跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

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
+2已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-08 10:17 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-07 11:02 — 2026-11-08 11:02（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：2026-11-08 10:17最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 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。

17,100 已收录论文14,661 AI 相关4,057 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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 17,100 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-08 10:15（北京时间）
新论文 · v1arXiv:2611.03834

Low-Rank Hierarchical Merging for Efficient Long-to-Short Reasoning

Zeqiu Yu, Xuesheng Zhang, Wenxiao Zhao, Shixiao Wang

原文摘要

Long-to-Short (L2S) model merging seeks to combine the strong reasoning capability of long chain-of-thought models with the concise style of base models, but existing methods that rely on linear interpolation and first-order activation statistics fail to capture how the loss landscape responds to parameter displacement, leading to degraded accuracy on hard tasks. We propose Low-Rank Hierarchical Merging (LHM), a training-free framework that replaces heuristic statistics with lightweight second-order curvature information. LHM consists of three components: (1) a low-rank Hessian approximation that efficiently estimates per-layer Hessian traces via Hutchinson's estimator on random inputs, eliminating the need for task-specific data; (2) a Layer Second-Order Sensitivity (LSOS) index that combines Hessian trace with task-vector norm to quantify per-layer fusion difficulty; and (3) a Dual-Constraint Coefficient Mapping (DCCM) that converts LSOS scores into layer-adaptive merge coefficients while jointly satisfying a fusion-error bound and a global length-reduction target. Experiments across six mathematical benchmarks on 1.5B and 7B models show that LHM outperforms state-of-the-art methods such as ACM-TIES and ORCA, achieving over 4\% accuracy gain and up to 93.1\% reduction in output length relative to the long-CoT model.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03832

El Agente Fármaco: A Scalable AI Scientist for Drug Discovery

Marcel Müller, Mohammad Ghazi Vakili, Yoshihiro Ogura, Ella Ashoori, Shimeng Wang, Alessandro S. Nascimento, Eddie Calleja, Yutong Zhao 等 16 位作者

原文摘要

Computational drug discovery offers a growing range of tools for proposing and evaluating molecules, but combining them and deciding what to do next still requires substantial expert effort. Here, we introduce El Agente Fármaco, an AI scientist that uses modern large language model (LLM) technology to turn discovery goals expressed in everyday language into complex, scalable computational screening workflows. The agentic harness selects scientific tools, reviews their results, and adjusts subsequent steps to the target and the user's objectives. Our approach centers on a shared scientific memory: Fármaco Atlas, which stores molecules, structures, and results together with their provenance -- a record of how they were obtained. The agent uses targeted database queries to retrieve the evidence needed for each decision. A single request can launch calculations for an entire collection of molecules, without requiring a separate LLM decision for every compound. This design limits the information the model must process as screening collections grow, while keeping the underlying results available for inspection and further analysis. The integrated tools support molecule generation, prediction of binding and molecular properties, and searches for compounds available for purchase. In a retrospective comparison with an expert-led campaign, the agent proposed chemically distinct candidates with competitive docking scores and higher calculated drug-likeness under explicitly imposed selection criteria. In a 22-task benchmark against plain tool calls and Codex, the agent achieved the highest observed mean model-judged score, with lower median cumulative token use and peak context. Fármaco provides a foundation for flexible, scalable drug discovery workflows that connect scientific reasoning with an enduring, traceable record of computational work.

cs.AI · cs.MA · q-bio.BM

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2404.15352

TransfoRhythm: A Transformer Architecture Conductive to Blood Pressure Estimation via Solo PPG Signal Capturing

Amir Arjomand, Amin Boudesh, Farnoush Bayatmakou, Kenneth B. Kent, Arash Mohammadi

