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

+197新增论文
+151其中 AI 相关
+16已有论文修订
+91新增 AI 导读

arXiv 最近完成扫描:2026-11-21 12:19 · 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 03:17 — 2026-11-22 03:17(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:2026-11-21 12:19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 1,861 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-21 12:17(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.

版本更新 · v3arXiv:2609.39601

GroundingPI:面向物理智能的视觉基元定位基础模型

GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives

Qize Yu, Lianrui Fan, Boyu Chen, Jiaqi Liang, Xini Ding, Yue Chen, Zetian Song, Yuran Wang 等 26 位作者

AI 速读 基于摘要

作者提出一个4B参数的定位基础模型GroundingPI,以点和框作为共享词表中的量化坐标,在34个定位基准上取得领先,并作为视觉骨干提升机器人与自动驾驶下游任务表现。

cs.CV · cs.AI · cs.LG · cs.RO

查看原文摘要

Precise grounding matters. It specifies which object is the target and where that object is, even in clutter and for tiny objects, and it has to be fast enough for closed-loop control. Yet vision-language-action (VLA) and world-action models (WAMs) take perception from general-purpose vision-language and video-generation backbones, which still fail in these settings. We introduce GroundingPI, a 4B grounding foundation model that generates points and boxes as quantized coordinates in a shared vocabulary. Training combines multimodal and spatial pretraining, supervised fine-tuning, and reinforcement learning with GRPO, using supervision from public datasets and dedicated data engines. Against 44 baselines across 34 grounding benchmarks spanning 11 perceptual capabilities, GroundingPI establishes a new state of the art, averaging 73.68%, above the larger GPT-6 Astra (71.54%). As a downstream visual backbone, GroundingPI improves performance on robotic manipulation and autonomous driving. Across RoboTwin 2.0 and RoboCasa-GR1, it outperforms all evaluated backbones in all four out-of-distribution settings, with relative gains of up to 24.8% over the strongest baseline. On RoboCasa-GR1, GroundingPI trained with 50% of the demonstrations outperforms those baselines trained with 75%. Its mean open-loop L2 error on nuScenes is 0.296 m. We systematically analyze GroundingPI's pretraining in scale and data composition. Grounding quality and downstream manipulation improve with pretraining scale, with generalization tracking perceptual gains most closely. Analyzing the data recipe across these 11 perceptual capabilities shows dense grounding's substantial benefits for both, and OCR's potential as a catalyst for perceptual learning. These results support grounding as a perceptual foundation, and dedicated perceptual pretraining as a promising direction for foundation models of physical intelligence.

版本更新 · v3arXiv:2609.39600

GroundAnything:以极速并行解码实现精准视觉定位

GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed

Qize Yu, Lianrui Fan, Bowen Ping, Xini Ding, Zetian Song, Junbo Niu, Kaixuan Wang, Tianxing Chen 等 22 位作者

AI 速读 基于摘要

提出4B参数的视觉定位基础模型GroundAnything,用块级去噪的双向扩散并行解码替代自回归串行生成,在30个定位基准上兼顾精度与速度。

cs.CV · cs.AI · cs.LG · cs.RO

查看原文摘要

Autoregressive (AR) grounding models serialize spatial predictions, introducing sequential latency and imposing a causal order on output tokens. We view grounding as visual evidence extraction: objects, locations, and spatial relations are jointly constrained by the image and query, yet their dependencies do not imply an intrinsic left-to-right generation order. This distinction makes bidirectional diffusion a natural fit, allowing spatial hypotheses to emerge in parallel and be jointly refined through iterative denoising. We introduce GroundAnything, a 4B-parameter grounding foundation model that reconciles fast parallel decoding with precise localization through blockwise denoising. Training combines grounding pretraining from public datasets and dedicated data engines, direct AR-to-diffusion conversion with joint AR and diffusion objectives, supervised fine-tuning, and GRPO-based reinforcement post-training. Across 30 grounding benchmarks, our autoregressive variant, GroundAnything-VLM, establishes a new overall state of the art among similarly sized models at 72.42%, remaining competitive with GPT-6 Astra (71.35%). With entropy-guided decoding, GroundAnything also surpasses the prior state of the art at this scale, averaging 61.75% versus 53.32% for the fast MTP-based LocateAnything model. We further explore decoding strategies, showing that an optional self-speculative mode achieves a 4.51$\times$ speedup over the AR counterpart with a 0.74 percentage-point drop in COCO F1mIoU. Infrastructure experiments show that progressive inference optimizations translate parallel decoding into practical speedups. These gains support efficient visual grounding in latency-sensitive real-world systems.

新论文 · v1arXiv:2611.26503

JARVIS:自主设计、构建与测试电路板的智能体

JARVIS: An Agent That Designs, Builds, and Tests Circuit Boards on Its Own

Shibo Zhou, Tianqi Hong, Zheng Yan, He Yang

AI 速读 基于摘要

作者提出具身智能体 JARVIS,用数字孪生预演加机器人执行,在无人干预下完成电路板的设计—制造—测试—学习闭环。

cs.RO · eess.SY

查看原文摘要

Power electronics is central to the energy transition, but developing new hardware still relies on human-led design, fabrication, testing, and iteration. We present JARVIS, an embodied AI agent that autonomously closes this loop for circuit boards. JARVIS maintains machine-specific capabilities and constraints, scans its workspace using a robot-mounted 3D scanner, and constructs an executable digital twin in which it rehearses robot motions, fabrication steps, and circuit behavior before consuming materials. A single text instruction initiates the physical experiment. Using unmodified desktop equipment, the agent coordinates a robot arm, a PCB printer that deposits conductive silver ink and solder paste, and a pick-and-place machine. It verifies progress using cameras and sensors, then tests the fabricated circuit with an OPAL-RT real-time simulator and an oscilloscope. Based on the measurements, JARVIS diagnoses deviations from the design and generates a revised design in KiCad for subsequent rehearsal. In a demonstration involving a 60 Hz notch filter for grid-connected converter sensing, JARVIS completed a first-run experiment in 2 h 39 min without human intervention, achieving 50.6 dB attenuation at 60 Hz. Its digital-twin rehearsal identified five issues before fabrication, including a test criterion that would have incorrectly rejected a functioning board. During execution, the agent also resolved encountered faults autonomously. These results demonstrate an integrated agent-driven workflow for physical design, fabrication, measurement, and iterative improvement of power-electronic circuitry. To our knowledge, JARVIS is the first system in power electronics in which an agent closes the physical design-build-test-learn loop for circuit boards.

