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
+92新增 AI 导读

arXiv 最近完成扫描:2026-11-23 01:07 · 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 2026-11-22 01:55 — 2026-11-23 01:55(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:2026-11-23 01:07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 130 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-23 01:05(北京时间)
新论文 · v1arXiv:2611.26318

ResVision:面向视觉推理的频谱匹配缩放与上下文保持检查

ResVision: Spectrum-Matched Resizing and Context-Preserving Inspection for Visual Reasoning

Guojian Zhan, Jiahao Xu, Yahui Liu, Yao Hu, Chuan Mu

AI 速读 基于摘要

ResVision 通过频谱匹配的自适应缩放与保留全局上下文的局部裁剪检查,缓解视觉推理中细节衰减、证据难检索和裁剪失配三类瓶颈。

cs.CV

查看原文摘要

Agentic visual reasoning improves vision-language models by selectively enlarging evidence without adding new scene content, but the benefit depends on whether fine structure remains accessible and whether local observations stay grounded in the full scene. We identify three recurring bottlenecks: high-frequency detail can be attenuated during visual-token formation; spatially distributed evidence can remain encoded yet difficult for the language model to retrieve; and isolated crops can weaken whole-detail correspondence through scale and positional mismatch. ResVision addresses these limitations with two complementary components. Spectrum-Matched Resizing (SMR) estimates image complexity and selects an adaptive global sampling scale, avoiding unnecessary enlargement on simple inputs while allocating more visual tokens to detail-rich images. Context-Preserving Inspection (CPI) returns each inspected crop together with the complete working view, preserving local detail and global context across tool turns. We evaluate Direct and Agentic variants on four frontier VLMs and 29 benchmarks spanning six visual-reasoning families. Complete ResVision (Agentic Base plus SMR plus CPI) is best for every model, improving by 3.36 to 4.94 points over Direct Base and 1.87 to 2.94 points over Agentic Base. These results show that adaptive visual sampling and context-preserving inspection address distinct, complementary constraints in multimodal reasoning.

版本更新 · v2arXiv:2603.23875

面向实时策略场景高效决策的自演化多智能体框架

Self-Evolving Multi-Agent Framework for Efficient Decision Making in Real-Time Strategy Scenarios

Li Ma, Hao Peng, Yiming Wang, Jie Liu, Kongjing Gu, Kangli Zi, Na Han, Hui Lin

AI 速读 基于摘要

提出 SEMA 自演化多智能体框架,通过自适应校准模型偏差、基于结构熵的动态观测剪枝与混合知识记忆机制,在 StarCraft II 场景中兼顾胜率与低延迟决策。

cs.MA

查看原文摘要

Large language models (LLMs) have demonstrated exceptional potential in complex reasoning,pioneering a new paradigm for autonomous agent decision making in dynamic settings. However, in Real-Time Strategy (RTS) scenarios, LLMs suffer from a critical speed-quality trade-off. Specifically expansive state spaces and time limits render inference delays prohibitive, while stochastic planning errors undermine logical consistency. To address these challenges, we present SEMA (Self-Evolving Multi-Agent), a novel framework designed for high-performance, low-latency decision-making in RTS environments. This collaborative multi-agent framework facilitates self-evolution by adaptively calibrating model bias through in-episode assessment and cross-episode analysis. We further incorporate dynamic observation pruning based on structural entropy to model game states topologically. By distilling high dimensional data into core semantic information, this approach significantly reduces inference time. We also develop a hybrid knowledge-memory mechanism that integrates micro-trajectories, macro-experience, and hierarchical domain knowledge, thereby enhancing both strategic adaptability and decision consistency. Experiments across multiple StarCraft II maps demonstrate that SEMA achieves superior win rates while reducing average decision latency by over 50%, validating its efficiency and robustness in complex RTS scenarios.

新论文 · v1arXiv:2611.25718

Hardening JavaScript Programs against LLM-Based Vulnerability Detection

Zhenhao Tian, Jintong Yu, Jingwei Feng, Jianwei Zhuge, Penghui Li

原文摘要

JavaScript programs are often distributed as source code, so attackers can analyze them for vulnerabilities. LLM-based vulnerability detection agents now make this analysis much easier. To mitigate this emerging threat, we present AntiAgent, a defense that lets developers harden their programs against such detection agents. AntiAgent transforms a program before release to impede an agent's analysis. To find effective transformations, AntiAgent evolves a corpus of programs with known vulnerabilities and traces how a detection agent analyzes each evolved version. It keeps the versions on which the agent misses or misreports the vulnerability and extracts their transformations into reusable rules. To protect a new program, AntiAgent carefully divides the task between an LLM and the rules, so that the transformations adapt to the program while preserving its semantics. We evaluate AntiAgent on real-world JavaScript applications against four detection agents, including Claude Code and Codex. AntiAgent reduces the number of vulnerabilities that each agent detects by 52.0-60.7%, outperforming the conventional obfuscator JS-Obfuscator and the LLM-based transformation method FPA on every agent. The transformed programs pass all project tests, indicating that AntiAgent preserves the original program semantics. The transformation rules also remain effective on vulnerability types absent from the corpus and on programs written in another language like Python.

cs.CR

新论文 · v1arXiv:2611.25626

Physical Laws without Physics Loss? Probing Learned Dynamics in Video World Models through Forced Response

