluations on Pitts250k, MSLS, Eynsham, AmsterTime and SVOX demonstrate that our method establishes a new SOTA for DINOv2-small models by outperforming all same-scale competitors, and delivers a $73\times$ speedup with 60\% lower-dimensional features while maintaining competitive (within 2.5% average R@1 gap) against the SOTA DINOv2-large-based two-stage method. Our code will be available at https://github.com/WiniTang/EfficientVPR.

cs.CV

新论文 · v1arXiv:2611.22418

CutAgent: Creative-Gene-Driven Planning and Experience-Guided Self-Refinement for High-CTR E-commerce Advertising Video Creation

Xuyue Huang, Guanbo Huang, Jiasong Feng, Run Ling, Ao Ma, Xi Zhao, Yaoyu Li, Jie Gao 等 13 位作者

原文摘要

E-commerce advertising video creation requires both high-level creative planning and reliable multi-modal production. However, existing methods often map product attributes directly to scripts or editing decisions without explicitly modeling advertising strategies, narrative structures, and production styles. They also have limited ability to reuse past production failures. To address these limitations, we propose $\textbf{CutAgent}$, a dual-agent framework that formulates advertising video creation as a Plan--Execute--Self-Evolve process. CutAgent comprises two collaborative agents, $\textbf{GeneAgent}$ and $\textbf{VideoAgent}$, connected by a structured creative gene that bridges product understanding and video production. GeneAgent maps multi-modal product inputs---textual attributes together with product images---to creative genes that specify narrative units and production rules. To train GeneAgent, we construct $\textbf{CutAgent-70K}$ with approximately 70K samples of product attributes/images, reverse-extracted creative genes, cleaned clip pools, and real-world CTR, and apply high-CTR supervised fine-tuning followed by CTR-guided GRPO. Guided by the generated gene, VideoAgent retrieves category-then-gene failure--correction experiences from a long-term memory as constraints for shot-script planning, then coordinates material retrieval, narration, subtitles, music, and timeline rendering. Independently, a reflection loop diagnoses quality defects, revises deficient production decisions, and writes verified corrections back to memory for later retrieval. Experiments on $\textbf{CutAgent-Eval}$ show that CutAgent outperforms representative baselines in e-commerce advertising video creation, achieving the highest online CTR of $\textbf{2.21\%}$.

cs.CV

版本更新 · v2arXiv:2510.10196

A Subspecialty Diagnostic System Powered by Self-Supervised Learning for Cervical Histopathology

Yizhi Wang, Li Chen, Qiang Huang, Tian Guan, Xi Deng, Zhiyuan Shen, Jiawen Li, Xinrui Chen 等 30 位作者

原文摘要

Cervical cancer remains a major malignancy in women, with large-scale human papillomavirus-based screening generating a large volume of biopsies and, for advanced cases, surgical specimens, imposing an overwhelming diagnostic burden that necessitates precise histopathological evaluation. Although deep learning shows promise, general foundation models offer a broader reach but remain limited in capturing subspecialty-specific features and task adaptability. We introduce the Cervical Subspecialty Pathology (CerS-Path) diagnostic system, built upon the subspecialized dataset and developed through two synergistic pretraining stages: self-supervised learning on approximately 190 million tissue patches to build a cervical-specific feature extractor, and multimodal enhancement with 2.5 million image-text pairs, followed by diagnostic functions integration and downstream task enhancement. CerS-Path integrates eight functions -- across morphological diagnosis, predictive analytics, and multimodal tasks -- to cover the diagnostic workflow from biopsies to resection specimens. Comprehensive evaluations demonstrate improved performance in cervical pathology in female patients, where CerS-Path outperforms state-of-the-art foundation models across 26 of 30 diagnostic tasks. Furthermore, in multicenter retrospective and prospective validation across six independent cohorts of women, CerS-Path achieves up to 99% sensitivity for clinically relevant lesion detection with acceptable specificity across sites, highlighting its potential for screening-derived histopathology and suitability for integration into high-volume diagnostic pathways.

cs.CV

版本更新 · v2arXiv:2609.05327

LLM-Driven Algorithm Design for Quantum Circuit Synthesis based on Binary Decision Diagrams

Yoonju Sim, Federico Berto, Chuanbo Hua, Jinkyoo Park, Changhyun Kwon

原文摘要

Quantum circuits are central to implementing quantum algorithms on quantum devices, where quantum gates must be reversible. Many quantum algorithms rely on Boolean functions, which must therefore be implemented reversibly within quantum circuits. Reversible circuit synthesis provides a way to translate such Boolean functions into reversible circuits. Binary decision diagrams (BDDs) offer a scalable approach to this task, but the resulting BDDs and circuits depend heavily on variable ordering. Existing ordering heuristics commonly minimize BDD size because it is closely tied to the circuit size. However, BDD size is an imperfect proxy for the quantum cost of the synthesized circuit (QCC). We propose \texttt{QuantumEvo}, an evolutionary framework that uses an LLM as a heuristic generator for QCC-aware BDD variable ordering. Instead of predicting orderings directly, \texttt{QuantumEvo} searches over ordering heuristics initialized from multiple heuristic families. Candidate heuristics directly manipulate variable orderings using standard BDD operations and are selected by downstream QCC. The discovered heuristic, HGA-QE, modifies the sifting step inside a genetic algorithm so that the procedure is better aligned with QCC. Across the benchmark set, HGA-QE achieves a 70.9\% tie-or-win rate against the per-function best baseline and is strictly best on 13.5\% of the functions. The results demonstrate broadly competitive QCC performance, with HGA-QE showing a clearer relative advantage in strict wins on the two benchmark suites drawn from sources different from the data used for heuristic discovery.