新论文 · v1arXiv:2611.26444

Mind2Act World:面向机器人操作中具身心智、物理动作与心智-动作组合的诊断基准

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

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

AI 速读 基于摘要

作者提出一个包含30个仿真操作任务、180种配置的诊断基准,用Mind、Act、Mind2Act三个视图区分系统是缺少某种能力还是无法组合已有能力。

cs.RO · cs.AI · cs.CV

查看原文摘要

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

新论文 · v1arXiv:2611.26423

Seer:用共享决策模型引导小型深度研究智能体

Seer: Guiding Small Deep-Research Agents with Shared Decision Models

Yuhao Zhou, Yang Zhou, Yuanxi Li, Jindi Lv, Dan Si, Qing Ye, Jiancheng Lv

AI 速读 基于摘要

Seer 在推理阶段把智能体的动作提议与后果预测、价值估计分离,用离线训练、可跨智能体复用的模拟器与价值估计器为小型本地深度研究智能体提供引导。

cs.AI

查看原文摘要

Deep-research agents repeatedly decide what to search, read, and verify, often using large cloud-hosted language models for action proposal. However, privacy and local control motivate running agents on users' devices, where limited memory and compute favor smaller models and complicate on-device training. Yet inference-time guidance faces three obstacles: exploring alternatives through real execution adds tool calls, prompted self-evaluation is bounded by the agent's judgment, and model-specific guidance risks repeated adaptation costs. We introduce Seer, an inference-time framework providing local guidance that separates the agent's action proposal from learned consequence prediction and value estimation. From a shared corpus of real research trajectories, we train two models: a tool-response simulator on observed call--response pairs and a value estimator on histories labeled with discounted terminal correctness. The simulator and estimator are trained offline and reused across agents without further training. Moreover, Seer executes only the selected action and adds only real tool responses to the committed history, avoiding tool calls on discarded candidates at additional inference cost. Across multiple deep-research benchmarks, Seer substantially improves agent performance for different language models. For instance, GAIA accuracy rises from 13.6% to 41.7% for Qwen3.5-4B and from 22.3% to 50.5% for Qwen3.5-9B. Furthermore, our analyses suggest that broader candidate coverage can compensate for imperfect simulation, while prediction and scoring errors limit the benefits of wider imagined search. These findings highlight the potential of reusable models for prediction and evaluation to strengthen small research agents through extra local computation without the real execution of the discarded candidates.

新论文 · v1arXiv:2611.26414

ZeroVLN:无需对VLM大脑进行监督微调的导航学习

ZeroVLN: Learning to Navigate without Supervised Fine-Tuning of the VLM Brain

Zixuan Huang, Yang Zhou, Guli Zhang, Sunzhu Li, Hongyan Xie, Zehao Chen, Fuzhen Zhuang, Kaixuan Wang 等 11 位作者

AI 速读 基于摘要

ZeroVLN 提出慢-快导航框架,让 VLM 大脑通过语义工具调用接口下达自然语言移动指令,并在不对 VLM 大脑做导航域监督微调的情况下,用闭环强化学习联合优化大脑决策与动作专家执行。

cs.AI

查看原文摘要

Representative vision-language navigation (VLN) methods typically couple a vision-language model (VLM) brain with a learnable action head and fine-tune the VLM brain on navigation-domain data to predict geometric goals. However, such adaptation can substantially alter base VLM weights and degrade general visual capabilities. We introduce ZeroVLN, a slow-fast navigation framework that achieves effective navigation with zero navigation-domain SFT of the VLM brain. Rather than teaching the brain to predict geometric goals, we equip it with a semantic tool-calling interface for conveying movement decisions to an action expert in natural language. We first adapt the action expert to carry out these movement requests, then jointly improve the brain's movement decisions and the action expert's continuous execution through closed-loop reinforcement learning (RL). Trained on the same navigation episodes, ZeroVLN substantially outperforms representative SFT-based hierarchical VLN methods on standard VLN-CE (continuous environments) benchmarks, while inducing only minor changes to the brain's weights and largely preserving its general capabilities. To our knowledge, ZeroVLN is the first slow-fast VLN framework with zero navigation-domain SFT of the VLM brain, and the first to jointly optimize its slow and fast policies through closed-loop agentic RL in VLN-CE.