Yutao Li, Chen Wang, Wangmeng Zuo, Hui Li

原文摘要

Do video world models learn physical laws without a physics loss, or merely imitate motion? Overall motion and appearance scores cannot settle it. We investigate this through nonlinear forced response: an excitation shakes the support of a suspended object. We introduce dual visual-numeric conditioning and adapt six image-to-video backbones to predict this motion using only the flow-matching loss. Wan predicts motion accurately and generalizes to unseen excitations, objects, poses, and scenes. Counterfactual tests suggest capabilities beyond replaying training videos. But what laws have they learned? We design three tiers of tests using Taylor expansions of the dynamics and geometry. All six reproduce the linear response, including resonance; five capture higher-order dynamics, including nonlinear softening. Remarkably, softening is barely present in training: only 0.74% of the swing's squared displacement. Extensions to a double pendulum and a rocking block show sustained dynamics are learned more faithfully than brief impacts. Yet learned dynamics may fail to appear when state estimation or propagation goes wrong. We turn these tests and findings into strategies to improve video training and generation.

cs.CV · cs.LG

版本更新 · v2arXiv:2611.16310

Selective Generative Restoration for Video Deraining via Uncertainty-Aware Diffusion

Yi'ang Chen, Han Li, Laibin Chang, Hui Liu, Kui Jiang, Junjun Jiang

原文摘要

Video deraining is challenging due to rain streaks, occlusions, and atmospheric effects. Existing methods mainly follow a deterministic restoration paradigm, assuming that clean scenes can be uniquely recovered from rainy observations. However, rain degradation is spatially heterogeneous. Reliable regions require faithful reconstruction, whereas severely occluded regions contain ambiguous content that require stronger prior-driven inference. Therefore, conventional deterministic restoration often produces over-smoothed results, while global generative restoration may introduce unnecessary hallucinations. We introduce a Selective Generative Restoration paradigm for video deraining, where generative priors are adaptively activated according to restoration uncertainty. Based on this principle, we propose Selective Generative Video Deraining (SGVD), an uncertainty-aware diffusion framework that enables adaptive fidelity preservation and generative recovery. Specifically, SGVD exploits stochastic diversity between dual one-step diffusion predictions to estimate region-level restoration uncertainty, which determines where observation fidelity should be preserved and where generative inference should be activated. Furthermore, an anchor-guided trajectory consistency mechanism is proposed to regularize stochastic diffusion evolution across frames, reducing temporal generation drift and improving video coherence. To achieve practical efficiency, SGVD adopts one-step diffusion inference while maintaining uncertainty-aware generative capability. Extensive experiments demonstrate that SGVD achieves superior restoration performance, perceptual quality, and temporal consistency compared with state-of-the-art video deraining methods.

cs.CV

版本更新 · v2arXiv:2611.20448

MMIntentFlow: An Intent-Driven Real-Time Multimodal Search System with Image-Text Queries at Xiaohongshu

Dongjia Zhao, Yuchen Ma, Chunsheng Shi, Ziqiu Gui, Chao Yuan, Jianing Zhu, Zhaoxing Zhang, Yahui Liu 等 12 位作者

原文摘要

Multimodal search with image-text queries helps users find notes in user-generated content (UGC) communities and serves as a key search tool for multimodal search agents. For such queries, query-note relevance depends on the user's retrieval intent and cannot be determined by visual or topical similarity alone. Simply reranking visual search results cannot fully address this challenge, as notes relevant to the user's intent may be missing from the initial candidate set. This motivates explicit intent modeling to align candidate retrieval and reranking under consistent relevance criteria. We present MMIntentFlow, an intent-driven real-time multimodal search system deployed at Xiaohongshu over an index on the order of ten billion entries. MMIntentFlow represents retrieval objectives with a hierarchical intent taxonomy and uses intent-specific relevance criteria to guide data construction, representation learning, and reranking. An offline agentic data workflow acquires candidates and verifies their relevance under these criteria to produce training supervision. The embedding model combines intent-aware contrastive learning, graded ranking, and distribution distillation, while a compact reranker assesses query-candidate evidence conditioned on predicted hierarchical intents. Evaluations demonstrate that MMIntentFlow delivers substantial gains in search engagement while supporting real-time search at industrial scale. In a user-level A/B test on the Xiaohongshu platform, MMIntentFlow outperforms the existing production system based on visual search followed by reranking, achieving relative gains of 28.17% in Top-4 query click-through rate, 18.96% in query click-through rate, and 12.56% in average time spent on search results pages per user. Production monitoring records an end-to-end P50 latency of 1.07 s.

cs.IR

新论文 · v1arXiv:2611.25394

Behavioral Containment: Source-to-Binary Function Matching for 1-Day Vulnerability Detection

Yifei Yang, Xuejiao Luo, Penghui Li

原文摘要

Vulnerabilities in reused open-source code often propagate into deployed binaries. Detecting them requires source-to-binary function matching, which locates the affected source function in a binary. Applying prior binary-to-binary approaches to this task would require compiling the source code with the same build configuration as the target binary, which is usually unavailable. Decompiling the binary does not make prior source-to-source approaches work either, because decompiled code differs substantially from the original source code. We observe that compilation transforms the code of a function but largely preserves its behavior. A binary function that implements a source function therefore contains its behavior, a property we call behavioral containment. Building on this, we present SBIND, which decompiles the binary and checks behavioral containment instead of comparing code. SBIND represents each function by behavioral paths, sequences of normalized operations from its entry to its exits, and aligns source paths with binary paths in order. To detect 1-day vulnerabilities, SBIND compares the binary with the vulnerable and the patched source only on the paths through the changed lines. On stripped binaries built with two compilers, two optimization levels, and four architectures, SBIND ranks the correct function first in 77.87% of 32,008 searches, against 45.69% for the state-of-the-art approach SBridge. On 26 1-day CVEs, SBIND reaches an F1 score of 0.70 on stripped binaries, against 0.51 for SBridge. Our replication of SBridge also revealed several issues in its implementation and evaluation, and its authors have acknowledged them.