cs.AI · cs.AR

版本更新 · v2arXiv:2605.09614

Reflection Anchors for Propagation-Aware Visual Retention in Long-Chain Multimodal Reasoning

Xuan Gong, Hanbo Huang, Hao Zheng, Yiran Zhang, Wenbin Dai, Weishu Zhao, Shiyu Liang

原文摘要

Long chain-of-thought (CoT) reasoning improves large vision--language models, but visual information often fades during generation, limiting long-horizon multimodal reasoning. Existing methods either re-inject vision at inference or train policies for stronger grounding, but where to intervene relies on perception heuristics rather than principled gain analysis, and how local visual influence propagates remains implicit. We study this problem from an information-theoretic standpoint and derive a lower bound on the downstream visual gain of a one-step intervention, which suggests two factors: local branching room (token entropy) and downstream visual propagation potential (suffix divergence from a vision-marginalized reference). Guided by this analysis, we propose reflection-anchor policy optimization (RAPO), a GRPO-based policy optimization method that selects high-entropy reflection anchors and optimizes a chain-masked finite-window KL surrogate for downstream visual dependence. Experiments on reasoning-intensive and general-domain benchmarks show that RAPO delivers substantial gains over strong baselines across multiple LVLM backbones. Mechanism analyses further indicate that reflection anchors are enriched for visually sensitive decision points and that RAPO increases contrastive visual-dependence signals along generated trajectories.

cs.CV

版本更新 · v2arXiv:2611.15764

AIFR: Adaptive Identity Feature Recovery for Diffusion-Based Makeup and Anime Portraits

Linyan Dai, Xinwei Zhang, Yaxin Xiao, Mengyu Sun, Xinwei Liu, Renyang Liu, Qingqing Ye, Haibo Hu

原文摘要

Diffusion-based makeup and anime portraits are increasingly popular in online content creation (e.g., virtual makeup editing and anime avatar generation), but their altered appearances can hinder face recognition (FR) in identity-based content screening. Existing methods mainly adapt FR encoders or restore input images. The former require costly gallery re-encoding, while the latter may be incomplete or distort identity-related facial details. To address these limitations, we aim to correct identity features within a frozen FR model to recover its output embeddings in its original space. Appearance changes vary in strength and affect facial regions differently. To this end, we propose Adaptive Identity Feature Recovery (AIFR), a framework that inserts a lightweight recovery module at a single intermediate layer to predict sample-level correction strength and spatially adaptive residual updates. Module training uses fused identity targets to guide embedding recovery in the original FR space and an identity-shift score to regulate correction strength and limit unnecessary changes. At inference, AIFR processes a single portrait in one forward pass without reference images, producing recovered embeddings that can be directly matched with existing gallery templates without re-encoding. With only 1.22M trainable parameters, AIFR improves the average TAR at FAR=$10^{-4}$ from 66.1% to 90.3% over the original ArcFace, and further experiments show improvements across unseen makeup styles, stylization strengths, and generators. Beyond recognition, the recovered embeddings can directly condition a pretrained Arc2Face model to generate faces with improved identity preservation, showing compatibility with embedding-conditioned downstream generation.

cs.CV

新论文 · v1arXiv:2611.16840

Kosmo-GFM:一个可生产部署的几何基础模型

Kosmo-GFM: A Production-Ready Geometry Foundation Model

Sheng Tang, Shengzhe Wei, Tiancheng Chen, Wenhua Jin, Xinyang Lu, Tinghao Jiang, Shuoxuan Feng, Yupeng Liu 等 32 位作者

AI 速读 基于摘要

提出集几何基础模型、位姿优化引擎与重建监督于一体的场景重建系统,并在多个基准上报告了深度、位姿与动态点误差方面的优势。

cs.CV

查看原文摘要

We present Kosmo-GFM, a scene reconstruction system that integrates a geometry foundation model (GFM), a pose optimization engine (PoseEngine), and reconstruction-derived supervision from KosmoWorld. GFM predicts camera parameters, depth, cross-view correspondences, and dynamic 3D points from images and videos. PoseEngine combines these predictions with geometric optimization to recover scene-level camera poses and geometry for downstream 3D and 4D Gaussian Splatting. KosmoWorld generates images and geometric supervision from reconstructed real-world scenes to improve GFM's geometric predictions. On the Sparse and Medium subsets of SpatialBench, GFM achieves the lowest absolute relative depth error and the highest relative-pose AUC at 5 degrees among the compared methods. It also achieves the lowest mean endpoint errors for dynamic points and scene flow across the five evaluated datasets. Across 34 scenes completed by all compared reconstruction systems, PoseEngine achieves the highest scene-averaged pose AUC at thresholds of 1, 3, and 5 degrees, with a cumulative runtime of 14.07 hours, approximately 20% of GLUEMAP's 69.67 hours. PoseEngine Flash provides a further accuracy-efficiency trade-off, with a measured mixed-precision runtime of 2.62 hours, approximately 4% of GLUEMAP's runtime. Separate scaling experiments show generally favorable trends with increased data, model computation, and training budgets. These results support the use of learned geometric priors within a scene-level reconstruction pipeline.