新论文 · v1arXiv:2611.26407

非高斯源下的流匹配:高效采样理论

Flow Matching from Non-Gaussian Sources: A Theory of Efficient Sampling

Yuchen Zhou, Lili Zheng, Yuxin Chen, Gen Li

AI 速读 基于摘要

作者为非高斯源分布的流匹配欧拉离散采样建立了非渐近收敛理论,在源分布满足正密度、有限总方差和Lipschitz得分等条件下给出了总变差误差的迭代复杂度。

stat.ML · cs.AI · cs.IT · cs.LG

查看原文摘要

Flow matching is a versatile framework for generative modeling that transports a source distribution to a target data distribution. A key advantage is its flexibility in the choice of source distribution, such as heavy-tailed and multimodal sources. Yet finite-step sampling guarantees for non-Gaussian sources remain limited. We establish a nonasymptotic convergence theory for Euler discretization of flow matching with linear interpolation. Suppose the source distribution on $\mathbb{R}^d$ has an everywhere positive, continuously differentiable density, finite total variance $\mathsf{TotVar}_{\mathsf{base}}$, and an $L$-Lipschitz score. Using the population velocity field and a suitable time grid, this sampler achieves total variation error at most $\varepsilon$ in $\widetilde{O}(Ld\mathsf{TotVar}_{\mathsf{base}}/\varepsilon)$ iterations, provided the target distribution satisfies a mild second-moment condition. These assumptions cover, among many examples, source distributions such as multivariate Student's $t$ distributions with more than two degrees of freedom and finite Gaussian mixtures with shared covariance, while accommodating target distributions with neither a smooth density nor bounded support.

新论文 · v1arXiv:2611.26390

SpecFlow:加速度谱中的流匹配用于多智能体轨迹预测

SpecFlow: Flow Matching in the Acceleration Spectrum for Multi-Agent Trajectory Forecasting

Ziyang Xu, Peng Han, Hai Zhou

AI 速读 基于摘要

SpecFlow 将未来加速度的 DCT 系数作为生成状态,用条件流匹配从噪声生成加速度谱,再经解析积分重建速度与位置,用于多智能体轨迹预测。

cs.RO

查看原文摘要

Multimodal trajectory forecasting must cover diverse future behaviors without sacrificing dynamical coherence. Most generative forecasters evolve frame-wise positions directly, leaving the relationships among position, velocity, and acceleration implicit. We present SpecFlow, a conditional flow-matching framework that treats the Discrete Cosine Transform (DCT) coefficients of future accelerations as its generative state. SpecFlow learns a transport from Gaussian noise to acceleration spectra and reconstructs velocity and position through fixed analytical integration initialized by the last observed state. A joint phase-space objective supervises all three kinematic levels. To represent destination uncertainty without future information, an endpoint predictor produces candidate destinations and confidence scores solely from observed context, and the highest-confidence candidate conditions the spectral denoiser. Alternating attention over trajectory hypotheses and agents captures multimodality and interaction. Under best-of-20 evaluation, SpecFlow achieves average minADE/minFDE of 0.15/0.22 on ETH/UCY, 0.69/0.86 at four seconds on NBA, and 7.38/11.57 on SDD. It establishes state-of-the-art results across all five ETH/UCY scenes and achieves the lowest four-second ADE on NBA with a tied-best FDE, while remaining competitive on SDD. Together, these results demonstrate that acceleration-spectrum flow matching provides an effective structured generative state across smooth pedestrian motion, coordinated multi-agent sports dynamics, and heterogeneous outdoor trajectories. Code will be made publicly available.

新论文 · v1arXiv:2611.26376

对齐驱动复用:从异构经验中学习可泛化的机器人使用智能体

Alignment Drives Reuse: Learning Generalizable Robot-Use Agents from Heterogeneous Experience

Ziyue Wang, Yaopeng Yang, Liyi Zhou

AI 速读 基于摘要

UniCraft 通过对齐异构场景几何、传感与控制接口及任务格式,让来自多个基准和本体的交互经验共同打磨一套共享操作技能与调度策略。

cs.RO

查看原文摘要

Vision-language models (VLMs) demonstrate broad generalization across tasks and domains. However, comparable generalization in robot manipulation remains challenging. Heterogeneity in robot embodiments, task formulations, geometric conventions, and action interfaces fragments interaction experience across benchmarks and hardware. We rethink robot skill learning through alignment: Can heterogeneous interactions across benchmarks and embodiments jointly improve one shared skillset for robot manipulation? We propose UniCraft, a framework for learning robot manipulation skills by aligning heterogeneous settings. Specifically, UniCraft represents observed scene geometry using consistent coordinate conventions and aligns sensing and control interfaces across robots. It organizes tasks from different benchmarks in a canonical format, allowing interaction feedback to jointly refine shared skills and the orchestration policy that guides their selection and composition, without any demonstrations or model weight updates. We interleave tasks from 3 benchmarks and 6 embodiments, collecting 2,700 learning rollouts per agent model. During training, UniCraft improves pooled task success on unseen scenarios and tasks by 9-28 percentage points on LIBERO-PRO, 10.8-13.3 on RoboTwin 2.0, and 3.1-14.4 on RoboCasa365 (Epochs 1-3). After training, with the learned skills frozen, UniCraft demonstrates zero-shot transfer across 4 new robot embodiments and 5 additional agent models on robosuite and RoboDojo.

新论文 · v1arXiv:2611.26358

Beam 模型技术报告

Beam Model Technical Report

Reflection Team, Adam Abdulhamid, Osama Abuelsorour, Yasmin Alameddine, Carlo Alfano, Duarte Alves, Brandon Amos, Selvaraj Anandaraj 等 230 位作者

AI 速读 基于摘要

Beam 是一个面向编码、推理与智能体工作负载的稀疏 MoE 模型,总参数 501.3B、激活参数 23.4B,作者报告其推理算力需求比同类模型低 3–4 倍。

cs.CL · cs.AI

查看原文摘要

Beam is a sparse Mixture-of-Experts (MoE) model with 501.3B total parameters and 23.4B active parameters, specifically built and optimized for coding, reasoning, and agentic workloads. Beam delivers frontier level reasoning, while requiring 3-4x less inference compute than many models of its class. Pretrained on 23.8T diverse, curated, high-quality tokens, Beam features a 1M-token context window achieved through a novel two-stage midtraining phase, built on verifiable, correctness-anchored data. Post-training leveraged a large-scale, fully asynchronous reinforcement learning (RL) campaign across 10.5K GB300 GPUs, generating over 100M rollouts over 4 weeks of training. We believe this is one of the largest scale RL runs conducted by any open lab to date. Across our evaluation suite, capabilities continued to improve as we increased RL compute, with no sign of a plateau. Supported by deep hardware-model co-design, FP8/NVFP4 quantization, and a 1.93B-parameter speculative decoding drafter (DFlash 2), Beam maximizes serving throughput with efficient, flexible deployment. Averaged across conversation turns and harm categories, Beam refuses or pivots on 88.9% of harmful requests while complying with 81.5% of harmless requests, achieving the highest refusal/pivot rate on harmful requests among open-weight models on the Pareto frontier.