cs.SE

新论文 · v1arXiv:2611.25126

TALD: Transferability-Aware Logit Disentanglement for Cross-Modal Knowledge Distillation

Hui Li, Pengfei Yang, Xinyi Feng, Junhong Liu, Tianyang Zheng, Hui Zeng, Le Dong, Kaibing Zhang 等 10 位作者

原文摘要

Cross-modal knowledge distillation can incur negative transfer when source-modality supervision conflicts with the target modality's discriminative characteristics. We propose TALD, a two-stage framework for Transferability-Aware Logit Disentanglement in class-aligned logit space. Guided by task-dependent self-benefiting and cross-modal exclusivity criteria, a Residual Disentangler decomposes logits from a teacher and an independently trained target-modality reference student into modality-general and modality-specific components. A Sample-Adaptive Modulator regulates decomposition constraints and sample-specific fusion weights. The learned modality-general components are then adaptively fused to supervise the final student. Across five benchmarks spanning vision, audio, and text, TALD achieves the largest mean accuracy gain and highest positive-transfer frequency among the compared methods. Across ten transfer directions with five runs each, TALD improves over training without distillation in 84% of evaluations, compared with at most 70% for the baselines, while offering a favorable accuracy-efficiency trade-off. We plan to release the code.

cs.CV

新论文 · v1arXiv:2611.24192

TrajWAM: Trajectory-Conditioned Future Learning for Vision-Language Driving

Xuerui Fang, Gulimila Kezierbieke, Chen Wangxing, Hui Li

原文摘要

World Action Models (WAMs) connect future scene prediction with action planning for autonomous driving. Each driving record pairs an executed ego trajectory with its observed future, providing a factual outcome for learning this connection. We present TrajWAM, a trajectory-conditioned WAM that improves vision-language driving through auxiliary bird's-eye-view (BEV) future learning. An ego-trajectory query conditions DINOv3-aligned BEV predictions from shared planner representations. Training combines factual reconstruction under the executed trajectory with one-sided feature separation under an unlabeled perturbed trajectory. Together, these objectives train the shared planner to generate driving waypoints. Native inference directly generates waypoints and bypasses the auxiliary future-prediction branch. On all 220 Bench2Drive routes, TrajWAM achieves 91.53 Driving Score and 75.45% Success Rate, exceeding a schedule-matched planning-only fine-tuning baseline by 5.31 Driving Score points and eight successful routes.

cs.CV · cs.RO

新论文 · v1arXiv:2611.24021

Continuum: Boundary-State-Aware Deterministic Scheduling in Dynamic LEO Networks

Siqi Yang, Zonghui Li, Chaoqun You, Yue Gao

原文摘要

Low Earth Orbit (LEO) constellations support mission-critical services requiring bounded latency and predictable delivery. However, conventional snapshot-based schedulers discard the forwarding progress of unfinished time-triggered traffic across topology transitions, degrading schedulability and timing consistency. We present Continuum, aboundary-state-aware rolling-horizon scheduling framework. Continuum inherits buffered-node and arrival-time information, jointly optimizing remaining routes and transmission slots, and refines latency to improve timing consistency while preserving original timing constraints. Ablations show up to 16.6 percentage points higher schedulability from boundary-state inheritance and a 10.9-37.7 times reduction in mean jitter from joint alignment. Scalability experiments evaluate synthesis performance for workloads of up to 10K flows.

cs.NI

新论文 · v1arXiv:2611.23690

A Probabilistic Behavioral RTL Simulation Framework for Probabilistic Compute Fabrics

Zehuan Wang, Chaohui Li, Ruihong Yin, Xunqi Li, Chris H. Kim

原文摘要

Coupled oscillator Ising hardware can produce different solution qualities across repeated runs of the same problem, while a deterministic behavioral model used for the design yields a single outcome under fixed conditions. Capturing this stochastic variability during design time is essential for evaluating how closely simulation reflects silicon behavior. This work presents a probabilistic behavioral RTL simulation framework that introduces Gaussian timing variation into coupling delays. This variation changes oscillator timing during evolution, producing different outcomes across runs while retaining the existing chip control and readout blocks. The framework is evaluated against measurements from two chips: a 28-nm CMOS chip with 66 spins and a 16-nm FinFET chip with 49 spins, using 250 problems run 100 times repetitively. Compared with deterministic simulation, the model reduces the average absolute gap between sorted simulation and silicon outcomes by 14.0% and 28.4% on the two chips, respectively. These results demonstrate that a simple behavioral timing variation model can be a useful tool for designing and verifying probabilistic computing chips.

cs.ET

版本更新 · v3arXiv:2610.26825

MemT-1.0: Towards Memory-Native Evolution

Zhiyu Li, Zeyu Zhang, Linyun Liu, Yiwei Bu, Chenyang Xi, Xichong Zhang, Yi Yu, Yu Yu 等 74 位作者