新论文 · v1arXiv:2611.16693

MobileProbe: Adaptive Security Evaluation of Mobile Agents via Trajectory-Aware Injection

Yingbin Jin, Ji'an Wang, HaoYang Chai, Hanjun Luo, Li Hu, Xinfeng Li, Huadi Zheng, PeiZhao Hu 等 10 位作者

原文摘要

Mobile GUI agents read the screen of a phone and operate apps on a user's behalf to complete multi-step tasks such as online shopping or messaging. Because the agent acts on whatever the screen shows, an attacker can embed malicious instructions into ordinary UI content and redirect its actions. We refer to this threat as environmental injection attack (EIA). Existing benchmarks measure this risk by pinning hand-crafted payloads to a fixed step of a fixed task. This approach faces two limitations. First, each payload is bound to one task in one app and does not transfer without manual redesign. Second, agents given the same task may follow different routes, so an agent that never reaches the injected page is recorded as safe without being tested. This insufficient test coverage can cause fixed-point benchmarks to underestimate the security risk of deployed mobile agents. In this work, we propose MobileProbe, a trajectory-aware red-teaming framework that evaluates mobile agents adaptively. MobileProbe discovers attacker-controllable content surfaces through automated pentesting, localizes vulnerable decision points along the agent's trajectory, and iteratively refines context-aware payloads through a surrogate-filtered evolutionary loop. We construct a benchmark of 83 long-horizon attack instances spanning 12 mobile applications. Each is annotated with a Confidentiality, Integrity, or Availability (CIA) attack goal to cover the principal categories of security threats facing mobile agents. On three representative agent architectures, MobileProbe attains higher attack success rates than human-written, zero-shot LLM, and prior automated red-teaming baselines adapted to the mobile domain. MobileProbe can serve as a pre-deployment auditing tool to systematically uncover vulnerabilities and inform security hardening of mobile agents.

cs.CR · cs.AI

新论文 · v1arXiv:2611.15161

CineMME: From Dialogue Grounding to Narrative Reasoning in Multimodal Video Understanding

Jin Liu, Dawei Du, Yexiang Liu, Sijie Zhu, Fan Chen, Junxian Duan, Huaibo Huang, Ran He 等 10 位作者

原文摘要

Narrative video understanding requires more than recognizing visible events: models must extract evidence from dialogue, bind it to speakers, and use it to infer narrative meaning. Existing video benchmarks evaluate aspects of this problem, including video question answering, audio-visual reasoning, and temporal grounding, but rarely test whether these abilities form a coherent dialogue-to-plot evidence chain within the same clips. We introduce \textbf{CineMME}, a human-verified benchmark designed to diagnose dialogue-grounded plot understanding, supported by approximately $1,600$ expert person-hours of annotation. CineMME contains $975$ curated short narrative video clips and two linked tracks: \textit{CineMME-Grounding}, with $13,554$ timestamped speech segments and $33,083$ speaker face boxes for temporal dialogue localization, transcription, and active-speaker grounding; and \textit{CineMME-Reasoning}, with $1,600$ multiple-choice and $316$ open-ended questions spanning perception, audio, narrative, social, and scene-presentation understanding. Our main evaluation compares $20$ MLLMs on reasoning and $9$ omni-modal models on grounding. The results reveal a pronounced who-what-when decoupling: Gemini-3 Pro localizes dialogue in time ($68.34\%$ tIoU) and transcribes it with a WER of $28.99\%$, yet achieves only $7.74\%$ vIoU for active-speaker grounding while achieving $67.66\%$ MCQ accuracy on questions with extractable answers. Modality ablations further show that vision is not uniformly beneficial: it improves performance on perception-heavy questions but can hurt dialogue-centric reasoning. CineMME provides a compact diagnostic testbed for evaluating how multimodal video models connect dialogue, speakers, visual evidence, and narrative meaning.

cs.CV

版本更新 · v2arXiv:2604.23442

资源受限边缘设备上基于无人机的杂草检测用于特定地点管理

Resource-Constrained UAV-Based Weed Detection for Site-Specific Management on Edge Devices

Linyuan Wang, Haibo Yao, Te-Ming Tseng, Kelvin Betitame, Xin Sun, Yanbo Huang, Dong Chen

AI 速读 基于摘要

该研究提出面向部署的无人机实时杂草检测框架,在三种Jetson边缘设备上系统评估YOLO与RT-DETR系列模型的精度—延迟权衡。

cs.CV

查看原文摘要

Weeds compete with crops for light, water, and nutrients, reducing yield and crop quality. Efficient weed detection is essential for site-specific weed management (SSWM). Although deep learning models have been deployed on UAV-based edge systems, a systematic understanding of how different model architectures perform under real-world resource constraints is still lacking. To address this gap, this study proposes a deployment-oriented framework for real-time UAV-based weed detection on resource-constrained edge platforms. The framework integrates UAV data acquisition, model development, and on-device inference, with a focus on balancing detection accuracy and computational efficiency. A diverse set of state-of-the-art object detection models is evaluated, including convolution-based YOLO models (v8-v12) and transformer-based RT-DETR models (v1-v2). Experiments on three edge devices (Jetson Orin Nano, Jetson AGX Xavier, and Jetson AGX Orin) demonstrate clear trade-offs between accuracy and inference latency across models and hardware configurations. Results show that high-capacity models achieve up to 86.9% mAP50 but suffer from high latency, limiting real-time deployment. In contrast, lightweight models achieve 66%-71% mAP50 with significantly lower latency, enabling real-time performance. Among all models, RT-DETRv2-R50-M achieves competitive accuracy (79% mAP50) with improved efficiency, while YOLOv10n provides the fastest inference speed. YOLOv11s and RT-DETRv2-R50-M offer the best balance between accuracy and speed, making them strong candidates for real-time UAV deployment.

