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

+0新增论文
+0其中 AI 相关
+0已有论文修订
+91新增 AI 导读

arXiv 最近完成扫描:2026-11-22 08:44 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-21 13:56 — 2026-11-22 13:56(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:2026-11-22 08:44最近发现新增版本:2026-11-21 12:19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。

29,158 已收录论文24,181 AI 相关8,992 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 42 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-22 08:42(北京时间)
版本更新 · v4arXiv:2605.29486

PhoneWorld:从真实应用轨迹到动态可验证的手机智能体环境

PhoneWorld: From Real-App Trajectories to Dynamic and Verifiable Environments for Phone-Use Agents

Yuxuan Liu, Xin Lai, Junyi Li, Pengyuan Lyu, Chenxin Li, Yiduo Guo, Zhengyao Fang, Yang Ding 等 24 位作者

AI 速读 基于摘要

PhoneWorld 将真实应用轨迹转化为可运行、可重置、可验证的 Android 环境,用于手机智能体的训练与评测。

cs.CL · cs.AI · cs.LG

查看原文摘要

Real applications provide the training setting closest to phone-agent deployment, but are difficult to reset, scale safely, and verify programmatically. Static screenshots and interaction trajectories preserve realistic evidence but cannot generate new experience. We introduce PhoneWorld, a trace-grounded framework that converts such evidence into runnable, resettable, and verifiable Android environments. PhoneWorld induces a usage-weighted interaction skeleton from observed pages, transitions, and state-changing operations; translates it into a behavior-grounded app specification; realizes the specification through an autonomous build--inspect--repair loop; and synthesizes executable tasks with programmatic verifiers. The resulting suite spans 34 consumer-facing apps across 16 domains and supports an audited online benchmark, verified trajectory generation, and online RL through common reset and verification interfaces. Evaluations with diverse general and open-source GUI agents show that PhoneWorld supports reliable end-to-end online interaction and exposes capabilities complementary to AndroidWorld. Controlled SFT experiments further show that PhoneWorld trajectories complement AndroidWorld supervision, transfer across online and offline benchmarks, and become more effective as data volume and app coverage increase. Under a matched RL budget, combining PhoneWorld mock-app rollouts with real-app rollouts improves performance over real-app RL alone on both real-phone tasks and AndroidWorld. Together, these results demonstrate that trace-grounded executable abstraction can bridge realistic mobile behavior and scalable agent learning, turning limited real-app evidence into a growing supply of controllable and verifiable environments for training and evaluation.

新论文 · v1arXiv:2611.24154

Game2Player: Scaling Gameplay Experience for Visual Agents through Environment-Player Co-Development

Xirui Jiang, Yuxi Chen, Rui Yang, Feng Luo, Pengcheng Wang, Bingxuan Li, Zihao Zhao, Yushan Li 等 14 位作者

原文摘要

Games are a rich testbed for visual agents, demanding perception, long-horizon planning, and precise control. However, collecting human gameplay is costly, and learning from gameplay videos requires inferring missing actions. Existing datasets also cover a limited range of games, often without explicit tasks or verifiable outcomes. To address these gaps, we introduce Game2Player, a framework that co-develops game environments and players to collect diverse and verifiable gameplay experience at scale. In the Game2Player loop, a Builder agent adapts existing web games, exposes their internal state, and defines tasks with state-based progress measures and success checks. A Coding Player and a VLM Player then attempt the tasks and report problems to the Builder for repair, so that play serves as both environment validation and training data collection. With Game2Player, we build 568 verified web games with 3,436 tasks, collect 15.7K trajectories (307 hours of gameplay), and hold out 50 games as the benchmark PlayerBench. To evaluate the collected experience as training data, we train VLM agents with progress-weighted SFT, assigning greater weight to steps that advance task progress. Game2Player-9B improves progress from 14.3% to 31.2% on PlayerBench and from 30.0% to 53.1% on the external GameWorld benchmark. More broadly, our work suggests a path for visual agents to scale their gameplay experience by building, verifying, and learning from existing game worlds.

cs.CV

版本更新 · v5arXiv:2507.23325

DualTopo: Spatio-Temporal Lane Graph Generation with Dual Latent World Models and Parallel Query Supervision

Yiming Yang, Hongbin Lin, Yueru Luo, Suzhong Fu, Chao Zheng, Xinrui Yan, Kun Tang, Chen Lv 等 10 位作者

原文摘要

Lane topology reasoning constructs a spatiotemporal road graph G = (V, E) in bird's-eye view (BEV), providing structured road representations for planning-oriented autonomous driving. Stream-based methods propagate temporal cues at both the query and BEV levels, yet suffer from two critical limitations: (1) initialized queries receive insufficient supervision, as temporal queries dominate Hungarian matching and leave them undertrained; and (2) temporal propagation is weakened by BEV boundary information loss during feature warping. Since initialized queries serve as propagation anchors, particularly at the first frame, these deficiencies compound across frames and degrade graph generation quality. We propose DualTopo, a spatio-temporal lane graph generation framework with dual latent world models and dual parallel decoder pathways. The dual-pathway decoder supervises temporal and initialized queries concurrently, ensuring initialized queries are well-trained and serve as reliable anchors. Dual latent world models conditioned on ego-motion propagate latent state representations from past observations to the present, substantially improving spatiotemporal graph generation. Extensive experiments on OpenLane-V2 demonstrate leading lane detection accuracy and competitive topology graph prediction. Code is available at https://github.com/YimingYang23/DualTopo.