原文摘要

Memory-native evolution requires making memory an intrinsic capability of foundation models, enabling them to continuously accumulate and utilize information. To this end, we introduce MemT-1.0, a new architecture of memory foundation models that internalize memory as part of model computation. Building on Metis, MemT-1.0 employs Gated DeltaNet-2 with a stable token-level memory update mechanism within each turn. We further introduce Mixture-of-Storage to scale native memory capacity. Following a deliberate backbone preparation, we develop a two-stage training pipeline consisting of continued pre-training and post-training, supported by 34B tokens of training data and efficient training and inference infrastructure. We release a model family comprising MemT-1.0-Nano, MemT-1.0-Flash, and MemT-1.0-Pro, and conduct a comprehensive evaluation of memory and general capabilities. The results show that they outperform the parametric memory baselines on average and remain competitive with retrieval-augmented methods, while largely preserving general capabilities. At a history length of 128K tokens, MemT-1.0-Nano achieves approximately $1.86\times$ end-to-end inference speedup and a $66\times$ reduction in persistent storage relative to full context KV cache. By internalizing retrieved procedural experience, MemT-1.0 improves task success on agentic tasks, providing a practical step toward memory-native evolution.

cs.CL · cs.LG

版本更新 · v2arXiv:2610.34203

MatOS: An Agent Operating System for Materials Research

Dingyang Lyu, Jing Gao, Zhonghao Chang, Jingjie Huang, Xiangran Cheng, Xin He, Yongda Huang, Zhen Lei 等 17 位作者

原文摘要

Materials research relies on scattered and growing data, knowledge, and simulation tools, and a single study often spans multi-day workflows across literature analysis, computation, and experiment. Large language model agents can now retrieve materials data, operate simulation codes, and close design-synthesis-characterization loops with autonomous laboratories. However, extending these agents with new capabilities, keeping long-running tasks on track, and letting them learn from past tasks and user feedback remain difficult. Here we present MatOS, an agent operating system for materials research with three core components: (1) a layered scientific asset graph that organizes data, knowledge, tools, skills, roles, and workflows as reusable assets; (2) a stateful adaptive workflow that runs tasks as explicit execution graphs with scientific checks, so that they can be resumed and traced; and (3) evidence-driven asset evolution, which revises these assets from execution records and user feedback. On ResearchClawBench, MatOS improves on the previously best-performing agent by 11.15% with the same base model and extends the cost-score Pareto frontier. With a common base model, it outperforms Codex CLI and Claude Code, exceeding Codex CLI by 2.13% on MatTools and 4.17% on SciAgentGym. In eight research cases, MatOS narrowed more than 30 million candidate structures to 97 solid-electrolyte candidates, identified 89 halide variants with higher computed conductivity than their parent structures, linked the force errors of 11 pretrained interatomic potentials to local atomic environments, and supported two new methods that reduce errors by 3.1% and 13.6% relative to their baselines. These results show that organizing research capabilities as reusable, evolving assets enables agents to carry out long, multistage materials studies. Code is available at https://github.com/DingyangLyu/MatOS.

cs.AI · cond-mat.mtrl-sci

新论文 · v1arXiv:2611.22733

Evolve in Panorama, Render in View: Panoramic World State Evolution for Video World Models

Longtao Jiang, Mingfei Han, Jianmin Bao, Tingjun Dai, Jinjie Wei, Zhiran Zhang, Xin Tao, Zhihui Li 等 10 位作者

原文摘要

Video world models should maintain a world that keeps evolving as the viewpoint changes. Yet when the camera turns away and returns, current models often freeze the unobserved scene, lose objects, or change their appearance, because content outside the view has no representation that keeps changing. We present PanoEvo, which uses a Panoramic Evolver to evolve the world state in the latent space of a panoramic video diffusion model, where every viewing direction is present at every time step, so the scene evolves whether or not it is observed. Existing panoramic video models are not trained to evolve a scene from a single image or the objects within it, so we build PanoEvo-Data, an event-centric dataset from real 360° videos, and train the Panoramic Evolver coarse-to-fine as an image-to-panoramic-video model. Since each view covers only a small part of the low-resolution panorama, directly projected views are blurry and often show low-quality details or structural errors. A Perspective Renderer, built on a perspective video diffusion model, reads this state via latent-space projection and direction-restricted cross-attention to render sharp, high-quality views. PanoEvo achieves the best overall score among 23 publicly evaluated models on WRBench and the highest total score on STEVO-Bench. Code, models, and data will be released.

cs.CV

版本更新 · v2arXiv:2611.21530

DuoFlow: Towards Synchronized Speech and Motion Generation with Fine-Grained Control

Jun Dong, Ronghui Li, Zhongyuan Hu, Yunqi Zhao, Lijie Guo, Ruizhang Xu, Di Kang, Linchao Bao 等 9 位作者

原文摘要

An embodied speaker's expressiveness depends not only on what is said, but also on how the voice sounds and how the body moves. However, existing joint speech-motion generation models are largely driven implicitly by transcript semantics or intermediate speech representations, offering little explicit control over motion hierarchy, body parts, or vocal style. To bridge this gap, we construct MotionSpeech, a structured benchmark for controllable joint speech-motion generation that includes transcripts, voice-style descriptions, and motion conditions at two hierarchical levels. Building on this benchmark, we propose DuoFlow, a dual-stream latent flow transformer that jointly denoises speech and motion under a shared noise level and a unified second-based temporal coordinate. Modality-specific residual connectors inject structured conditions into the corresponding streams, layer-wise bidirectional cross-modal attention coordinates their generation, and a monotonic phoneme pathway combines normalized progress anchors with CTC supervision to strengthen speech temporal modeling. DuoFlow provides a unified interface for fine-grained motion and vocal-style control and demonstrates the ability to synthesize high-quality, synchronized, and instruction-consistent speech-motion sequences. Project page, https://jundong-dev.github.io/DuoFlow-project-page.

cs.CV

版本更新 · v2arXiv:2608.24089

CodeHID: Learning an Addressable Hierarchical Code Index for Generative Code Retrieval