版本更新 · v2arXiv:2611.02324

The DynaCell Evaluation Suite for Dynamic 3D Virtual Staining of Live Cells

Alexandr A. Kalinin, Dihan Zheng, Taylla Milena Theodoro, Ivan Ivanov, Eduardo Hirata-Miyasaki, See-Chi Lee, Aofei Liu, Sricharan Reddy Varra 等 15 位作者

原文摘要

Understanding how cells respond to perturbations over time is central to cell biology and drug discovery. Live-cell imaging captures the dynamics of perturbation-induced phenotypes in individual cells. While fluorescence imaging can visualize specific molecular phenotypes, labeling and repeated illumination often affect cell health. Virtual staining offers an alternative by predicting these fluorescence images from images acquired without fluorescent labels. Although many virtual staining models have been developed, their performance on volumetric time-lapse data remains poorly characterized. We address this gap with an evaluation suite for 3D time-lapse virtual staining of live cells. The suite combines paired 3D time-lapse images acquired with and without fluorescent labels, a set of baseline models, and three metric tiers measuring pixel-level fidelity, organelle segmentation performance, and single-cell phenotype similarity. Using this evaluation suite, we study metric and model behavior across 3 cell types, 2 microscopes, 4 organelles, and 3 perturbation states. We find that regression baselines better predict the spatial localization of target organelles, whereas the generative baseline better captures the distribution of phenotypes across cells. These differences expose trade-offs between structural and phenotypic fidelity that are obscured by single-metric evaluation and suggest how virtual staining models can be developed for diverse downstream tasks such as localization, segmentation, tracking, and phenotypic profiling. We release the curated datasets, baseline checkpoints, and evaluation code as part of DynaCell, a broader framework for image-based profiling of cell-state dynamics.

cs.CV · q-bio.QM

新论文 · v1arXiv:2611.09124

Toward the Era of Agentic Embodied Intelligence

Chao Liang, Ke Chen, Fengxiaoxiao Li, Shibo Huang, Yufeng Sun, Zhaokai Yin, Jianhuan Lai, Haozhe Feng 等 10 位作者

原文摘要

Foundation models increasingly guide robot actions, yet sustained autonomy requires efficient control and failure recovery. We introduce A2-MEAS, an embodied multi-agent framework built around code as a scaling interface. Learned correction codes combine corrective language, spatial evidence, execution history, and action proposals. MetaBrain provides training supervision and runtime guidance. A correction encoder and adapter absorb this knowledge into policy weights during training, while fresh codes adapt behavior with frozen weights at deployment. The action model, A2-WLA, adds motion-aware history and a latent world model to a vision-language-action policy. Surprisingly, this simple design with action pretraining and task specialization reaches 0.5755 Q-score on the 50-task BEHAVIOR 2026 public subset before online correction, 2.21x the 2025 winner's reported 0.2605 across different benchmark editions and training configurations. On all 100 BEHAVIOR 2026 public tasks, A2-MEAS achieves 0.6411 Q-score and 45.40% task success. On RoboTwin 2.0, A2-WLA achieves 93.98% average success, rising to 95.05% with the complete system. Across 12 real-robot tasks in five household settings, A2-WLA achieves 57.92% average success versus 26.67% for pi0.5. In long-horizon pour-over coffee preparation, a history-conditioned adapter raises post-failure completion at two filter-handling steps from 14% to 94% and from 8% to 82%, compared with A2-WLA retries. Our training infrastructure delivers 427.1 samples per second, 4.03x the throughput of a pi0.5 reference implementation on matched hardware. We will release the system, models, training scripts, and infrastructure to support efficient embodied learning.

cs.RO

版本更新 · v2arXiv:2611.00942

EPIC: Differentiable Energy-Force Consistent Uncertainty Quantification and Propagation for Machine-Learned Interatomic Potentials

Tianhao Su, Musen Li, Shunbo Hu, Tong-Yi Zhang

原文摘要

Machine-learned interatomic potentials (MLIPs) now rival density functional theory in accuracy and are increasingly used to screen vast crystal databases, yet they can produce unreliable predictions for chemistries outside their training distribution without clear warning. Existing force-level evidential approaches do not inherently define a corresponding uncertainty model over the potential energy surface, limiting the consistent propagation of uncertainty to energy-derived observables. Here we introduce Energy-Propagated Intrinsic Confidence (EPIC), a general energy-centered evidential framework that derives forces as exact gradients of the predicted mean energy, ensuring conservative force fields while providing an analytical estimate of energy uncertainty. Coupled to a MACE backbone trained on the Materials Project trajectory dataset, EPIC propagates uncertainty diagnostics to equations of state, anisotropic structural uncertainty ellipsoids, and phonon dispersions through a Monte Carlo procedure. Applied to 10,966 candidate crystals, the fraction classified as robustly dynamically stable increases from 11\% in the highest-uncertainty quartile to 53\% in the lowest-uncertainty quartile. Furthermore, element-resolved analysis reveals a pronounced chemistry dependence in the relationship between epistemic uncertainty and predicted dynamical stability, highlighting potential limitations in the description of complex bonding environments. EPIC thus provides a physics-aware, chemistry-sensitive uncertainty diagnostic for high-throughput screening and autonomous materials discovery.

cs.CE

新论文 · v1arXiv:2611.08318

学习任务还是学习验证器?重新审视具身自我改进中的评判标准暴露

Learning the Task or Learning the Verifier? Rethinking Criteria Exposure in Embodied Self-Improvement

Wenbo Huang, Jianxin Bi, Shunyu Yang, Ruiyang Si, Rui Ni, Qiang Wang, Shulong Jiang, Yintianrun Zhang 等 13 位作者

AI 速读 基于摘要

作者通过受控实验质疑具身自我改进智能体在基准测试中暴露成功评判标准(Criteria Exposure)的做法,指出其可能诱导代码过拟合验证器而非真正完成任务。

cs.AI · cs.RO

查看原文摘要

Self-improving embodied agents are increasingly being developed and compared on robot simulation benchmarks. Several recent works expose the benchmark's success criteria to the learning agent, a practice we call Criteria Exposure (CE). These criteria, originally written to verify policies trained by imitation learning, often demand more than the corresponding language instructions, so a score from such a verifier may not faithfully reflect whether the instructed task was completed, especially for robot-control programs written by an agent. As embodied coding agents report ever higher benchmark scores, a natural question arises: when a coding agent is exposed to the benchmark's criteria, does it generate code that better performs the instructed task, or code that simply overfits to the verification criteria? We conduct controlled experiments with a self-improving agent with and without CE, and find that with CE the agent quickly produces code with a higher success rate under the given criteria, but this advantage disappears when the criteria are changed slightly without departing from the original instructions. More importantly, the skills the agent develops under CE transfer poorly across tasks. We further propose instruction-faithful criteria and show that they better reflect the performance of agent-generated programs.