新论文 · v1arXiv:2611.26349

Perfumer:基于大语言模型的智能体框架加速第一性原理计算中的结构弛豫与电子能带预测

Perfumer: A Large Language Model-based Agentic Framework Accelerating Structural Relaxation and Electronic Band Prediction for First-Principle Calculation

Zhiwei Li, Yuhao Zhou, Yikai Yang, Haonan Wang, Qing Ye, Jiancheng Lv, Kazunari Matsuda

AI 速读 基于摘要

Perfumer 是一个基于大语言模型的智能体框架,耦合 Quantum ESPRESSO 与两个预测模型,加速结构弛豫和电子能带预测。

cond-mat.mtrl-sci · cs.LG

查看原文摘要

First-principles structural relaxation and band calculations require substantial computation and expertise. Here we present Perfumer, a large language model-based agentic framework that couples Quantum ESPRESSO with two predictive models. Across tested structures, pre-relaxation with Perfumer-relax model followed by QE refinement yielded a 2.75-fold overall speedup over QE alone. Perfumer-band model combines a periodic graph neural network with a latent Hermitian spectral head returns 12 band energies at any requested wavevector, preserving reciprocal lattice periodicity and time-reversal symmetry without constructing Hamiltonian. Trained on 125,153 self-curated band structures, Perfumer-band model reaches a median per-material mean absolute error of 0.157 eV on 2,607 test materials, including lanthanide, actinide and magnetic compounds, from held-out composition families spanning 85 elements, taking about 97 ms per material on two consumer CPU cores. The agent turns natural-language requests into relaxation-to-band workflows, from a single uploaded structure to automatically constructed new candidates and returns predicted properties.

新论文 · v1arXiv:2611.26317

Language-Oriented Semantic Modeling for Target Language Extraction

Mehmet Sinan Yıldırım, Ke Zhang, Shuai Wang, Haizhou Li

原文摘要

Target Language Extraction (TLE) aims to isolate speech in a target language from multilingual mixtures. Existing approaches primarily rely on acoustic modeling with language identity labels, which provide only coarse categorical guidance. In this work, we propose a language-oriented semantic modeling framework that augments acoustic extraction with language-specific semantic representations. A pre-trained speech semantic model is adapted via language-aware prompt conditioning and parameter-efficient fine-tuning to generate target-language-focused semantic representations from the mixture. {These capture high-level semantic structure of the acoustics and they} are integrated into the extraction model to provide structured semantic guidance beyond identity labels. Experiments on the CommonVoiceMix dataset show that incorporating semantic representations consistently improves over acoustic-only baselines, achieving up to 1.16 dB SI-SDR gain.

cs.CL · eess.AS

版本更新 · v2arXiv:2610.37358

When Is Additional Retrieval Worthwhile? A Cost-Aware Study of Evidence Gain and Answer Reliability in RAG

Zhouting Zhao

原文摘要

Retrieval-augmented generation (RAG) can benefit from more sophisticated retrieval, but extra retrieval may be unnecessary for many questions and gains in evidence retrieval may not translate into faithful or correct answers. We study a cost-aware, two-action retrieval policy that chooses between a dense-retrieval-plus-reranking baseline and a hybrid lexical--dense retriever. Rather than classifying baseline retrieval as simply successful or unsuccessful, we estimate the question-specific incremental evidence-retrieval benefit of hybrid retrieval using features available before the routing decision. A regularized linear model and decision threshold are selected using document-grouped cross-validation and frozen prior to held-out evaluation. On 60 previously unseen QASPER training-split articles (188 questions, 169 evidence-evaluable), the policy triggers hybrid retrieval on 46 questions (24.5\%) and obtains the same evidence Hit@10 as always-hybrid retrieval (78.70\%, versus 76.92\% for always-keep). Paired, paper-cluster bootstrap intervals do not establish a reliable utility advantage. We further compare generated answers from a 4-bit Qwen3-4B model under the three retrieval policies. Provisional answer-level assessments show no clear correctness or faithfulness improvement after partial review, despite the evidence-retrieval result. The generation assessments remain model-assisted and lack independent human validation. These results expose an important distinction between retrieving relevant evidence efficiently and improving the reliability of the generated answer. The work is presented as a reproducible empirical study, not a claim of statistically established answer-quality superiority.

cs.IR

新论文 · v1arXiv:2611.26179

RegionAgent: Two-Stage Preference Optimization for Regional Image Restoration

Weiyu Zhou, Jiacong Tang, Tao Hu, Axi Niu, Jinqiu Sun, Peng Wu, Wei Dong, Qingsen Yan