cs.CV

新论文 · v1arXiv:2611.22901

Done, But Still Working: Anytime Evaluation of When Coding Agents Should Stop

Zerui Yang, Quan Xue, Miaomiao Dong, Chaorui Zhang, Xuanyu Zheng, Xiyuan Wang, Haolin Ruan, Xueyan Niu 等 12 位作者

原文摘要

Coding agents often continue working after their own tests pass. Does this additional work improve the patch, and how much could be saved by stopping earlier? We study these questions through anytime evaluation: replaying recorded runs, scoring intermediate patches with hidden tests, and measuring the cost incurred at each step. For policies that only stop a run or select an earlier patch, this allows paired comparisons without generating new trajectories, provided replay preserves the relevant states. Across about 6,000 runs of eight open models in two scaffolds on SWE-bench Verified, we find substantial differences in the value of continued work. The hindsight saving available at passing self-tests ranges from under 1% to 57%, depending on the model and scaffold. A rule that stops after the same patch passes twice saves 23% in a preregistered replication, but the preregistered quality test does not establish non-inferiority. We explain these differences by measuring how often a rule fires, how often the patch changes afterwards, and whether those changes repair or break it. Fine-tuning agents to imitate the rule saves 30% over six seeds, while quality preservation remains uncertain. Our results help identify both the opportunities and the risks of early stopping.

cs.AI

新论文 · v1arXiv:2611.22238

Context Has a Price: Adding and Removing Context for LLM Coding Agents under Prefix Caching

Zerui Yang, Miaomiao Dong, Quan Xue, Chaorui Zhang, Xuanyu Zheng, Xiyuan Wang, Haolin Ruan, Xueyan Niu 等 12 位作者

原文摘要

Coding agents repeatedly send their conversation history to a language model. Adding useful code may reduce search, while removing old tool outputs may shorten later prompts. But do these changes reduce the cost of solving a task? We study this as a measurement problem in more than 20,000 runs of open models on SWE-bench Verified, SWE-bench and Loc-Bench. We account separately for uncached input, cached input and output tokens. Three findings emerge. First, in our main evidence-package experiments, retrieved code reduces read and search commands by 18--34%, but increases cost by 33--42% when cached input costs one tenth of uncached input, without a measurable improvement in resolution. Second, removing old observations can either save money or increase cost: the same approach saves 19--36% without a cache discount but increases cost by 38--116% with a tenth-price cache. Third, shorter prompts do not guarantee cheaper runs because agents may respond by taking more steps. We also find that concurrent experiments can share cached prefixes and distort cost comparisons. These results show why context-management methods should be evaluated using both token prices and the agent's subsequent behavior.

cs.AI

新论文 · v1arXiv:2611.22045

Beyond Acuity Accuracy: A Multidimensional Framework for Evaluating Patient-Facing Emergency Triage AI Tools

Ruio Heerschap, Henry Foote, Mahmoud Alwakeel, Zhouhan Qian, Jiaqi Wang, Elisabeth Bond, Yang Yang, Jonathan Chong Kai Liew 等 22 位作者

原文摘要

Patient-facing AI triage tools may support care-seeking and emergency department prioritization, but require evaluation beyond acuity accuracy alone. We developed SAFE-Triage, a framework integrating human review, automated metrics, LLM-as-judge evaluation, and simulation testing across clinical performance, patient interaction, and clinician-facing summary quality. We applied SAFE-Triage to 40 MIMIC-IV-derived emergency vignettes and a 10,030-case acuity analysis comparing prompted LLM triage (PLT) with rule-augmented prompted LLM triage (rPLT). PLT achieved higher emergency severity index (ESI) accuracy (57.5% vs 42.8%, $P < 0.001$), lower undertriage (13.1% vs 29.8%, $P < 0.001$), and higher clinician ratings across all domains. rPLT produced shorter and more stable outputs with higher automated readability scores. SAFE-Triage identified trade-offs between acuity accuracy, undertriage risk, communication quality, readability, and summary quality, supporting pre-deployment refinement and ongoing monitoring by showing where triage tools are efficient, need improvement, or need clinician oversight.

cs.CL · cs.CY

新论文 · v1arXiv:2611.22009

DiagTrace: An Interactive Benchmark for Clinical Decision Making

Yufan Wang, Rui Yang, Yi Lin, Chunhua Weng, Yifan Peng

原文摘要

Large language models (LLMs) have shown strong performance on medical question answering and diagnostic reasoning benchmarks. However, existing evaluations typically provide all patient information upfront and assess only the final diagnosis or rationale. This setup ignores the need to acquire diagnostic evidence incrementally from incomplete information in real-world diagnosis. To bridge this gap, we introduce DiagTrace, a source-grounded benchmark for evaluating whether LLMs can reconstruct the documented diagnostic trajectory through interactive information seeking. Each benchmark instance is built from a PubMed Central case report and includes an initial presentation, an event bank, a clinical course, and diagnostic references. DiagTrace contains 510 cases across eight specialties, with 225 used to evaluate four LLMs on clinical-course alignment, interaction quality, and efficiency. Results reveal trade-offs in coverage, source-consistent ordering, and turn use.

cs.CL · cs.AI

新论文 · v1arXiv:2611.20997

OpenMAS-GApp: A Comprehensive Benchmark for Domain-Adaptive Multi-Agent Application Construction

Xunkai Li, Kairui Yang, Jiaxi Li, Yuecong Mao, Zekai Chen, Xinle Zhang, Rong-Hua Li, Guoren Wang