Zhen Li, Yuhong Chen, Wenhao Xu, Xiaodong Li, Hui Li

原文摘要

Code retrieval models have predominantly relied on a flat matching paradigm that treats code snippets as independent candidates, making them less capable of distinguishing similar code candidates. Generative retrieval offers a solution by constructing a learnable index over the code corpus, guiding the retriever to better understand how code candidates are semantically organized and addressed. However, naively applying generative retrieval in the code retrieval task may result in operating over an identifier space whose prefixes do not correspond to meaningful code-semantic regions. In this paper, we propose CodeHID, a generative code retrieval framework that reformulates the code retrieval task from flat candidate matching to coarse-to-fine semantic address generation. CodeHID relies on two core components. First, Pseudo-Neighbor Guided DocID Learning constructs a globally static hierarchical index by applying multi-level residual quantization and $k$-nearest-neighbor pseudo-supervision, ensuring that semantically related code snippets share prefixes while preserving target-level separability. Second, Dual-Phase DocID Generation Guidance reliably navigates this fixed index by combining training-side ranking enhancements, using hard negatives and rank distillation, with inference-side candidate constraints and prefix-aware decoding. Extensive experiments on CoSQA and ProCQA benchmarks demonstrate that CodeHID outperforms existing sparse retrieval, pre-trained code models, dense code retrieval, and generative retrieval baselines by a large margin in most cases, achieving particularly strong improvements in rank-one retrieval metrics.

cs.IR

版本更新 · v2arXiv:2610.18352

Let the Mind Conceive, Let the Hand Achieve: Coupling Grounded Action and Progress Evaluation for Long-Horizon Manipulation

Youpeng Wen, Gang Wang, Tianyu Huang, Weiwei Zhang, Zhijian Huang, Wei Chen, Xieyuanli Chen, Yunhui Liu

原文摘要

A robot following a multi-step instruction needs to act on the right objects in the right order, even as the scene changes. It must also maintain awareness of task progress and determine when to advance. To address these challenges, we introduce Orchestra, an agent harness that separates task planning and execution management from action generation. Orchestra decomposes a complete multimodal instruction into ordered subtasks, tracks completed steps, and updates the locations of relevant objects and destinations during execution. It maintains a shared context containing the active subtask, spatial grounding, and recent observations. An action policy uses this context to generate actions, while a separately trained progress evaluator estimates when to advance to the next subtask. To evaluate whether robots trained on atomic instructions and short trajectories can execute longer subtask sequences, we introduce a benchmark named RMBench-Compose. Orchestra achieves a mean success rate of $68.22\%$ across nine RMBench tasks, outperforming Mem-0 by $26.22$ percentage points. On RMBench-Compose, it achieves an Average Success Length (ASL) of $7.35$ subtasks, $2.46$ times that of HarnessVLA. Across four real-world multi-step tasks, it improves mean ASL by $25.0\%$ over Orchestra using the base $π_{0.5}$ policy. These results show that Orchestra helps robots carry out longer sequences of subtasks while preserving the requested subtask order and acting on the specified objects. Our code and project page are available at https://youpengwen.github.io/Orchestra

cs.RO · cs.AI

新论文 · v1arXiv:2611.22017

SkillBuffBench: Measuring What Agent Skills Contribute across Harnesses, Models, Skill Access Modes and Memory

Gengyue Dong, Ye Wei, Zheng Zhu, Yidong Han, Jiale Miao, Xiaojun Jia, Guanghui Li

原文摘要

Agent Skills, file-based packages of procedural knowledge that a coding agent can discover and load on demand, are now shipped by every major agent harness, yet the evidence for how much they help comes almost entirely from settings in which the right Skill is hand-picked for the task and the agent starts from a blank slate. Neither holds in deployment, where an agent chooses from whatever library happens to be installed and frequently carries memory from earlier work. We present SkillBuffBench, a benchmark and paired evaluation protocol that treats Skill access as a three-level factor (no Skill, a curated Skill, and automatic invocation from an installed library), crosses it with memory (off and on), with four agent harnesses and with multiple models (the state-of-the-art proprietary models from Anthropic, Google and OpenAI, and the state-of-the-art open-weight models from Chinese providers), every model being run under every harness, and evaluates the result on research tasks contributed by domain experts together with the Skills they use, currently in materials science and biology, with the suite extended on a rolling basis. Every run is marked by a deterministic verifier; uncertainty is reported with a paired, task-level bootstrap; and cost, agent rounds and wall-clock time are reported alongside the score rather than folded into it. This version of the paper describes the design of the benchmark, its evaluation protocol and its current tasks and Skills. The evaluation is in progress: results will be added once the runs are complete, and the task suite, results and analysis will continue to be updated on a rolling basis.

cs.AI · cs.CL · cs.LG

版本更新 · v2arXiv:2610.11161

VGGT-VLA-World: Intent-Conditioned 3D World Evolution for Autonomous Driving

Zhaoyang Liu, Zhigui Lin, Kun Jiang, Tianhui Li, Changye Liu, Ziying Song, Diange Yang