原文摘要

Recent statistics indicate that approximately 1.3 billion individuals worldwide suffer from hypertension, a leading cause of premature death globally. Blood Pressure (BP) serves as a critical health indicator for accurate and timely diagnosis and/or treatment of hypertension. Traditional BP measurement methods rely on cuff-based approaches, which lack real-time, continuous, and reliable BP estimates, crucial for the timely diagnosis/treatment of hypertension. Driven by recent advancements in Artificial Intelligence (AI) and Deep Neural Networks (DNNs), there has been a surge of interest in developing data-driven and cuff-less BP estimation solutions. In this context, current literature predominantly focuses on coupling Electrocardiography (ECG) and Photoplethysmography (PPG) sensors, though this approach is constrained by reliance on multiple sensor types. An alternative, utilizing standalone PPG signals, presents challenges due to the absence of auxiliary sensors (ECG), requiring the use of morphological features while addressing motion artifacts and high-frequency noise. To address these issues, the paper introduces the TransfoRhythm framework, a Transformer-based DNN architecture built upon the recently released physiological database, MIMIC-IV. Leveraging the Multi-Head Attention (MHA) mechanism, TransfoRhythm identifies dependencies and similarities across data segments, forming a robust framework for cuff-less BP estimation solely using PPG signals. To our knowledge, this paper represents the first study to apply the MIMIC IV dataset for cuff-less BP estimation. TransfoRhythm achieves highly accurate results with a Root Mean Square Error (RMSE) of [2.21, 1.84] and a Mean Absolute Error (MAE) of [1.37, 1.06] for systolic and diastolic blood pressures, respectively.

eess.SP · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03826

Rethinking Next-Visit Diagnosis Prediction Beyond Aggregate Metrics: Retrieval--Memory Multi-Agent Adjudication

Heejoon Koo

原文摘要

Next-visit diagnosis prediction forecasts the diagnoses documented at a patient's next encounter, turning retrospective electronic health records into prospective clinical prediction. However, conventional aggregate evaluation obscures its multifaceted nature: distributionally, models must handle variable-size diagnosis sets and long-tailed labels; temporally, they must distinguish persistent, newly recorded, and recurrent diagnoses; and both vary with observed history depth. We introduce an evaluation framework along these dimensions and apply it to rule-based heuristics, LLM-based prompting, retrieval, memory, and multi-agent approaches. This reveals that repeating the last visit outperforms most LLM-based approaches overall despite predicting no new or recurrent diagnoses, and that retrieval and memory exhibit distinct profiles whose relative strengths vary across temporal transitions and backbones. Motivated by this, we propose LONGINUS, a retrieval-memory multi-agent adjudication framework combining evidence retrieved from patient records with structured memory of the patient trajectory. Using cross-view agreement as a reliability heuristic, it preserves shared predictions and adjudicates disagreements without revealing their source. Across MIMIC-III and MIMIC-IV with four LLM backbones, LONGINUS achieves the best transition-specific performance among LLM-based methods in nearly all settings while remaining competitive with them on aggregate metrics.

cs.CL · cs.AI · cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03825

A Tutorial on Shape Servoing of Deformable Objects-Part II: Advanced Concepts

Ignacio Cuiral-Zueco, Alessio Caporali, Miguel Aranda, Gianluca Palli, Gonzalo López-Nicolás, Youcef Mezouar

原文摘要

In robotics, shape control, or shape servoing, refers to the automatic manipulation of a deformable object toward a desired shape. This article is the second of a two-part tutorial on data-driven, Jacobian-based shape control, in which the deformation Jacobian, a local model of how robot motion changes the measured shape, is estimated from measurements. Part I built the shape-servoing loop and derived a local stability condition. This paper starts by using the singular value decomposition of the deformation Jacobian to identify shape changes that can be produced by small robot motions, those that require large robot motions, and those that are locally unavailable. It then analyses how the choice of shape features determines how the controller regulates the object's shape and, therefore, how much the object deforms on its way to the target. It then describes three ways in which the shape control loop can fail: loss of controllability, loss of observability, and occurrence of mechanical instabilities. It closes with shape-control extensions to time-varying targets, secondary tasks, and three-dimensional objects.

cs.RO · eess.SY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03815

AIRoA-0: Long-Horizon, Precise, Cross-Embodiment Manipulation from Handheld Data

Yueh-Hua Wu, Kei Ota, Hanlong Li, Hayata Yuasa, Jason Wang, Kengo Ikeuchi, Kensuke Chiyoma, Makoto Sugiura 等 20 位作者