原文摘要

Images under non-uniform coupled degradations require diverse restoration capabilities for different degraded regions. Existing methods employ globally uniform operations, potentially overlooking regional differences and causing incomplete restoration or even damage to image content. Moreover, a degraded region may require successive restoration actions, and earlier actions may alter residual degradation characteristics or introduce artifacts, potentially hindering subsequent restoration. To address these challenges, we propose RegionAgent, an adaptive restoration framework that trains a Vision-Language Model (VLM) through two-stage preference learning to generate a region-specific restoration action at each iteration. Specifically, we first train the VLM to select an action suited to the current region through step-level Direct Preference Optimization (DPO), using preferences derived from immediate restoration feedback to supervise only the differing component in each action pair. To account for the effects of current actions on subsequent restoration, we then apply trajectory-level DPO, using preferences derived from complete trajectory scores to supervise the sole differing action in each trajectory pair. Furthermore, as conventional image-pair datasets do not directly provide preferences over regional restoration decisions, we construct a regional restoration preference dataset comprising 10K action pairs and 20K trajectory pairs for two-stage VLM training. Experiments across multiple datasets demonstrate strong restoration performance under both mixed and single degradations. Ablation studies further validate the effectiveness of two-stage preference learning in improving restoration quality.

cs.CV · cs.AI

新论文 · v1arXiv:2611.26159

When Foundation Models Disagree: Representational Heterogeneity for Calibrated Uncertainty in Whole-Slide Image Classification

Yekai Shen, Yuqian Wang, Zishun Liao, Rongsheng Wang, Wenting Chen, S. Kevin Zhou, Qingsong Yao

原文摘要

Pathology foundation models supply strong representations for whole-slide image classification, yet the confidence attached to their predictions remains hard to trust. Prevailing uncertainty estimators act within a single feature space and thereby overlook the uncertainty that the choice of foundation-model representation itself induces. This work introduces CALIFUSE, a calibration-oriented framework that fuses several pathology foundation models for the specific purpose of uncertainty estimation. Departing from accuracy-driven fusion, CALIFUSE reads representational heterogeneity across encoders as an explicit confidence cue. Slide-level decision consensus is coupled with chunk-level evidence agreement quantified through Jensen-Shannon divergence, so that both prediction stability and fine-grained evidence consistency inform the estimate. Foundation-model encoders stay frozen. A task-specific nnMIL classifier is still trained for each FM; CALIFUSE then estimates confidence at inference without training an extra fusion module. Evaluated on seven WSI classification tasks under several foundation-model combinations, the framework sharpens calibration, misclassification detection, and selective prediction relative to both the strongest single-encoder baseline and naive ensemble averaging, all while preserving competitive balanced accuracy.

cs.CV · q-bio.QM

新论文 · v1arXiv:2611.26145

Can World Models Predict Rice Growth? Toward Agricultural World Models

Wenkai Ji, Zeteng Li, Yinkun Guo, Jie Zhou, Liang He, Zhenong Jin

原文摘要

World models can imagine how a physical scene evolves over the next few seconds, but growers need to know how a crop will develop over weeks to months: will this rice plant have headed a month from now, and how will it look at harvest? We introduce agricultural world modeling, the task of predicting how the same plant will look at a requested horizon of days to months, from one photo of it, its cultivar, and its camera view. In preliminary analysis, even state-of-the-art image generators get this wrong: they often grow the plant too little or give it the color and form of the wrong growth stage. We argue that they do not work out the plant's developmental state, which the photo reveals only indirectly. We therefore propose AgroWM, which reasons about development before it draws growth. Its reasoning module, PhenoClock, works out the current growth stage, predicts the future one, and writes a Growth Script with numeric targets for height, plant area, and color; its generation module, the Rooted Renderer, then edits the photo to follow this script, adding new organs and colors to the photographed plant. Because pixel scores can prefer an unchanged copy of the photo, we instead check each forecast's traits and developmental timing against the plant's own later photos. On rice, 54.6% of the forecasts of AgroWM are matched to the target stage (Stage R@1), against 34.8% for GPT Image 2.5, 24.0% for Qwen Image 2.1, and 47.4% for the strongest domain-specific baseline, the same backbone fine-tuned without Growth Scripts; 9 to 20 weeks ahead, it still reaches 46.4%, against 35.7% for that baseline. On maize, a crop with a different body plan and stage scale, the same design again scores best on all four measures.

cs.CV · cs.CL

新论文 · v1arXiv:2611.26128

CryoGaussian: Heterogeneous Cryo-EM Reconstruction Made Explicit with Gaussian Splatting

Ziwen Wang, Jiajun Fan, Chaoran Cheng, Ruihan Guo, Yanru Qu, Juexiao Zhou, Ge Liu

原文摘要

Single-particle cryo-electron microscopy (cryo-EM) determines macromolecular structures from noisy particle images. However, rare, transient compositional states and subtle, continuous conformational variation are difficult to resolve. We present CryoGaussian, a Gaussian splatting method for heterogeneous cryo-EM reconstruction that fits an explicit Gaussian density representation directly to the particle images through a differentiable rasterizer rendering orthographic line integrals modulated by the contrast transfer function. The Gaussians are initialized randomly, with their number derived from the estimated spatial support of the molecular density and their minimum size bounded by the Nyquist frequency of the particle images. To capture the compositional and conformational variation across particle images, we learn particle-image and per-Gaussian latents that jointly modulate the base position, amplitude, and scale of each Gaussian. Each structural state is then reconstructed by fitting the Gaussians conditioned on its inferred latent. On CryoBench, CryoGaussian achieves state-of-the-art reconstruction accuracy for both compositional and conformational heterogeneity. On experimental data, it resolves a rare compositional state of the 50S ribosomal subunit (class C4, 1.3% of particles) with rRNA helix 68 docked in the absence of the central protuberance, and continuous conformational motion of the SF3b and helicase subcomplexes of the pre-catalytic spliceosome. We further optimize the rasterizer for additive cryo-EM projection, reducing training time by 12.8-28.0$\times$.

cs.CV

版本更新 · v2arXiv:2611.11437

How to "train" a surgeon? Benchmarking generalist agents in surgical scene understanding