原文摘要

VGGT provides a strong foundation for geometry-centric world models by recovering unified 3D scene geometry from visual observations. Although recent extensions enable temporal 3D prediction, their future evolution remains weakly conditioned on driving intentions and actions, limiting their ability to model alternative action-dependent futures. We propose \textbf{VGGTWorld-VLA}, an intention-conditioned extension of VGGT-World for controllable 3D world evolution in autonomous driving. First, we introduce an action--semantic conditioning mechanism that injects complementary driving semantics and ego-motion representations into the future-token stream, enabling different future geometry predictions for the same observed scene under alternative ego actions. Second, we develop a geometry--language--action bridge that adapts historical geometry, VLA semantic features, and maneuver and trajectory representations for joint conditioning of future geometry prediction. We evaluate future geometry prediction on NAVSIM, with ablation studies examining the contributions of semantic and action conditioning. Compared with baseline, our method reduces future-depth RMSE by 13.7\% and improves $δ_1$ by 4.11 percentage points on NAVSIM motion subset. Controlled action-input interventions further show that the model uses the supplied action information. These results support semantic and action conditioning for controllable VGGT-based world prediction in autonomous driving.

cs.CV · cs.RO

版本更新 · v6arXiv:2605.18267

SRC-Flow: Compact Semantic Representations Enable Normalizing Flows for Image Generation

Longtao Jiang, Jianmin Bao, Zhendong Wang, Xin Tao, Zhihui Li, Xiaojun Chang

原文摘要

Normalizing flows (NFs) provide exact likelihoods and deterministic invertible sampling, but have historically lagged behind diffusion models for large-scale image generation. We identify a key obstacle: NFs are required to learn a single invertible transport over the full ambient space, making them highly sensitive to high-dimensional representations. This leads to a semantic-capacity mismatch in modern visual representation spaces, where semantic information is compact but encoded in overcomplete features. We propose SRC-Flow, which introduces a Semantic Representation Compressor (SRC) to compact high-dimensional RAE features into a low-dimensional semantic space before flow modeling and preserve reconstruction through the frozen RAE decoder. This compact space reduces the modeling burden of NFs and enables effective likelihood-based generation in semantic representation space. We further adopt constant noise regularization tailored to the fixed unconditional bijection learned by flows. On ImageNet 256x256 and 512x512, SRC-Flow achieves state-of-the-art generation quality among normalizing flow methods, with gFID scores of 1.65 and 2.07 under classifier-free guidance, while retaining exact likelihood computation in the compact semantic representation space and deterministic invertible sampling at the flow level. Codes and models will be released in the future.

cs.CV

新论文 · v1arXiv:2611.20810

Prediction-Driven Contract Matching with Controlled Overbooking for Cloud-Edge DDoS Scrubbing Markets

Yue Luo, Houyi Qi, Minghui Liwang, Xinlei Yi, Han Jiang, Xuejiao Zheng

原文摘要

Cloud-edge distributed denial-of-service (DDoS) scrubbing requires ex-ante capacity commitments under uncertain traffic, heterogeneous budgets, resource costs, and fulfillment risks. We develop a prediction-driven two-stage contracting mechanism coordinating business entities (BEs), edge scrubbing nodes (ESs), and a cloud scrubbing center (CS) through BE-ES (B&E) main-service and ES-CS (E&C) supplementary contracts. In the first offline phase, Transformer forecasts generate candidate reserved scrubbing rates, generalized Nash bargaining determines candidate prices, and interim many-to-one B&E matching permits controlled overbooking under scenario-based aggregate ES shortfall-risk assessment. In the second offline phase, formal E&C reservations are established subject to capacity and payment constraints; their finalized rates and prices update ES-side proxy scores and guide localized risk-aware B&E contract adjustment. During online fulfillment, an edge-first, cloud-assisted weighted proportional allocation policy allocates scrubbing capacity under finalized contracts without rematching, renegotiation, or additional cloud reservations. Experiments with CICDDoS2019-derived workloads show that the proposed mechanism satisfies the prescribed empirical shortfall-risk criterion across all 100 evaluated horizon-instance pairs, whereas the NoRisk ablation violates it in all 100. Runtime measurements indicate lightweight online fulfillment relative to offline contract formation. The evaluated configurations also exhibit limited overall scrubbing coverage and near-zero realized cloud utilization.

cs.NI

版本更新 · v2arXiv:2605.09636

PDEAgent-Bench: A Multi-Metric, Multi-Library Benchmark for PDE Solver Generation

Zhen Hang, Yushan Yashengjiang, Junhui Li, Huanshuo Dong, Yang Wei, Zhezheng Hao, Jiangtao Ma, Songlin Bai 等 24 位作者

原文摘要

PDE-to-solver code generation aims to automatically synthesize executable numerical solvers from partial differential equation (PDE) specifications. This task requires not only understanding the mathematical structure of PDEs, but also selecting appropriate discretization schemes and solver configurations, and correctly implementing the resulting formulations in finite-element method (FEM) libraries. Existing code generation benchmarks mainly evaluate syntactic correctness, or success on predefined test cases. To our knowledge, there is currently no publicly available benchmark specifically for PDE-to-solver code generation, and general-purpose code benchmarks do not fully capture the unique challenges of numerical PDE solution, such as ensuring solver accuracy, efficiency, and compatibility with professional FEM libraries. We introduce PDEAgent-Bench, to the best of our knowledge, the first multi-metric, multi-library benchmark for PDE-to-solver code generation. PDEAgent-Bench contains 645 instances across 6 mathematical categories and 11 PDE families, with common FEM libraries for DOLFINx, Firedrake, and deal.II. Each instance provides an agent-facing problem specification, a reference solution on a prescribed evaluation grid, and case-specific accuracy and runtime targets. PDEAgent-Bench adopts a staged evaluation framework in which generated solvers must sequentially pass executability, numerical accuracy, and computational efficiency checks. Experiments with representative LLMs and code agents show that models can often produce runnable code, but their pass rate drops substantially once accuracy and efficiency requirements are enforced. These results indicate that current agents remain limited in producing numerically reliable and efficient PDE solvers, and that PDEAgent-Bench provides a reproducible testbed grounded in the practical requirements of numerical PDE solving.