新论文 · v1arXiv:2611.07238

How Do AI Agents Waste Your Money?

Huimin Zeng, Yuxuan Lu, Jesse Cai, Eric Hanchen Jiang, Di Wu, Po-Nien Kung, Wenbo Hu, Ziyi Wang 等 11 位作者

原文摘要

AI agents may consume massive tokens across a wide range of tasks, but how many of those tokens are really necessary? Although prior work has shown that agents can incur unexpectedly high token costs, we still lack a systematic way to identify and measure token waste. In this work, we introduce a unified framework for measuring token waste across heterogeneous agent systems. Our framework records and normalizes complete agent trajectories, identifies removable spans using an LLM-as-a-Judge (LLMaJ), and maps the identified text spans back to the original trajectory for token-level measurement. We validate the identified waste through direct interventions by removing marked spans, resuming agent execution, and measuring changes in task outcomes and subsequent actions. In online pruning experiments, we remove 41-46% of the model's reasoning while largely preserving task performance across two distinct agent benchmarks. Using this framework, we analyze agents across multiple settings. Our analysis shows that token waste has a system-level structure that aggregate token usage alone cannot reveal. First, waste varies more across tasks and agent settings than across models. Second, reasoning and visible execution can exhibit different waste patterns. Third, different harnesses can introduce distinct sources of inefficiency even under the same model and task. Overall, our framework transforms token waste into an actionable optimization signal, enabling researchers and practitioners to train more efficient models, design better reasoning strategies, and optimize agent harnesses toward reducing unnecessary computation rather than merely reducing token usage.

cs.CL

版本更新 · v3arXiv:2608.04463

The Judge is Part of the Experiment: Auditing Peer Context Sensitivity in LLM-Based Evaluation

Alicia Guerra, Jiaming Qu, Yibo Hu

原文摘要

Large language model (LLM)-based judges are increasingly used to evaluate AI systems. An underexplored area is applying these judges to multi-agent systems, where they may see the interactions behind a final answer. These interactions, which we call peer context, can affect an evaluation in two ways: (1) they can change the answer produced by the multi-agent system, because an agent might be swayed by other agents, and (2) they can change how a judge evaluates that same answer, depending on whether the judge sees them. In this paper, we separate these two effects through a controlled experiment. We first let an agent answer a question and then answer again after seeing peer responses. We then prompt judges to rate the same final answer with and without the peer context. Finally, we check whether the judges' ratings establish a valid measure of answer quality. Across three benchmarks, four open-weight LLMs as agents, and six judges, we find that peer context changes not only the answer but also how an identical answer is judged, and judges react to it in opposite directions. Moreover, providing peer context for a wrong answer misleads agents more than correct peers help them; without the correct answer, judges struggle to tell known-correct from known-wrong answers---a problem that a well-fitted statistical model does not reveal. Our results show that even when evaluating the same answer, how a judge is set up can change the conclusions differently. We therefore call for evaluations to report what each judge sees, document detailed results per judge, and validate rating scales. These practices are an important step toward the accountable use of LLM-based judges.

cs.CL

新论文 · v1arXiv:2611.06768

PyRUA-REAL: Robot Exploration and Adaptive Learning through RSI in the Real World

Qiang Wang, Jianxin Bi, Shulong Jiang, Ruiyang Si, Wenbo Huang, Kaiqi Chen, Jiaxin Li, Liyun Li 等 10 位作者

原文摘要

Coding agents powered by models such as GPT-6-Astra connect spatial reasoning with executable robot behavior, raising the question of how such agents can produce lasting improvements in robot capabilities from physical interaction. In this work, we study embodied recursive self-improvement (RSI) through real-world exploration, code refinement, and deployment using PyRUA-REAL, a framework in which coding agents retain interaction experience as persistent memory and reusable executable skills that inform subsequent exploration and improvement. Our empirical study places physical manipulation at the center of the improvement process, examining how agents collaborate, what kinds of execution feedback support effective code refinement, and how task specifications and previously acquired skills influence robustness and task transfer. We further investigate the efficiency and capability of the resulting programs when deployed without involving an online agent for decision-making. Across eight real-world tasks, PyRUA-REAL achieves an average success rate of 91.1%. In complementary evaluation on 42 tasks from the RoboDojo benchmark, it achieves an average success rate of 84.4%. This study provides empirical guidance for turning physical exploration into reusable robot skills that support continued improvement and robust, efficient deployment.

cs.RO

版本更新 · v2arXiv:2611.04501

Sample-Grained Approximate Unlearning with Provable Per-Sample Bounds

Yaxin Xiao, Yulin Jin, Li Tang, Haoyang LI, Huadi Zheng, Qingqing Ye, Haibo Hu

原文摘要

Machine unlearning aims to erase the influence of a designated forget set from a trained model while preserving strong utility on the retain set. Approximate unlearning methods efficiently achieve this goal without full retraining, but their effectiveness is primarily assessed using dataset-level aggregate metrics. These aggregate metrics can mask deviations from retraining at the level of individual samples. In this work, we focus on per-sample unlearning effectiveness. We introduce SALA (Sample-grained Likelihoods ALignment), a plug-in optimization framework that enables approximate unlearning methods to operate at the level of individual samples by steering each example toward its correct target distribution. To quantitatively assess this behavior, we further propose the sample-grained distribution gap, a metric that captures per-sample discrepancies between approximate unlearning and exact retraining output distributions. We provide theoretical guarantees showing that SALA contracts this gap and yields a bounded per-sample discrepancy to retraining. To make this framework practical, we develop a low-cost estimation method for the member and non-member target distributions. Extensive experiments on classification and generation tasks demonstrate that SALA reduces the sample-grained distribution gap by up to $86.67\%$ when paired with existing approximate unlearning baselines, while also improving robustness to unlearning hyperparameters.