原文摘要

Constructing multi-agent system (MAS) applications across domains requires translating diverse requirements into executable systems, involving task decomposition, agent and tool selection, and execution organization. Existing studies have explored individual aspects of MAS construction, including agent generation, architecture design, workflow generation, and component selection. However, these methods are often developed and evaluated independently, using different task specifications, component resources, and execution settings. This makes it difficult to compare their construction capabilities or determine how they can be applied to different domains. To address this problem, we propose OpenMAS-GApp, a One-for-All benchmark for MAS application construction across diverse domains. It standardizes task inputs, component resources, construction interfaces, and execution environments to support MAS construction under consistent conditions. Within OpenMAS-GApp, we provide Graph Harness as a reference construction method that derives task dependencies, selects compatible agents and tools, and organizes their interactions into executable graphs. We evaluate construction methods across 19 benchmark datasets under 20 evaluation settings spanning four application types and four professional domains.

cs.MA

新论文 · v1arXiv:2611.20524

GaugeRoPE: RoPE-Compatible Executable Latent Attention

Yuanhang Gao, Xiangrui Yang, Lingyuan Meng, Yuanfeng Chen, Dongsheng Li

原文摘要

Latent KV cache compression reduces memory footprint by mapping historical keys and values into compact representations. However, generic compressed key states require reconstruction to native dimension before applying RoPE and computing attention scores, adding sequence-scaling overhead to the decode path. We characterize when a latent KV representation can serve directly as the execution state of pretrained RoPE. For RoPE-based transformers, exact static linear execution of the rotary key path requires the latent-to-native map to preserve the pretrained RoPE action through an intertwining relation, restricting exact mixing to coordinates that share the same RoPE frequency. Guided by this characterization, we build GaugeRoPE, a training-free executable latent KV representation. It combines a RoPE-compatible carrier that preserves the rotary action with an approximate position-independent residual key--value (RKV) correction for complementary key and value information, both evaluated without per-token dense historical K/V reconstruction. On Mistral-7B, GaugeRoPE achieves $5.85\times$ KV compression while maintaining quality close to the full-cache baseline. Additional MHA results validate the construction beyond GQA. GaugeRoPE achieves up to $2.48\times$ the decode throughput of the vanilla uncompressed baseline through direct latent execution.

cs.LG · cs.CL

新论文 · v1arXiv:2611.19546

Evidence-Conditioned Completion and Synthesis of Electronic Health Records

Sicheng Shu, Parker Knight, Huitao Li, Yuan Luo, Yifan Peng, Shawn N. Murphy, Rui Yang, Chuan Hong

原文摘要

Patient information can guide electronic health record (EHR) generation, but how its amount shapes predictive utility and disclosure risk remains poorly characterized. Here we present EHRDiB, which unifies visit completion and synthesis by distinguishing original missingness from withheld inputs and combining a shared multimodal representation with an evidence-conditioned latent diffusion bridge. We compared EHRDiB with three completion and eight synthesis methods on MIMIC-IV and numerical and discretized Duke Health representations. Evaluation covered downstream predictive utility, generative diversity, and distributional fidelity for both tasks, and disclosure risk for synthesis. EHRDiB achieved the smallest utility gaps from real-data-trained classifiers in seven of eight completion comparisons. In synthesis, AUPRC gaps were 45.2% smaller for ten MIMIC-IV principal-diagnosis targets and 53.3% smaller for numerical Duke Health data relative to the best comparator. Synthesis with calibrated thresholding yielded the lowest marginal distribution error across all three datasets, with Coverage above 0.95 for both output rules. Across twelve evidence-fraction intervals in MIMIC-IV synthesis, membership-inference AUROC increased from 0.516 to 0.598 as the mean target evidence fraction rose from 0.20 to 0.50; utility gaps narrowed relative to the lowest evidence configuration but did not decrease monotonically. Our study provides a unified framework and empirical foundation for EHR generation that considers both its utility for clinical analysis and its information disclosure risk.

cs.AI · stat.AP

新论文 · v1arXiv:2611.19527

PathLoop: Self-Evolving Multi-Agent Reasoning for Evidence-Grounded Whole-Slide Image Analysis

Jincheng Li, Zhengyi Liu, Zelin Liu, Yihui Zhan, Yifei Sun, Xiangyu Li, Minye Shao, Lingyao Kong 等 15 位作者

原文摘要

Analyzing whole-slide images (WSIs) requires combining evidence across tissue regions and spatial scales. Multi-agent systems offer a promising approach to this task. However, existing systems make limited use of molecular evidence, often select visually prominent but less representative regions while overlooking global context, and struggle to reuse experience from previous cases. To address these challenges, we present PathLoop, a self-evolving multi-agent framework that integrates omics data for evidence-grounded WSI analysis. Specifically, PathLoop coordinates visual and omics interpreters across slide, patch, and pixel levels, using molecular signals to guide region selection and combining local tissue details with global slide features. A judgment agent then checks the consistency of the collected evidence against Pathology-Wiki, a knowledge base built from 48 entries across 24 organ systems, and triggers re-examination when the evidence is inconsistent. To reuse past experience, a four-level memory stores reasoning trajectories, practical tips, skills, and tools to guide future cases, forming a loop of evidence collection, review, and memory update. We evaluate PathLoop on four TCGA cohorts with biomarker prediction, survival prediction, and subtype classification. The results demonstrate the effectiveness of PathLoop across these tasks and support its use for evidence-grounded WSI analysis.

cs.CV

新论文 · v1arXiv:2611.17621

AscendGYM: A Cost-Aware Kernel Optimization Benchmark for Real-World Workloads on Ascend NPUs