Gengyuan Zhang, Xiao Han, Shijie Zhou, Abdullah Koukash, Jingpei Wu, Jindong Gu, Yuqicheng Zhu, Nassir Navab 等 9 位作者

原文摘要

Evaluating general-purpose multimodal large language models (MLLMs) for surgical scene understanding remains limited due to scarce surgical data and fragmented evaluation protocols. We address these challenges through a two-stage evaluation framework for surgical scene understanding. In Stage I, we introduce SurgKnowBench, a diagnostic benchmark that harmonizes public surgical datasets across procedures and tasks and evaluates proprietary and open-source MLLMs to map the boundary of pretrained surgical competence. SurgKnowBench reveals that current models retain partial visual priors but remain weak on relational and procedural understanding and workflow assessment. Building on this failure frontier and motivated by the scaffolded nature of surgical training, we introduce SurgAgentGym, an agentic environment where general-purpose MLLM agents can use bounded knowledge search over SurgWiki and general-purpose visual grounding for surgical tasks. SurgAgentGym evaluates whether generalist agents can improve surgical understanding at inference time through tool-mediated evidence use, without additional surgical training. Our results show that agentic inference narrows the gap mainly for perception-heavy tasks, while fine-grained localization and expert-style assessment remain persistent bottlenecks. This opens a path toward future studies of agentic surgical understanding.

cs.CV · cs.AI

新论文 · v1arXiv:2611.26105

PhysVAM: Physics-oriented Future Value Action Model for Dynamic Object Manipulation

Yuxiang Yang, Jingbo Zhang, Jiaru Zhong, Junliang Chen, Yirui Zhou, Guangming Wang, Haitao Lin, Huaiyuan Xu 等 10 位作者

原文摘要

Predicting future scene or object states does not necessarily reveal how robot-object interactions will advance or hinder a task. This challenge is particularly pronounced in dynamic robotic manipulation, where objects continue moving during perception and execution. Effective action generation therefore requires not only modeling object dynamics but also anticipating how future interactions will shape task progress. To this end, we propose \textbf{PhysVAM}, a Physics-oriented Future Value Action Model that represents anticipated interactions through their effects on future task progress. This value-based formulation provides task-directed foresight without reconstructing future visual states. Conditioned on current observations and historical object and robot motion, PhysVAM jointly learns action generation and multi-horizon future-value prediction. The value branch learns horizon-specific latent representations through future task-value prediction from successful and failed trajectories. These future-value representations are integrated into the action policy through gated cross-attention, guiding action generation toward interactions that facilitate task success. Extensive simulation and real-world experiments demonstrate superior task success, with absolute success-rate improvements of 27.0 and 27.5 percentage points over the strongest baselines in simulation and real-world tasks, respectively. Project page: https://metarobo.github.io/physvam.github.io/.

cs.RO

新论文 · v1arXiv:2611.26062

GenSPARQL: A Generative Extension of SPARQL for Incomplete Knowledge Graphs

Jingcheng Wu, Yi Wang, Hongkuan Zhou, Steffen Staab, Bo Xiong

原文摘要

Knowledge graphs on the Web are incomplete, and SPARQL answers a query only from the stored triples. Large language models (LLMs) can predict missing facts, but an LLM returns names instead of IRIs and requires one call per binding of a query variable. We present GenSPARQL, a generative extension of SPARQL 1.1 with an operator GENOP that binds values generated by an LLM to query variables during query evaluation. A similarity join maps generated names to entities of the graph, and the query planner invokes the LLM only for the bindings selected by the other graph patterns and filters. In a web workbench, attendees query two graphs built from Wikidata and inspect generated values, mapped entities and LLM calls. In our evaluation with three open-weight LLMs, the embedding similarity maps 83% of the entities named by the LLMs and yields only one incorrect match.

cs.DB · cs.AI

新论文 · v1arXiv:2611.26046

Agentic Scaling of Embodied Tasks in Simulation for Synthetic Data Collection and Policy Evaluation

Kang Wang, Xiaolei Zhou, Xiaoyu Wu, Zhendong Wang

原文摘要

Scaling embodied interaction data requires a broad collection of usable tasks, yet specifying and validating each task instance remains costly. We present AgenticTask, an agent-based framework that expands existing task collections under human intent. Its central representation links interaction requirements to object and part bindings, scene and robot configurations, initial conditions, and completion criteria. A task-generation agent reuses interaction structure to construct supported variations and revises incompatible configurations using validation feedback. A task-execution agent uses the same bindings and geometric records to select robot-supported skills and check completion against the original task criteria. On RoboCasa, the framework builds the AgenticTask collection, saving 16,450 task instances from 20,323 construction attempts at a throughput of 166.97 saved instances per elapsed hour, with 62.26% of construction attempts passing the configured physical checks. The execution agent completes approximately 38% of evaluated tasks, with successful cases spanning object placement, articulated manipulation, and sequential arrangement. Diagnostic analysis identifies improvement priorities in construction reliability, action selection, task-robot compatibility, and runtime integration. Together, these results demonstrate task-collection expansion with measured construction productivity and concrete execution evidence, providing a foundation for subsequent interaction-data collection for embodied AI.

cs.RO

新论文 · v1arXiv:2611.25965

Power Setpoint Tracking for Large-Scale EV Charging: Transformer-Constrained Charging Policy Learning with Self-Tuning Constraint Prices

Daniyal Sajedi-Hosseini, Yoshihiko Fujisawa, Shubham Singh, Lei Zhou, Katsuki Fujisawa, Sebastien Gros, Mazaher Karimi, Xun Shen