cs.AI

版本更新 · v2arXiv:2611.18026

A Generalizable Approach to Safety-Aware Robotic Behavior Planning with an Explicit Constraint Space

Xianxu Wu, Shang-Ching Liu, Zhaocong Liang, Hengxiang Chen, Yujian Ma, Shenwen Deng, Qiang Li, Yung-Hui Li 等 9 位作者

原文摘要

Large language and vision-language models have substantially advanced robotic behavior planning from natural-language instructions and visual observations. However, safe manipulation in tabletop environments remains challenging because the safety constraints required for a task depend on the surrounding scene and may not be explicitly specified in the instruction. We propose a safety-aware behavior planning framework based on an explicit Constraint Space that stores reusable textual safety rules. Rather than retrieving rules solely by semantic similarity, we formulate constraint selection as task- and environment-conditioned applicability learning. A lightweight query-conditioned dual-tower model identifies the constraints applicable to the current context, which are then provided together with the original task and image to a multimodal behavior planner. To handle incorrect constraint selections and previously unseen hazards, we introduce a multimodal Safety Inspector that evaluates generated primitive plans, reconstructs the complete applicable constraint set, and provides corrective planning feedback. Validated inspection feedback is further used for test-time adaptation of constraint applicability and parameter-efficient adaptation of the Safety Inspector through LoRA, while newly identified constraints are incorporated into the Constraint Space. The resulting framework integrates explicit safety knowledge representation,context-aware constraint selection, corrective safety inspection, and test-time knowledge adaptation for safety-aware robotic behavior planning.

cs.RO · cs.LG

新论文 · v1arXiv:2611.19917

Delayed Heuristic-Behavior-Target Coupling for Off-Policy Reinforcement Learning in Inventory Control

Enhui Li, Yuan Cheng, Peiting Han

原文摘要

Many reinforcement learning methods tie data collection to the task policy, while coordinating independently optimized behavior and target policies remains challenging. Policies learned by these methods can perform unreliably in long-horizon tasks under uncertainty, such as inventory control, where failures can incur extreme costs. We introduce Heuristic Behavior Policy Optimization (HBPO), an off-policy framework that routes heuristic guidance through persistent behavior learning, coupled with target-policy, updating separately with residual-based advantage estimation and emphatic weighting. Under matched environment interaction budgets on DSIS and its risk-augmented variant DSIS-RB, HBPO recovers many high-cost initial policies and improves most non-collapse comparison groups. Cold starts achieve competitive costs without final cost collapse across all tested seeds. We identify a transmission chain in the delayed heuristic-behavior-target coupling as a key driver of recovery and improvement. Generation-level diagnostics trace heuristic uptake and subsequent selective target responses, while component ablations support the contribution of this transmission mechanism to policy recovery and improvement.

cs.LG

版本更新 · v2arXiv:2611.02721

IssueLighter: An Issue Type-Aware LLM Agent for Issue Report Validity Assessment

Jiawei Ran, Yuxia Zhang, Ziyang Zhao, Hui Liu

原文摘要

Invalid issue reports are prevalent in open source software (OSS) projects, imposing substantial burdens on maintainers who already face a high risk of burnout. Prior research has primarily focused on identifying invalid reports for specific issue categories (e.g., bug and wontfix), leaving the broader landscape of OSS issue types largely unexplored and limiting the generalizability of existing approaches. Moreover, existing methods provide little support for explaining or validating their predictions, reducing their practical usefulness for maintainers. With the rise of LLM-based agents, it remains unclear whether a comprehensive understanding of the causes of invalidity across all issue types can improve validity assessment performance while producing well-grounded rationales. To this end, we first manually annotated the validity status of 520 issue reports from three OSS projects, i.e., pandas, scikit-learn, and mypy, resulting in 257 invalid reports and 263 valid ones. Then, we conducted a thematic analysis on these invalid reports and identified 13 causes of invalidity that are closely specific to issue types. Based on these insights, we propose IssueLighter, an agent-based framework with a type-aware validity assessment strategy that dynamically executes commands. Experimental results show that IssueLighter consistently and substantially outperforms all baseline methods, with an average F1 improvement of over 20 percentage points. Ablation studies confirm that both the type-aware strategy and the taxonomy of causes of invalidity contribute to the performance gains. Qualitative analysis further demonstrates that IssueLighter generates rationales grounded in accurately identified causes of invalidity and supported by evidence. Moreover, leveraging these rationales, we challenged maintainers' original decisions in four disputed cases, and all received approval.

cs.SE · cs.AI

版本更新 · v2arXiv:2602.24195

Uncertainty Quantification for Multimodal Large Language Models with Incoherence-adjusted Semantic Volume

Gregory Kang Ruey Lau, Hieu Dao, Nicole Kan Hui Lin, Bryan Kian Hsiang Low

原文摘要

Despite their capabilities, Multimodal Large Language Models (MLLMs) may produce plausible but erroneous outputs, hindering reliable deployment. Accurate uncertainty metrics could enable escalation of unreliable queries to human experts or larger models for improved performance. However, existing uncertainty metrics have practical constraints, such as being designed only for specific modalities, reliant on external tools, or computationally expensive. We introduce UMPIRE, a training-free uncertainty quantification framework for MLLMs that works efficiently across various input and output modalities without external tools, relying only on the models' own internal modality features. Inspired by Determinantal Point Processes (DPPs), UMPIRE computes a novel incoherence-adjusted semantic volume of sampled MLLM responses for a given task instance, which couples semantic embedding dispersion with the quadratic entropy of the responses. This approach effectively captures both the global semantic diversity of samples and the local incoherence of responses based on internal model confidence. We provide theoretical analysis motivating UMPIRE's design, and extensive experiments show that UMPIRE consistently outperforms baseline metrics in error detection and uncertainty calibration across image, audio, and video-text benchmarks, even with small sample budgets. We also demonstrate UMPIRE's generalization to non-text output tasks, including image and audio generation. Our code is available at https://github.com/daohieu17ctt/UMPIRE.