AI Training Platform Team, Bingwei Zhang, Jing Li, Amir Abdullin, Sihang Chen, Xin Chen, Liangjun Feng, Yingmeng Gao 等 27 位作者

原文摘要

Kernel optimization is essential for efficient large language model (LLM) training and inference on Ascend NPUs. Existing Ascend kernel benchmarks primarily focus on kernel generation, with less emphasis on the ability of agents to optimize existing implementations under input configurations drawn from real workloads. To address this requirement, we introduce AscendGYM, a benchmark whose initial suite comprises 48 kernels across three difficulty levels. Each kernel is paired with test cases whose data types and tensor shapes are collected from real-world training and inference tasks. Consequently, performance improvements on AscendGYM map directly to the corresponding workloads. In terms of usability, two evaluation modes are supported in AscendGYM: model evaluation and model-harness evaluation. The kernel optimization capabilities of both trained models and custom agents are allowed to be measured. It provides a complete execution environment that closely reproduces how Ascend kernels are invoked in practical pipelines. For model evaluation, it additionally includes a built-in harness equipped with search orchestration and experience accumulation. Finally, we propose a new metric, the Speedup-Token Score (STS), which quantifies performance gains relative to token cost. By jointly considering speedup and cost, STS enables the assessment of practical kernel optimization capability of a model or harness under an acceptable budget. AscendGYM is available at https://github.com/SLAI-AITP/AscendGYM.

cs.AI · cs.DC · cs.LG

新论文 · v1arXiv:2611.16442

DesignTaste: Benchmarking AI-Generator Visual Design Against Award-Wining Works

Zhou Chen, JiaXiang Li, DanYing Pan, Ye Li, TianRui Yang, EnBao Zhang, YaNan Xiao, LiXin Sun 等 17 位作者

原文摘要

Text-to-image benchmarks commonly assess text-image alignment or overall preference. Whether models can produce good designs when a brief leaves the appearance open remains less well understood. We introduce DesignTaste, a visual design benchmark that compares generated images with award-winning works. From these works and their publicly available context, we derive 403 design briefs: 100 poster tasks from 100 Beste Plakate 2025 and 303 tasks spanning 20 categories from ADC 2026. Six leading commercial text-to-image models each generate an image from the same brief. A single model judge scores each output and the corresponding award-winning work independently on five evaluation dimensions. On each dataset, only ArtArk achieves a higher mean overall score than the award-winning works. All six models score lower in Creative Originality on both datasets. These results show that producing finished, visually appealing images does not imply that a model can develop good design solutions.

cs.CV · cs.AI

版本更新 · v3arXiv:2510.04161

HEHA: Bounded Suboptimal Planning for Constrained Routing and Its Use in Heterogeneous Multi-Robot Exploration of Unknown Environments

Longrui Yang, Yiyu Wang, Jingfan Tang, Yunpeng Lyu, Shizhe Zhao, Chao Cao, Zhongqiang Ren

原文摘要

This paper considers the path planning problem for autonomous exploration of an unknown environment using multiple heterogeneous robots such as drones, wheeled, and legged robots, with different capabilities to traverse complex terrains. A key challenge there is to intelligently allocate the robots to the unknown areas to be explored and determine the visiting order of those areas subject to traversability constraints, which leads to a large-scale constrained multiple hamiltonian path problem (mHPP) that needs to be quickly and iteratively solved every time when new space is explored. To address the hallenge, we propose HEHA (Hierarchical Exploration with Heterogeneous Agents) using a recent hierarchical method that decomposes the exploration into global planning and local planning. The major contribution in HEHA is its global planning, where we propose a new routing algorithm RCH (Routing with Constraints and Heterogeneity) that can quickly find bounded sub-optimal solutions for mHPP to minimize the maximum path length (i.e., makespan) among the agents subject to traversability constraints. Additionally, the local planner in HEHA also considers heterogeneity to avoid repeated and duplicated exploration among the robots. The experimental results show, in the presence of heterogeneous traversability, our RCH can solve mHPP with up to 47% smaller makespan than several baselines, and HEHA can reduce the exploration time by up to 30% compared with existing approaches.

cs.RO

版本更新 · v2arXiv:2610.09074

TAP: Efficient Long-Horizon Agent Pruning via Trajectory-Anchored Recovery

Yuanzhe Li, Pengxin Wang, Yuxin Ren, Jianing Deng, Jingtong Hu, Song Wang, Jingdi Chen, Huanrui Yang

原文摘要

Emerging long-horizon agentic tasks require repeated model calls, worsening the inference cost of already-costly language models. While narrow agentic tasks suggest potential for aggressive model pruning without performance drop, empirical results show existing methods proposed for question answering tasks severely degrade task performance when applied to agentic models. We trace this failure to two decisions: what to prune and how to recover. For pruning, one-shot importance estimates fail to track how the pruned model adapts. For recovery, offline distillation covers only teacher prefixes, while full-trajectory on-policy distillation causes student errors to compound across turns. In this work, we propose Trajectory-Anchored Pruning (TAP), the first structural pruning framework for reinforcement learning (RL)-trained agents. TAP couples structural pruning with efficient on-policy recovery, anchoring interactions to teacher trajectories while allowing the student to generate each reasoning-action response. A frozen dense teacher supervises the student's response prefixes, addressing within-response training-inference mismatch while preventing student-induced deviations from propagating across training turns. Instead of one-shot pruning, TAP re-scores channels using gradients of the recovery objective on the recovered student, connecting iterative channel selection to the evolving policy. With 60% of FFN channels removed, TAP retains 99.2% and 88.0% of the dense 7B agents' task success rates on ALFWorld and WebShop, respectively, while reducing GPU time per successful task by approximately 22% and 17%. These results demonstrate effective structural compression of long-horizon agents under a limited recovery budget.