cs.LG

版本更新 · v2arXiv:2609.33518

SceneScaffold: Active Scene-State Construction for Unified 3D Scene Understanding

Xiangqi Li, Libo Huang, Jiarui Zhao, Weilun Feng, Chuanguang Yang, Zhulin An, Yongjun Xu

原文摘要

Recent 3D large multimodal models (3D-LMMs) rely on a visual bottleneck to compress complex 3D scene evidence into a limited number of visual tokens compatible with large language models (LLMs). Current visual bottlenecks, however, often passively compress heterogeneous 3D evidence into a homogeneous object-centric token sequence, leaving the spatial organization of the scene under-represented. This under-representation forces the LLM to recover spatial relations from a flattened token sequence, leading to unstable reasoning in relation-intensive and spatially ambiguous scenes. To address this issue, we propose SceneScaffold, an active scene-state construction framework for unified 3D scene understanding. SceneScaffold reformulates the visual bottleneck from a passive feature compressor into an active scene organizer, constructing a role-aware spatial scaffold before language reasoning. Specifically, SceneScaffold organizes superpoint-level visual evidence into scene-state components with distinct structural roles: entity states preserve core object semantics, scene-frame states maintain spatial references via boundary and region anchors, relation states encode object-environment interaction cues, and a global summary provides compact context. Through this role-aware construction, SceneScaffold provides the LLM with a spatially organized scene representation before language reasoning. Experiments on unified 3D scene understanding tasks, including 3D visual grounding, question answering, and dense captioning, demonstrate the effectiveness of SceneScaffold, while diagnostic results further show its applicability to relation-intensive and spatially ambiguous cases. Code is available at https://github.com/lixiangqi707/SceneScaffold.

cs.CV

新论文 · v1arXiv:2611.02826

RxnMiner: A Multimodal Agent for Structured Reaction Data Extraction from Chemistry Figures

Jinbo Hu, Songren Zhang, Chuanxun Fu, Jinrui Huang, Zhen Hao Wong, Dongxu Cui, Haoran Fan, Muhao Ge 等 22 位作者

原文摘要

Reaction data underpin machine learning for reaction prediction, condition recommendation, and retrosynthetic planning, yet extracting these data from literature figures still requires substantial manual effort. Many figures encode multiple experiments through shared templates, substituent tables, and product grids. Recovering concrete reaction records therefore requires molecular recognition, association of evidence with individual experimental entries, and reconstruction of indirectly specified participants. We present RxnMiner, a multimodal agent system that combines an expert-informed extraction procedure with a chemistry toolbox to coordinate these operations. The agent reads molecular structures, resolves shared and entry-specific evidence, and instantiates participants from templates to assemble source-linked reaction records. We also introduce ChemRxn-Bench, a benchmark of 603 reaction figures with 8,547 manually annotated and reviewed reaction records, evaluated under a common protocol for exact molecular identity and reactant-product pairing. On this benchmark, with Qwen3.8-Flash-Next as the backbone, RxnMiner raises stereochemistry-aware reaction macro-F1 from 21.0% under direct prediction to 71.0%, compared with 25.0% for the strongest existing extraction system. Across five backbones, it also outperforms the same base agent without the extraction procedure and chemistry toolbox by 9.4 to 25.5 points. Applied without human intervention to 10,107 literature figures, RxnMiner produces a silver corpus of 88,202 source-linked reaction records.

cs.AI

版本更新 · v3arXiv:2605.11442

Mobius Injection: From One-Shot Prompt Injection to Sustained Resource Exhaustion in AI Agent Infrastructure

Zi Liang, Ronghua Li, Yanyun Wang, Qingqing Ye, Haibo Hu

原文摘要

Large Language Model (LLM) agents have emerged as key intermediaries, orchestrating complex interactions between human users and a wide range of digital services and LLM infrastructures. While prior research has extensively examined the security of LLMs and agents in isolation, the systemic risk of the agent acting as a disruptive "hub" within the user-agent-service chain remains largely overlooked. In this work, we expose a novel threat paradigm by introducing Mobius Injection, a sophisticated attack that weaponizes autonomous agents into zombie nodes to launch what we define as Agent-based and -Oriented DDoS (AbO-DDoS) attacks. Mobius Injection composes known indirect prompt injection and persistent agent components through a distinct structural mechanism named Semantic Closure, which induces sustained recursive execution of agent components through a single injection event. We demonstrate that this attack is lightweight for the adversary, can evade traditional volumetric DDoS monitors and input filters calibrated for low false-positive rates, and is highly configurable, allowing for surgical targeting of specific environments or model providers. To evaluate the real-world impact, we conduct extensive experiments across three representative claw-style agents and three mainstream coding agents, integrated with 12 frontier proprietary or open-weight LLMs. Our results demonstrate that Mobius Injection achieves substantial attack success across diverse tasks, driving single-node call amplification up to 51.0x. Under coordinated multi-node pressure, each infected node still drains about 123k--127k tokens on a shared five-GPU backend; benign request latency rises by abou 23x--24x, and coordinated infections eventually saturate shared capacity until benign traffic is effectively denied service.