原文摘要

AIRoA-0 (A-0) is a bimanual manipulation system learned from 16,151 hours of handheld demonstrations, with no robot data collected at any stage. The demonstrations are recorded with YUBI, our open-source handheld gripper, which lets people record manipulation data anywhere with no robot present. From a single instruction, A-0 sorts more than a dozen small parts into their numbered cells and changes the mop pads and brush of a robot vacuum; among other tasks, it unzips a pencil case and folds a towel. It performs these tasks using only a camera on each wrist, with no head or scene camera, at a site where none of its training data was recorded. Across the ten tasks of our evaluation, it averages a success rate of 78%, against 27% for the strongest of four other vision-language-action models post-trained on the same task demonstrations. We collect no teleoperation data and use no reinforcement learning or on-robot corrections, and the robot appears only at test time. The system learns which regions of each wrist view matter for the task, predicts the stage the task has reached, and decodes actions as a continuous stream. A-0 is embodiment-agnostic: it runs on robots that mount the YUBI gripper, such as a bimanual Franka, TX-G2, OpenArm and UR. We are releasing the dataset, to our knowledge the largest open dataset of handheld-gripper demonstrations with task and subtask instructions, together with the pre-trained weights and the post-training recipe. Videos of A-0 on every task are on the project page, https://a-0.airoa.io. Anyone can build the gripper, record a task of their own and post-train the model on it in under four hours on a single node of eight H200 GPUs.

cs.RO · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03816

Data-Driven Spectrum Access Technologies for 6G

Foad Sohrabi, Harish Viswanathan, Sivarama Venkatesan, Jinfeng Du, Aliye Özge Kaya, Navin Hathiramani, Pavan Koteshwar Srinath

原文摘要

The surge in global mobile traffic, driven by 5G adoption and emerging applications, necessitates new spectrum allocations for 6G systems. With most major swaths of spectrum below 15 GHz already allocated to other services, co-existence between cellular and incumbent services such as satellite or radar systems is critical to make such spectrum accessible for 6G. At the same time, the advent of artificial intelligence offers a new opportunity for designing more efficient spectrum sharing techniques. This paper presents four novel data-driven spectrum access techniques to enable efficient use of spectrum for the 6G era: 1) co-existence technique for efficient protection of fixed incumbent receivers within an established protection area; 2) data-driven approach for protecting satellite receivers via control of radiated power above the horizon; 3) spectrum sensing-based fast-time-scale physical resource block blanking; and 4) base station-based spectrum occupancy detection to enable fast-time-scale spectrum sharing with satellite and non-terrestrial network incumbents. These techniques leverage artificial intelligence and extreme multiple-input multiple-output capabilities to enable efficient spectrum co-existence/sharing while maintaining cellular network performance.

eess.SP · cs.IT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03806

BEND 2.0: Benchmarking the Capabilities Needed to Design DNA

Andreas Bjerregaard, Rachael DeVries, Dionysia Danai Brilli, Panagiotis Antoniadis, Yan Li, Anders Krogh, Wouter Boomsma, Ole Winther 等 9 位作者

原文摘要

Genomic foundation models are increasingly used to propose DNA sequences and edits. But successful design requires capabilities that current benchmarks do not measure. Here we introduce BEND 2.0 (BENchmark for DNA language models), which tests how well models predict the effects of DNA changes and whether these predictions can guide sequence design. Across eight tasks built on five experimental datasets, we find that model choice and how representations are accessed both affect performance. Linear readouts fitted to frozen representations can match or exceed models' native outputs, and functional post-training substantially improves the models' capabilities. Linear readouts transfer well across experimental assays and genes, suggesting that models capture functional patterns beyond the data used to fit individual predictors. At the same time, strong prediction of average effects can conceal weaker prediction of context-specific effects, and accurate prediction of combined mutation effects does not imply accurate prediction of their interactions. In design tasks, model predictions can reduce the number of candidates needed to find a desired response, but still leave substantial room for better design choices, particularly for context-specific and multi-cell objectives. Our benchmark reveals that genomic models now display signs of general utility but have yet to saturate on performance in even simple tasks.