cs.LG

新论文 · v1arXiv:2611.14910

MuEdit: An efficient multi-task editing method towards inter-domain knowledge conflicts

Songshi Liang, Ting-En Lin, Zixuan Huang, Yuchuan Wu, Yongbin Li, Zihe Wang, Rui Yan

原文摘要

Large language models (LLMs) require frequent knowledge updates across heterogeneous domains, but existing editing methods fail when applied sequentially to multi-task settings. We trace this collapse to inter-domain null-space misalignment: heterogeneous tasks induce distinct Jacobian geometries, causing their common null space to shrink dramatically and leaving insufficient admissible directions for conflict-free updates. We propose the Conflict Index to quantify this geometric interference, and introduce Mu-Edit, which mitigates multi-task conflicts via (1) conflict-aware ordering to minimize cumulative interference, and (2) dynamic low-rank approximation to expand the null space when ordering alone is insufficient. Experiments across five functional domains and three backbones show that Mu-Edit significantly outperforms existing baselines in multi-task editing performance while preserving general capabilities, and remains effective under incremental task arrival.

cs.AI · cs.CL

新论文 · v1arXiv:2611.13945

Chem World: A Large-Scale Benchmark and Physics-Aware Framework for Trustworthy Molecular Property Prediction

Tianyou Bai, Huan Wang, Mingchen Gao, Tongrui Yang, Fangyue Lin, Pinze Ren, Zhenlin Zhao, Siming Dong

原文摘要

Molecular property prediction is fundamental to computational chemistry and drug formulation research, yet existing benchmarks remain fragmented across datasets, properties, and evaluation protocols, limiting systematic evaluation of model generalization. We introduce Chem World, a large-scale benchmark integrating 17 public datasets with over 800,000 molecular and chemical-system instances across 10 property tracks, covering single-molecule and multi-component systems, including drug solubility. Chem World provides a unified testbed for evaluating molecular representations and compositional modeling across diverse chemical properties. Building on the benchmark, we propose PACM (Physics-Aware Compositional Modeling), which combines molecular representations with composition-aware modeling and domain-specific physical constraints. Extensive experiments show that molecular language models provide strong and transferable representations, while PACM consistently improves prediction across diverse chemical systems. Chem World and our PACM-powered drug-property prediction Agent support generalizable chemical modeling and offer a foundation for AI-assisted biomedical research and drug formulation development.

cs.LG · cs.AI

版本更新 · v2arXiv:2605.01340

Terrain Perception for Agricultural UAVs in Complex Farmland via Rotating mmWave Radar

Zhihao Zhan, Le Tao, Shaobin Li, Chenxin Fang, Xingrui Yang, Liang Li, Rui Fan, Yuhang Ming

原文摘要

Accurate terrain perception is essential for terrain-following flight of agricultural uncrewed aerial vehicles (UAVs), yet remains challenging in real-world farmland due to occlusions, complex terrain geometry, and environmental disturbances. Millimeter-wave (mmWave) radar is a promising sensing modality for this task due to its robustness to adverse conditions; however, existing UAV-mounted radar systems rely on fixed field of view (FoV) and terrain extraction methods designed for dense light detection and ranging (LiDAR) data, leading to incomplete and unreliable terrain estimation. To address these limitations, we present a low-cost rotating mmWave radar-enabled terrain perception framework for agricultural UAVs operating in complex farmland environments. Specifically, a mechanically rotating sensing design is introduced to enlarge spatial coverage and improve terrain observability beyond the limitations of fixed-view radar under dynamic low-altitude flight. Building upon this sensing capability, we further design a pose-consistent terrain reconstruction pipeline tailored for sparse, noisy, and partially observable radar data, enabling reliable ground extraction and continuous terrain surface estimation in challenging agricultural scenarios. The complete system is deployed on a real agricultural UAV platform and evaluated through extensive field experiments. Experimental results demonstrate improved terrain coverage and estimation accuracy, achieving an F1 score of 94.42% for ground segmentation, while the closest rival only achieves 90.48%.

cs.RO · eess.SP

版本更新 · v2arXiv:2609.34064

Learning Perturbation Robust Policies for LLM Agents with Stable Optimization

Pengxin Wang, Yuanzhe LI, Yuxin Ren, Huanrui Yang, Jingdi Chen

原文摘要

Reinforcement learning (RL) has become an effective post-training paradigm for long-horizon large language model (LLM) agents. However, we find that the resulting policies can be sensitive to various policy perturbations, such as hidden-state noise, pruning, and quantization. In this work, we study how to improve perturbation robustness during policy optimization. We first introduce the notion of a perturbation robust policy and analyze conditions under which perturbed policy updates preserve stable monotonic improvement. Based on this analysis, we introduce Stable Perturbation-Robust Policy Optimization (SPrPO), which applies adaptive and sensitivity-aware perturbations during RL training. We evaluate SPrPO on ALFWorld and WebShop and conduct systematic experiments across multiple perturbation types and scales, showing improved perturbation robustness while maintaining stable policy optimization.