cs.CR · cs.AI · cs.CL

版本更新 · v2arXiv:2609.38850

Beyond Outcome Rewards: Post-Rationale Distribution Optimization for Selective Prediction in Reasoning Models

Zhimin Gao, Meibo Hu, Jiamian Wang, Zhiqiang Tao, Pichao Wang

原文摘要

Reasoning models are trained to produce correct answers, yet selective deployment requires ranking which answers to accept or defer, and outcome-reward training does not directly optimize the post-rationale distribution used for that decision. We identify two mismatches: expected correctness is mode-seeking rather than distribution-eliciting, and scoring an average across rationales rewards disagreement unavailable to a single-rationale decision. We introduce Post-Rationale Distribution Optimization (PRDO), which applies a proper score to the answer distribution after each sampled rationale, without target rationales or separate confidence labels. Across four 0.6--3.8-billion-parameter models on MMLU-Pro, PRDO improves Brier score, error ranking and secondary accuracy relative to budget-matched, temperature-scaled GRPO. At 20\% realized error, oracle coverage rises by \npj{Q3a_vs_grpo.qwen3-0.6b.mp.oracle_cov@0.2.ppabs}--\npj{Q3a_vs_grpo.phi-4-mini.mp.oracle_cov@0.2.ppabs} percentage points, and ranking gains transfer to unseen tasks. Matched controls identify proper, per-rationale scoring as the active design choices, while verification tasks show the boundary: better selective ranking can coexist with lower full-coverage accuracy. Code is available at https://github.com/ZimmyGao/openjev-rlcd

cs.AI · cs.CL

版本更新 · v2arXiv:2608.25429

Distance Is Not Enough: Forget-Retain Alignment Gap Predicts LLM Relearning Robustness

Yi Chen, Hanna Hsieh, Shuhong Liu, Chuanbo Hua, Zihan Ma, Kun Wang, Joo-Young Kim

原文摘要

Machine unlearning aims to make a model forget specific data, yet unlearned LLMs often fail to stay unlearned: brief fine-tuning can revive removed knowledge. Existing robustness predictors rely on global weight-space displacement, but distance alone can be misleading when random or destructive updates collapse performance. We argue that relearning robustness depends on update structure: robust unlearning should affect forget-critical weights while sparing retain-critical ones. We introduce the Forget-Retain Alignment Gap (FRAG), a training-free predictor that scores an update's forget-retain alignment without running a relearning attack, and separates selective from dense updates more reliably than global distance. Building on the forget-critical, retain-sparing principle, Forget-Retain Pruning (FRP) improves relearning robustness. Our results suggest that weight selectivity better explains robustness than distance alone. Code is available at https://github.com/Yi1-Chen/FRAG.

cs.AI · cs.LG

版本更新 · v2arXiv:2606.04262

Can I Take Another Dose? DoseBench: Evaluating LLM Decision-Making in OTC Dosing QA

Maroof Kousar, Jinsung Han, Mohit Chandra, Munmun De Choudhury, Yibo Hu

原文摘要

Large language models (LLMs) are increasingly used to answer everyday health questions online, including whether someone can take another dose of an over-the-counter (OTC) medication. Yet this common safety-relevant setting remains underexplored in medical QA. Answering these questions requires checking previous doses, timing, and product-specific dosing limits, while recognizing when important information is missing. We introduce DoseBench, a focused benchmark of 230 consumer-style acetaminophen and ibuprofen dosing questions with human-annotated YES, NO, and AMBIGUOUS labels, and evaluate eight LLMs with five responses per question. Overall accuracy ranges from 44.8% to 62.2%, while models incorrectly approve 14.0% to 60.5% of prohibited doses. Models with similar accuracy can therefore make very different dosing decisions. Additional analyses show that these failures are not easily fixed by giving models more guidance. Asking models to check dose, timing, and missing information makes them more cautious, while providing drug facts improves accuracy but can make them overlook missing information. These findings highlight a broader challenge in health QA: applying rules correctly and recognizing when information is missing.

cs.CL · cs.AI

新论文 · v1arXiv:2610.38546

Implicit Minor Detection from Multi-Turn Dialogue in High-Risk AI Interactions: A Constrained Self-Evolving LLM Harness

Xiaohan Zhang, Ying Zhao, Ruilin Guo, Xuanyuan Yu, Kaibo Huang, Yukun Wei, Zhongliang Yang, Linna Zhou

原文摘要

In high-risk text interactions, a system may need to estimate whether the current speaker is likely to be a minor before applying age-conditioned safeguards. Many text-based dialogue systems lack strong identity signals such as account information, verified identity, facial data, or device data, and must rely on weak cues that emerge across multiple turns. We formulate implicit minor detection under weak identity information as a high-risk user-attribute inference task and propose a constrained framework comprising a large language model, a Harness, and a Maker-Checker protocol. The framework controls when inference is invoked, requires structured dialogue-linked evidence, and subjects validation-selected Harness revisions to version-level review. On a controlled Chinese benchmark comprising 8,328 multi-turn dialogues, our method improves average precision and minor-class F1 by 7.60 and 6.37 percentage points, respectively, over direct inference using the same LLM family.

cs.CL

新论文 · v1arXiv:2610.35753

CLOSURE: Cross-Channel Closure for Multivariate Time Series Anomaly Detection

Fan Xu, Hao Wu, Zhi Song, Hanbo Huang, Wenzhuo Ma, Nan Wang, Wei Gong, Xibin Zhao