cs.AI · cs.CL · cs.CV · cs.LG

版本更新 · v2arXiv:2604.14833

Federated User Behavior Modeling for Privacy-Preserving LLM Recommendation

Hongyun Yang, Shicheng Wang, Xinhua Wang, Xinchang Zhang, Hui Liu, Lei Guo

原文摘要

Large Language Models have shown great success in recommender systems. However, the limited and sparse nature of user data often restricts the LLM's ability to effectively model behavior patterns. To address this, existing studies have explored cross-domain solutions by conducting Cross-Domain Recommendation tasks. But previous methods typically assume domains are overlapped and can be accessed readily. None of the LLM methods address the privacy-preserving issues in the CDR settings, that is, Privacy-Preserving Cross-Domain Recommendation. Conducting non-overlapping PPCDR with LLM is challenging since: 1)The inability to share user identity or behavioral data across domains impedes effective cross-domain alignment. 2)The heterogeneity of data modalities across domains complicates knowledge integration. 3)Fusing collaborative filtering signals from traditional recommendation models with LLMs is difficult, as they operate within distinct feature spaces. To address the above issues, we propose SF-UBM, a Semantic-enhanced Federated User Behavior Modeling method. Specifically, to deal with Challenge 1, we leverage natural language as a universal bridge to connect disjoint domains via a semantic-enhanced federated architecture. Here, text-based item representations are encrypted and shared, while user-specific data remains local. To handle Challenge 2, we design a Fact-counter Knowledge Distillation module to integrate domain-agnostic knowledge with domain-specific knowledge, across different data modalities. To tackle Challenge 3, we project pre-learned user preferences and cross-domain item representations into the soft prompt space, aligning behavioral and semantic spaces for effective LLM learning. We conduct extensive experiments on three pairs of real-world domains, and the experimental results demonstrate the effectiveness of SF-UBM compared to the recent SOTA methods.

cs.IR

版本更新 · v2arXiv:2611.12799

Agentic-OPD: Recovering Forgotten Agent Capabilities via On-Policy Distillation for Agentic Tasks

Tingcheng Bian, Kangye Gong, Jinchang Luo, MingQuan Cheng, Feiran Liu, Ni Li, Xiaoling Xia, Haiwei Wang 等 9 位作者

原文摘要

Reinforcement learning is now the mainstream paradigm for training LLMs on agentic tasks, yet standard practice keeps only the best-validation checkpoint and discards the rest. We show that this is lossy: in GRPO training of LLM agents, the best-validation checkpoint fails on problems that earlier checkpoints from the same run had already solved, and the union of problems solved across checkpoints far exceeds any single one. The discarded checkpoints thus form a teacher pool obtained at no additional training cost, which on-policy distillation (OPD) can mine to recover the lost coverage. Mining this pool raises two challenges: i) which checkpoint to distill from, as no checkpoint dominates the others and complementarity to the student is problem-specific; ii) where to trust it, as even a well-chosen teacher is only locally superior, so indiscriminate distillation overwrites behavior the student has already mastered. We propose Agentic-OPD, which treats the best-validation checkpoint as the student and all saved checkpoints as frozen teacher candidates, using the student's evolving capability gaps to guide both teacher selection and supervision filtering: the HCN policy (Highest Coverage Next) dynamically selects teachers by weighted coverage of the student's unsolved problems, while the LAD module (Locality-Aware Distillation) confines transfer to failed student rollouts on problems where the teacher performs better. Across five agentic task domains and 24 benchmarks and task subsets, Agentic-OPD improves over its initialization checkpoint by up to 7.4 points, with a 4B student surpassing the latest frontier models GPT-5.6 and DeepSeek-V4.1 on deep search. Agentic-OPD recasts a finished RL run as a reusable pool of policies and establishes post-RL capability recovery as a stage orthogonal to improvements in the RL algorithm itself.

cs.LG · cs.AI

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.

版本更新 · v3arXiv:2605.07388

A Marine Debris Detection Framework for Ocean Robots via Self-Attention Enhancement and Feature Interaction Optimization

Yuyang Li, Jiashu Han, Yinyi Lai, Wenbin Kang, Zenghui Liu

原文摘要

Marine debris detection for ocean robot is crucial for ecological protection, yet performance is often degraded by low-quality images with blur, complex backgrounds, and small targets. To address these challenges, we propose YOLO-MD, an enhanced YOLO-based detection framework. A Dual-Branch Convolutional Enhanced Self-Attention (DB-CASA) module is designed to strengthen spatial-channel interactions, improving feature representation in degraded images. Additionally, a lightweight shift-based operation is introduced to enhance fine-grained feature extraction for objects of varying scales while maintaining parameter efficiency. We further propose SFG-Loss to mitigate class imbalance and optimization instability via dynamic sample reweighting. Experiments on the UODM dataset demonstrate that YOLO-MD achieves 0.875 precision, 0.822 F1-score, and 0.849 mAP50, outperforming the latest state-of-the-art methods. The effectiveness of this method has also been verified through real-world robotic edge deployment experiments.

cs.CV