cs.LG · cs.AI

版本更新 · v4arXiv:2602.02711

Dynamic Mixed-Precision Routing for Efficient Multi-step LLM Interaction

Yuanzhe Li, Jianing Deng, Jingtong Hu, Tianlong Chen, Song Wang, Huanrui Yang

原文摘要

Large language models (LLMs) achieve strong performance in long-horizon agentic tasks through multi-step interaction and reasoning at test time. However, repeatedly invoking these models incurs substantial inference cost over an episode. Post-training quantization (PTQ) reduces this cost, but using a fixed low precision throughout an episode can sharply lower task success. We observe that interaction steps differ sharply in their sensitivity to quantization: given the same context, decoding a step at low precision turns a success into a failure at only about 1% of the steps, which we call critical steps. Based on this observation, we propose Dynamic Mixed-Precision Routing (DMR), a framework that adaptively selects between high-precision and low-precision versions of the same LLM at each decision step. Leveraging an entire-space factorization to jointly predict a step's divergence and its effect on the outcome, DMR learns to recognize these critical steps by training only a lightweight router on the model's hidden state. By reusing a shared high-precision KV cache and the hidden states, DMR avoids redundant context prefill and a separate text encoder, enabling precision switching with less than 1 ms of overhead per step and adding less than 0.11% to step latency for routing. This mixed-precision design also enables nested quantization, reducing the memory footprint by 39% on average compared with FP16. Across three long-horizon agentic benchmarks with nested quantization, DMR achieves an average 2.44x decode speedup over FP16 at comparable task success rates, without fine-tuning the underlying model. On ALFWorld with GPTQ, DMR achieves a 1.71x decode speedup with 86.9% success, compared with 87.2% for FP16.

cs.AI

新论文 · v1arXiv:2611.12296

RecoGEM: A Serving System for Production-Scale Generative Recommendation

Xiangrui Yang, Yunfeng Zhao, Jiawei Yang, Fangyu Zhang, Enrui Zhao, Liang Zeng, Cheng Peng, Minhui Xie 等 11 位作者

原文摘要

Generative recommendation (GR) is moving industrial recommender systems (RecSys) from scoring candidate items to autoregressively generating item identifiers. This shift promises higher recommendation quality, but makes serving substantially harder: each request executes a short sequence of dependent decoding steps that explore a large item space and select promising candidates on the latency-critical path. GR not only creates structural mismatches with conventional RecSys pipelines, but also challenges the architectural and optimization assumptions of LLM serving stacks, making direct adoption of existing systems difficult. We present RecoGEM, our production GR serving system. RecoGEM uses a runtime--engine decoupling architecture to move GR-specific serving responsibilities, such as candidate-state transitions and live artifact updates, to a dedicated runtime. Its execution engine exploits GR's short token sequences, large candidate populations, and predictable step shapes to optimize self-attention, candidate selection, and execution planning. RecoGEM has been deployed for over nine months across our production lines, serving applications with hundreds of millions of users and supporting more than ten GR model families. On our OneModel production workloads, RecoGEM reaches over 1,000 QPS per serving instance with P99 latency below 35 ms and a 2.88$\times$ throughput improvement over representative baselines.

cs.DC · cs.AI · cs.IR

新论文 · v1arXiv:2611.11840

Correct Answers from Insufficient Histories: A Controlled Study of Agent Memory Evaluation

Quan Xue, Zerui Yang, Chaorui Zhang, Haolin Ruan, Xueyan Niu, Xuanyu Zheng, Xiyuan Wang, Weixi Zhang 等 10 位作者

原文摘要

An answer can match the reference for a complete agent history even when the reader's visible history does not determine it. We study this distinction using executable device logs. Our protocol separates reference agreement, certified evidence sufficiency, and context-appropriate behavior. Insufficiency requires two legal histories yielding byte-identical visible contexts but different answers; public chronology and query cutoffs certify sufficient prefixes. On 80 confirmation histories, Qwen3-32B matches 87 hidden references among 203 insufficient raw-prefix instances, with only seven appropriate abstentions. A fixed-input DeepSeek-V4-Flash replication matches 85 and abstains on 21 of the same 203 instances. Each reader makes 1,600 requests. Compact CSV's estimated appropriateness effects remain inconclusive: +3.16 percentage points, clustered 95% interval [0.00,6.57], for Qwen and +2.46, [-1.84,6.94], for DeepSeek. A separate held-out judge study achieves 99.38% correctness but retains support errors and truncations; a deterministic baseline solves all constructed cases. These results support an evaluation diagnosis across two hosted reader configurations, not gains for a general memory system or natural-language evidence assessment.

cs.AI

版本更新 · v4arXiv:2608.26086

TraceML: What Auto-Research Agents Miss in Long-Horizon ML Development

Jiarui Yan, Weiwei Sun, Sijie Li, Wenhan Li, Yiming Yang

原文摘要

Auto-research agents now run machine-learning development unattended for hours, revising data pipelines, models, and validation from their own feedback, yet on most competitions they still finish below strong human competitors. Outcome-based benchmarks record this gap but not its cause, because they grade the final submission and discard the development process behind it. We introduce TraceML, which pairs human and agent work on the same competitions under one version-level schema: 4,465 human Kaggle trajectories across 134 competitions, seven of which are also worked by two agent scaffolds, giving 430 paired human and 207 agent trajectories. Every code version carries its score, its timestamp, and labels for the action taken, its intent, the edit size, and the score effect. Read this way, the gap becomes concrete. Experts alternate data work, validation, model changes, and ensembling, and return to approaches they had set aside. Each agent scaffold instead collapses into a narrow loop: Codex spends its steps re-weighting ensembles and tuning submissions, MLEvolve mutates its model in place, and neither pivots at the human rate nor reopens abandoned work. A short planning prompt distilled from human practice moves the behaviors it names toward the human profile and lifts scores, but the effort profile stays agent-shaped: instruction closes only the part of the gap that reduces to instructions. We release the corpus, the schema, and the labeling models, together with an open-source toolkit that turns a run from any command-line agent into a TraceML trajectory and reads it against the human cohorts.