原文摘要

Multivariate time series produced by industrial installations and server clusters are under continuous monitoring, and anomaly detection is the first line of defense before a local fault escalates into a system-wide failure. In the absence of labels, the dominant paradigm trains a reconstruction model on normal data and scores the residual to reach a verdict. Recent work has steadily enriched the expressiveness of the recovery map through Transformers, diffusion models, and cross-scale associations. A residual, however, only certifies that an observation can be recovered; it does not certify that the variables still explain one another as they do under normal operation. A coordinated yet unfamiliar operating transition inflates the residual without breaking any relationship, whereas a sensor drifting away from its peers may leave the residual silent. Methods that fold inter-variable dependencies into the reconstruction objective inherit this ambiguity, because their relational evidence is ultimately supervised by the same recovery loss. We therefore propose CLOSURE, which evaluates recoverability and cross-channel consistency as two normal-data prediction tasks learned in separation. The recoverability task is solved by a diffusion reconstructor conditioned on a discrete memory of normal temporal bases. The consistency task is solved by a relation-closure operator that predicts every channel exclusively from the others, where the target's own trajectory is withheld and sparse signed gates decide which peers are actually used. The two scores are reconciled only through calibration on normal data. Extensive experiments show that CLOSURE consistently outperforms recent reconstruction-, frequency-, and topology-based detectors on public benchmark streams, confirming the value of examining consistency alongside recoverability.

cs.AI

新论文 · v1arXiv:2610.34649

RobotAgentBench: Towards Open-world Robot Autonomy

Lingjun Mao, Jinglin Cao, Lukun He, Wenpeng Xu, Yuchen Yan, Hengyu Jin, Zijun Zhang, Jinzhou Tang 等 25 位作者

原文摘要

Recent advances in vision-language-action (VLA) and world-action models (WAMs) have significantly improved robotic manipulation, yet deploying robots in the open world demands a higher level of autonomy beyond executing predefined tasks. Robot agents offer a promising paradigm for this transition, integrating task discovery, contextual reasoning, physical execution, and adaptive recovery into a closed interaction loop. However, existing benchmarks largely evaluate isolated capabilities, failing to capture the complexity of open-world robot autonomy. We introduce RobotAgentBench (RAB), a comprehensive benchmark for evaluating robot agents in realistic, open-world household environments. Through an agent-assisted, human-in-the-loop real-to-sim pipeline, RAB constructs 50 diverse household layouts with interactive objects and physically grounded tasks, encompassing 90 atomic tasks, 18 short-horizon tasks, 8 long-horizon tasks, and 4 open-ended scenarios. RAB provides a multi-level evaluation of robot agent capabilities: (1) task-level assessments systematically examine five complementary dimensions: task discovery, context reasoning, manipulation, failure recovery, and robustness; (2) scenario-level evaluation assesses how agents integrate these capabilities to autonomously fulfill high-level user needs. Furthermore, RAB enables systematic comparisons of standalone VLA/WAM models and diverse robot agent architectures under a unified planning-execution-verification framework. Extensive experiments reveal substantial gaps between manipulation and autonomy, demonstrate the advantages of agentic architectures and recursive self-improvement, and highlight the remaining challenges toward open-world robot autonomy.

cs.RO · cs.AI

新论文 · v1arXiv:2610.33106HF 社区推荐

VibeGame: Prompt-to-Game Development with AI-Native Engine and Self-Evolving Adversarial Agent Team

Wenbo Hu, Ken Li, Jiazhe Wei, Yukang Cao, Weiyi Hong, Jiayi Dai, Chenjun Bai, Jiajun Liang 等 16 位作者

原文摘要

Large language model agents have enabled software development through natural-language interaction, but extending this paradigm to end-to-end game development remains challenging. Building a playable game requires coordinating code, scenes, assets, animations, physics, and configurations, while allowing developers to validate their integrated behavior through interactive testing. We introduce VibeGame, a framework for creating complete 2D game projects from natural-language prompts and optional reference images. Its AI-native game engine represents project state as schema-validated structured text and provides frame-synchronous runtime control, enabling agents to inspect game states, execute actions, and verify behavior at their own pace. Built upon this interface, we design an Adversarial Agent Team of eight specialized agents to separate implementation from review, so that problems are found and fixed through multi-round loops. For each conducted and accepted project, we further introduce a training-free self-evolution mechanism to distill it into reusable skeletons, modules, and collaboration contracts for future development. We evaluate prompt-assets-to-game (PA2G), where agents are given an asset library, and prompt-to-game (P2G), where agents generate their own art. On a GameCraft-Bench subset, VibeGame in P2G consistently outperforms a range of agent harnesses in either P2G or PA2G with the same underlying model, including GPT-6.1-Sol.

cs.MA

版本更新 · v2arXiv:2610.09117Berkeley BAIR

Workhorse: Learning Robust Whole-Body Humanoid Loco-Manipulation from Human Data

Songbo Hu, Qiayuan Liao, Yufeng Chi, Kevin Zakka, Yakun Sophia Shao, Pieter Abbeel, Koushil Sreenath

原文摘要

Humanoid robots still struggle to plan contact-rich whole-body manipulation from egocentric RGB and proprioception. Workhorse learns such manipulation from robot-free human demonstrations. A visual planner predicts five-link targets: the poses of the torso, both wrists, and both feet. A reinforcement-learning whole-body tracker follows them on the robot. Both policies train separately on the same recorded human poses, without retargeting. We augment the training data of each policy to imitate the errors that the other makes at deployment. On a real Unitree G1, Workhorse transport boxes with its hands and a kick, catches a thrown box, and topples and climbs a suitcase. During box transport, we show recoveries after a person pushes the robot or takes the box away. In a simulated copy of the demonstration room, the system completes box transport in 77% of episodes, and in 64% under 40 N.s pushes. With both policies retrained from the same demonstrations, a simulated second humanoid completes box transport in 83% of episodes without pushes.

cs.RO · cs.LG