原文摘要

In power setpoint tracking (PST), an operator follows a purchased charging profile without overloading shared transformers or undercharging vehicles. PST is cast as a constrained Markov decision process that minimizes tracking error subject to overload and mean user-satisfaction constraints. Transformer-Constrained Charging Policy Learning (TC-CPL) extends soft actor-critic with proportional-integral Lagrange-multiplier updates from measured violations, a residual on the incumbent dispatcher that is warm-started from its demonstrations, and a transformer-aware encoder shared by all ports. It observes no departure times or states of charge. Simulations (five seeds, 100 paired days) compare it with the incumbent, Round-Robin. On a 600-port, 122-substation district, raw overload falls from 3.59 to 0.0017 kWh/day (overloaded seed-days from 77% to 0.4%), and absolute tracking error falls by 27%. Delivered energy rises by 16%, and satisfaction rises from 0.959 to 0.989. On a 42-kW transformer with household load, overload falls from 1.86 to 0.0014 kWh/day and satisfaction rises from 0.974 to 0.985, but absolute tracking error is 22% higher. Against hand-set fixed multipliers, self-tuning is statistically indistinguishable on the district. On the single transformer, it raises satisfaction by 0.011 at similar overload, but a short sweep found a better-serving fixed pair. The overload multipliers stay below their cap.

cs.LG · eess.SY

版本更新 · v5arXiv:2507.18061

TELEVAL: A Benchmark Designed for Spoken Language Models in Chinese Interactive Scenarios

Zehan Li, Hongjie Chen, Qing Wang, Yuxin Zhang, Jing Zhou, Hang Lv, Mengjie Du, Yaodong Song 等 12 位作者

原文摘要

Spoken Language Models (SLMs) are expected to support natural spoken interaction beyond task completion. Existing benchmarks assess a range of semantic tasks and conversational capabilities. However, high task scores do not necessarily imply reliable and appropriate spoken interaction. To address this gap, we introduce TELEVAL, a large-scale benchmark focused on Chinese spoken interaction. It evaluates responses to spoken inputs without additional task-specific prompts or predefined answer options. TELEVAL covers two complementary aspects: (1) Reliable Content Fulfillment, which measures semantic accuracy under diverse acoustic and linguistic conditions, and (2) Interactional Appropriateness, which assesses conversational naturalness and appropriate adaptation to auditory cues. Experiments reveal limitations in both aspects. Strong results on factual question-answering datasets do not consistently extend to locally relevant knowledge or challenging speech conditions, such as Chinese cultural questions and dialectal speech. Models also struggle to adapt their responses to auditory cues, even in cases where they explicitly recognize them. We further document a recurring failure pattern, termed the "Caption Trap", in which some responses describe a perceived auditory cue instead of addressing the user's conversational needs. Overall, the evaluated SLMs struggle to deliver consistently accurate and conversationally appropriate responses. TELEVAL provides a diagnostic framework for evaluating both content reliability and conversational adaptation.

cs.CL · cs.AI · cs.SD · eess.AS

版本更新 · v2arXiv:2609.37745

Optimizer-dependent training dynamics converge to the same one-third optimal data scaling

Hyunseok Lee, Mihir Basil, Yizhou Liu, Jeff Gore

原文摘要

Neural scaling, in which loss falls as a power law with training, is central to large language models, and one recent proposal is that a $1/3$ exponent emerges from learning peaked distributions. That account describes SGD, but models in practice are trained with adaptive optimizers. Here we separate two exponents the $1/3$ account does not distinguish: how fast the loss falls with training steps along a single run, and how fast the optimally tuned loss falls with dataset size $D$. We show that the first, a dynamic exponent, is optimizer-specific while the second, an optimal data exponent, converges to $1/3$ across optimizers. In an online teacher-student model we decompose the loss into norm growth (radial) and alignment toward the teacher direction (tangential), each decaying as a power law with dynamic exponents $α_{r}$ and $α_{t}$. Under SGD, both are close to $1/3$, so the data exponent is also $1/3$ across different learning rates. Under Adam the two separate: $α_{r} \simeq 0.48$ but $α_{t} \simeq 0.08$. Since the total loss is minimized when these two parts are balanced, the optimal learning rate is optimizer-dependent: $D$-independent for SGD but falls with $D$ for Adam. Yet tuned to that optimum, the loss returns to $D^{-1/3}$ for both. A stochastic-dynamics analysis explains why: the optimizers can trade decay speed between the two channels, but they all fall on a single dynamic exponent relation, $2α_{r}+ α_{t} = 1$, which fixes the optimal data exponent at $1/3$. Across seven optimizers, including Muon, the measured exponents are consistent with this relation, and the optimal-loss envelopes agree with $D^{-1/3}$ across them. The optimizer sets how fast a model learns per step; tuned optimally, it changes the prefactor but not the rate at which loss falls per sample.

cs.LG

新论文 · v1arXiv:2611.25917

LIFT: Latent Flow Matching for Probabilistic Cell Fate Dynamics with Single Cell Snapshots

Bowen Yang, Junda Ying, Yuxuan Wang, Peijie Zhou, Lei Zhang

原文摘要

Lineage tracing links cell states through clonal ancestry, but does not generally identify unique source-descendant pairings. Learning from such data therefore requires a model of conditional outcomes, rather than only the terminal population distribution. We introduce LIFT, a latent flow framework for probabilistic cell-state generation from lineage-informed couplings. Variational inference encodes alternative outcomes in a latent space, while a conditional prior enables sampling from the initial state alone. A Mean Flow decoder predicts future cell state directly, requiring one decoder evaluation per sampling, which makes it convenient to predict cell fate through large scale Monte-Carlo sampling. This construction combines a representation of one-to-many relationships with efficient sampling and an analysis of conditional prediction error. Experiments on synthetic and real datasets demonstrate LIFT's ability to recover both population distribution and cell fate probabilities.