cs.LG · cs.AI

新论文 · v1arXiv:2611.04715

ZeroGR: Filtering-First Constrained Decoding for Generative Recommendation

Xiangrui Yang, Jiawei Yang, Liang Zeng, Daqian Ding, Ziqian Liu, Bing Tian, Cheng Peng, Yunfeng Zhao 等 12 位作者

原文摘要

Generative recommendation is gaining traction in production, retrieving items by generating their identifiers one token at a time. The generated sequences must identify relevant catalog items, so constrained decoding couples relevance scoring with validity filtering. Because most possible sequences are invalid, scoring before filtering wastes computation on candidates that will be discarded. Our evaluation shows that filtering first can avoid this work with negligible impact on recommendation quality. We present ZeroGR, a filtering-first constrained decoding system for generative recommendation. ZeroGR uses a step-sliced filtering index to reduce GPU memory use by tailoring data representations to each decoding step. Its execution engine adopts shared-slot execution to accelerate data exchange across stages and hybrid projection to adapt computation to workload patterns, thereby reducing execution overhead. During index refreshes, ZeroGR applies layout-guided streaming construction to speed up updates and limit serving interference. Extensive evaluation shows that ZeroGR accelerates the filtering and scoring pipeline by up to $9.9\times$ over representative baselines while reducing GPU index memory use and accelerating index reconstruction.

cs.DB · cs.IR

新论文 · v1arXiv:2611.04337

Mitigating Spatial Blindness in Multiple Instance Learning for Whole-Slide Image Analysis

Xiangyu Li, Jincheng Li, Xing Xie, Bin Guan, Shaohua Kevin Zhou, Rui Yan, Ran Su

原文摘要

Whole-slide multiple instance learning can predict diagnostic and prognostic labels from tissue composition while making limited use of spatial organization. Providing coordinates or a graph does not establish that a trained predictor uses tissue neighborhoods. We examine this gap as spatial blindness and hypothesize that early composition learning can weaken supervision of a spatial pathway. We introduce ResTopoMIL, which freezes a learned composition predictor before training a graph residual with a coordinate-reassignment separation loss. Permutation and information analyses distinguish architectural symmetry, available spatial information and the proposed optimization mechanism. On a controlled spatial task, staged training achieved an AUC of 0.987, compared with 0.684 for the same jointly trained architecture. Performance remained high on a composition-only task. Across four WSI classification and five survival benchmarks, ResTopoMIL improved mean primary performance on eight tasks; four improvements remained significant after Holm-adjusted patient-cluster tests. Coordinate-free residual controls recovered some of the gains, while neighborhood destruction reduced performance close to the composition anchor. Neighborhood-preserving transformations and anatomy-stratified perturbations further characterized this dependence. These results support fixing a composition reference as a practical intervention for learning spatial corrections, while retaining additional appearance capacity as a contributing explanation.

cs.CV

新论文 · v1arXiv:2611.04327

Anchor: Augmented Cross-Layer Recurrent State for Long-Context Retrieval in Test-Time Training

Vimal William, Yuanzhe Li, Danella Zhao, Huanrui Yang

原文摘要

Parameter-efficient linearization turns a pretrained autoregressive Transformer into an efficient model by hybridizing sliding-window attention (SWA) with a constant-size recurrent memory. But does every layer's recurrent state contribute to long-context retrieval? Investigating an SWA and Test-Time Training (TTT) hybrid, we find that retrieval is sparse across depth, concentrated in a few anchor layers, and that the remaining states hold similar information expressed through layer-specific transformations. We exploit both observations in Anchor: TTT memory placed only at the anchor layers, and a cross-layer recurrent state written once and read by many layers, each through its own learned read map that realizes a layer-specific stretch and rotation, along with demonstrated generalization to other hybrid attentions. On Llama-3.1-8B and Mistral-7B, Anchor delivers 2.3-3.1x higher recall and 6.7-8.9 points higher MMLU accuracy than LoLCATs with a 10x smaller recurrent state, retains 91-95% of the teacher's MMLU accuracy, and cuts end-to-end latency by up to 4.3x relative to softmax attention.

cs.LG · cs.AI

版本更新 · v3arXiv:2602.20191

MoBiQuant: Mixture-of-Bits Quantization for Token-Adaptive Any-Precision LLM

Dongwei Wang, Jinhee Kim, Seokho Han, Denis Gudovskiy, Yohei Nakata, Tomoyuki Okuno, KhayTze Peong, Kang Eun Jeon 等 11 位作者

原文摘要

Dynamic runtime latency and memory constraints necessitate flexible large language model (LLM) deployment, where an LLM can be inferred with various quantization precisions based on available computational resources. Recent work on such any-precision quantization either relies on hardware-inefficient vector quantization or induces additional scaling factors when switching between bit-widths. Meanwhile, existing post-training quantization (PTQ) methods calibrated for a fixed low precision show poor generalizability under runtime precision change. In this work, we attribute the source of poor generalization across bit-widths to a precision-dependent outlier migration phenomenon where the distribution of PTQ-sensitive tokens changes across precisions. Motivated by this observation, we propose MoBiQuant, a novel any-precision Mixture-of-Bits quantization framework that adjusts weight precision for flexible LLM inference based on token sensitivity. Specifically, we propose a many-in-one recursive residual quantization that can iteratively reconstruct higher-precision weights at runtime and mitigates outlier migration with a token-aware router to dynamically select the optimal inference precision of each token.Extensive experiments show that MoBiQuant matches or surpasses frontier single-precision PTQ while exhibiting strong elasticity, achieving significant memory savings and throughput gains of up to $1.34\times$ over state-of-the-art any-precision methods. Our code is available at https://github.com/SimWangArizona/MoBiQuant.

cs.LG · cs.AI · cs.CL

新论文 · v1arXiv:2610.38439

Predict the Reward, Not the World: World Reward Models for ML Agents

Yuxiao Lee, Zherui Yang, Fan Liu, Hao Liu

原文摘要

Search-based machine-learning (ML) agents improve a solution by writing candidate programs, executing them, and keeping the best. Execution gives the search reliable feedback, but a single run can take hours, and most runs end in programs the agent discards. Recent agents try to save these runs by letting a large language model act as a world model that predicts how each program would perform. However, a wrong prediction feeds the search false information. We argue that an agent does not need to predict the outcome of execution, only the decision that execution would support. We propose World Reward Models (WRMs), which learn from real execution results to choose directly which candidate will perform better, without predicting any intermediate outcome. We prove that a selector which predicts execution from the same inputs cannot outperform the best direct selector, that predicted outcomes add an error which can make a likelihood-trained world model prefer the worse program on every instance, and that cross-entropy on executed winners drives a WRM toward the optimum. Our WRM, ForeCritic, adapts a 9B typed decision model to 5k executed program pairs. On 12,438 held-out pairs from 26 ML tasks, it picks the better program 79.4% of the time, while general-purpose LLM judges reach 53--62%, and its probabilities are calibrated. Inside AIDE, ML-Master, and ForeAgent, it cuts mean task time by 4.4--7.5 times while keeping their mean scores within 0.01 or raising them.

cs.AI · cs.CL

新论文 · v1arXiv:2610.38244

Precedent or Intent? What Coding Agents Follow When Evolving Existing Code

Haichao Zhu, Geyang Xu, Zhaorui Yang, Jiyuan Wang, Qian Zhang

原文摘要

Existing code reveals past implementation decisions but rarely explains the reasoning behind them. When coding agents implement new features or modify existing functionality, past decisions may conflict with new task instructions. This raises a fundamental question for agentic software evolution: when multiple implementations satisfy the same functional requirements, how do coding agents decide whether to follow existing code or new task instructions? We investigate this question through bidirectional, controlled experiments in purpose-built repositories, followed by validation in real-world open-source repositories. Our approach isolates three competing sources of guidance: (1) agents' default preferences, (2) repository precedents, and (3) explicit task instructions. We conduct 5,625 trials across four coding agents and six implementation pairs, with validation in four open-source repositories spanning three programming languages. We find that agents share the same default implementation choices, yet overwhelmingly follow repository precedent when it conflicts with those defaults (359/360 trials). Crucially, not all precedents carry equal influence: three supporting local files yield 96% adoption, compared with only 4% for sibling-resource files, and changing file placement alone can shift adoption from 0% to 100% at a fixed example count. When new task intent conflicts with existing code, written priority rules achieve substantially higher success than code examples alone (59/60 versus 38/60 joint successes for two agents on two implementation pairs). The effectiveness of explicit rules also extends to open-source repositories, where a harness-loaded rule raises joint success from 0/120 to 117/120. These findings motivate design-decision traceability that preserves not only implementation choices but also the rationale and priorities that should guide future changes.

cs.SE · cs.AI

版本更新 · v2arXiv:2603.29109

SemLoc: Structured Grounding of Free-Form LLM Reasoning for Fault Localization

Zhaorui Yang, Haichao Zhu, Qian Zhang, Rajiv Gupta, Ashish Kundu

原文摘要

Large language models (LLMs) can describe what a piece of code should compute, but they do so in free-form text. Such text cannot be checked against program executions, and it does not reveal whether a statement is correct. We present SemLoc, which turns LLM reasoning into executable, verifiable semantic constraints. With structured semantic grounding, the LLM writes each property as a constraint with a fixed category, attached to an anchor in the code graph, such as a variable definition, branch, loop, or return. SemLoc inserts each constraint as a runtime check and runs the tests, which yields a semantic violation spectrum over passing and failing tests. Counterfactual verification then patches the code at an anchor and reruns the tests; a patch that a constraint suggests counts as verified only if all tests then pass. We study SemLoc on fault localization, where the tests serve as the oracle for verification, with four LLMs on QuixBugs and on SemBugs, a new dataset of 809 real bugs from 750 GitHub projects. The constraints are executable: 99.4% become runtime checks, and on programs where coverage ties the faulty line with at least half of the covered lines, their violations alone rank it first in 40.9% of the cases, compared with 2.2% for spectrum-based fault localization and 7.0% for Daikon invariants. They make the LLM's answers verifiable: 68.4% of SemLoc's top-ranked answers carry a patch that the tests confirm, and 93.6% of these are correct, which the LLM's own confidence cannot match. SemLoc's first-rank accuracy does not differ significantly, for any of the four LLMs, from that of an LLM given the same inputs (81.4% vs. 82.0%), and it far exceeds that of an LLM that sees only the function (50.0%).

cs.SE · cs.AI