cs.LG

版本更新 · v3arXiv:2611.06120

ReactWorld: Structuring Interaction Responses for Embodied Video Generation

Hanwei Liu, Huijia Zhang, Hanzhang Wang, Guangyu Liu, Hanbei Zhan, Linjie Hu, Bin Xiao, Xuan Zhou 等 9 位作者

原文摘要

Embodied video world models predict scene changes caused by robot actions, yet generated object responses may remain inconsistent with task intent and contact dynamics. Critical responses in embodied scenes often concentrate in local regions and specific time intervals. Inspired by chain-of-thought reasoning, we introduce ReactWorld, an embodied video generation model guided by structured interaction anticipation. In the generation backbone's feature space, an interaction response field predictor anticipates how the interaction will unfold, explicitly describing participant roles, future motion response intensity, and local motion changes. A response feedback adapter forms increments to object features from the difference between the object branch's outputs with predicted and zeroed local dynamics inputs. It also converts predicted displacements into positional biases for temporal attention. These two mechanisms guide object feature updates and information retrieval across frames, respectively. Through interaction anticipation and generative feedback, ReactWorld achieves an average score of 77.51 on RBench, outperforming PhysisForcing by 3.29 points with improvements in all nine categories. On EZS-Bench, it achieves a Domain score of 86.98 and an average score of 81.87.

cs.CV · cs.RO

新论文 · v1arXiv:2611.25866

From Sequence to Space: Explicit Spatial Belief with Vision-Language Distillation for Active Geo-Localization

Ziyang Xu, Peng Han, Hai Zhou

原文摘要

Active geo-localization (AGL) asks an agent to navigate a small aerial search grid and reach a target specified by an aerial image, a ground-level photograph, or text. Existing methods align the goal modalities well, but they keep the navigation state inside a large sequential Transformer and train with a dense distance reward that uses the hidden goal location. This paper proposes EAGLE, an Explicit spatial-belief Agent for Geo-Localization and Exploration. Offline training jointly optimizes a teacher-conditioned Swin branch and a context-free Swin student from the same randomly masked partial mosaics. The teacher branch attends to frozen full-scene context extracted by Qwen2.5-VL-7B, both branches receive masked-cell aerial-feature reconstruction and uncertainty supervision, while the student additionally distills stop-gradient feature predictions from the teacher. After distillation, Qwen, its cached context, and the teacher-attention branch are discarded. The retained student predicts cell-level aerial-feature embeddings and predictive uncertainty from partial observations alone. These predictions are combined with the modality-aligned goal embedding and a trajectory-derived visitation mask to construct the spatial belief tensor. The student is then frozen while a compact CNN actor-critic is optimized with PPO. EAGLE achieves state-of-the-art average success rates of 78.1%, 76.4%, and 76.8% on MASA, xBD zero-shot transfer, and the MM-GAG zero-shot aerial-goal split, respectively, without using a VLM or cached visual tokens at inference. Code will be made publicly available.

cs.RO

新论文 · v1arXiv:2611.25854

Learning-Based System Identification for DVL-Constrained AUV Localization

Mingxi Zhou, Emir Cem Gezer, Lin Zhao, William McConnell, Chengzhi Yuan

原文摘要

Nowadays, most AUVs utilize Doppler velocity logs (DVLs) and inertial measurement units (IMUs) to achieve satisfactory dead-reckoning results. However, the DVL bottom lock may not be available in some scenarios, such as moving over a soft bottom or traveling further away from the seafloor beyond the DVL's range. As a result, the localization system solely reliant on the IMU data will experience significant drift. The relatively high cost of DVLs also inhibits multirobot or swarm operations. In this article, we present the results of using fully connected feedforward neural networks to predict vehicle velocity (surge, sway, and heave) for AUV localization. Approximation functions for the vehicle velocities are derived based on the generalized six degree-of-freedom dynamic equation and kinematics, proving that they are suitable for feedforward neural networks with measurable inputs. The neural networks are trained using field data collected using an AUV. An ablation study was conducted to investigate the impacts of hyperparameters, and the most effective models were selected using the Akaike information criterion. The selected neural network models are tested on three new sets of mission data collected on two different days. The quantitative results show that localization using vehicle velocities predicted by neural networks yields lower averaged root-mean-square distance errors and standard deviation compared to the DVL-aided dead-reckoning method. However, the extent of this improvement was found to depend on ocean current conditions. The promising results show that lightweight fully connected feedforward neural networks offer an attractive approach for inertial-based underwater localization when DVLs or their measurements are not available.

cs.RO

版本更新 · v3arXiv:2608.22294

Semantic Role-Structured World Model for Physical Interaction Planning

Juntao Cheng, Yijun Shen, Qunchao Jin, Xiansheng Chen, Wei Liu, Rui Qian, Jingyi Peng, Yunsong Zhou 等 9 位作者

原文摘要

World models for robotic manipulation must capture how actions transform a scene in ways that are meaningful for task execution. Existing object-centric approaches preserve the transient identity of entities, while leaving the evolving task structure that gives those dynamics meaning largely implicit. We introduce SemRole, a world model that represents scene evolution through semantic roles: a task-conditioned structure explicitly encoding the functional status of scene entities, their task-relevant relations, and the current phase of execution. Conditioned on language, visual observations, and proprioception, SemRole uses this structured state to govern action generation and action-conditioned dynamics, predicting interaction events, relation satisfaction, and phase progression. At inference time, these predictions guide phase-aware action selection and local repair of invalid rollouts. We instantiate SemRole on both lightweight LeWM and pretrained Cosmos backbones, improving closed-loop success from 45.5% to 83.0% on LIBERO, 42.9% to 55.2% on RoboCasa, and 55.0% to 81.0% on real-robot Galbot transfer. Across backbones and domains, explicitly modeling task-semantic structure yields substantially stronger world-model-based manipulation.

cs.RO