q-bio.GN · cs.LG · q-bio.QM

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03786

3D dark matter map of the JWST COSMOS-Web field using diffusion-based generative priors

Diana Scognamiglio, Brandon Zhao, Katherine L. Bouman, Olivier Doré, Caitlin M. Casey, Maximilien Franco, Ghassem Gozaliasl, David Harvey 等 20 位作者

原文摘要

Mapping the three-dimensional distribution of dark matter is key to tracing the growth of cosmic structure. Two-dimensional weak lensing mass maps recover its projected distribution, but they blend structures at different distances along the line of sight. We reconstruct the three-dimensional matter distribution in the 0.54 deg$^2$ COSMOS-Web field using deep James Webb Space Telescope imaging, with an effective source density of 121 galaxies arcmin$^{-2}$ We combine a physical weak lensing forward model with a diffusion-based Bayesian generative prior learned from cosmological simulations, yielding a posterior distribution of the matter field across 20 lens planes to $z \simeq 2$, doubling the redshift reach of previous Hubble Space Telescope-based 3D reconstructions and approaching cosmic noon, an epoch of rapid galaxy growth. The reconstruction separates structures that overlap in projection and recovers non-Gaussian matter structure across a range of spatial scales, including over-densities associated with independently identified galaxy clusters that were not detected in earlier weak lensing maps. Posterior sampling quantifies the range of three-dimensional matter distributions allowed by the data, enabling a probabilistic visualization of the cosmic web while propagating uncertainties in its inferred structure. Null and simulation-based tests show that the recovered structures are supported by the lensing signal and are consistent with expectations from the fiducial $Λ$CDM cosmology. These results extend three-dimensional weak lensing mapping into the high-redshift, non-Gaussian regime and establish a route towards probabilistic mapping of the evolving cosmic web with current wide-field lensing surveys.

astro-ph.CO · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03647

Pixel-UMI: Learning Environment-Aware Whole-Body Manipulation from Sensorized Human Demonstrations

Jason Jingzhou Liu, Tony Tao, Deepak Pathak, Ruslan Salakhutdinov

原文摘要

Sensorized human demonstrations offer scalable data for mobile manipulation, but embodiment differences complicate policy learning. We present Pixel-UMI, a pipeline for learning environment-aware whole-body policies from human data. We first introduce Environment-Aware Retargeting (EAR), which combines reconstructed scene geometry with demonstrated head and gripper trajectories to determine robot posture and generate collision-aware joint and base targets. Delay-calibrated action assignment converts these trajectories into actions. However, kinematic differences can leave residual pose errors, creating viewpoint mismatches between human demonstrations and robot observations. We therefore introduce Retargeting-Error-Aware Masking (REAM), which uses these errors during training to reduce reliance on mismatched views at deployment. Finally, because estimated actions cannot fully capture contact-rich interactions, we collect on-policy human corrections through DAgger to improve performance. We evaluate Pixel-UMI on five challenging tasks spanning articulated-object manipulation, deformable-object handling, constrained-space reaching, whole-body collision avoidance, and contact-rich bimanual coordination, achieving 87.0% average task progress. Video results are available at https://pixel-robot.com/pixel-umi

cs.RO · cs.AI · cs.CV · cs.LG · eess.SY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03648

Pixel: A Co-Designed Full-Stack Robot System for Learning General-Purpose Mobile Manipulation

Tony Tao, Jason Jingzhou Liu, Ruslan Salakhutdinov, Deepak Pathak

原文摘要

General-purpose mobile manipulation requires a combination of capable robot hardware, scalable demonstration collection, expressive whole-body control, and effective policy learning. Yet these components are often developed independently, creating mismatches that limit the capabilities of the complete system. We present Pixel, a co-designed full-stack system for learning general-purpose mobile manipulation. Pixel combines a low-cost wheeled humanoid with human-aligned kinematics and compliant grippers, multiple teleoperation and robot-free human data-collection interfaces, a unified whole-body controller, and a common policy learning pipeline across human and robot demonstrations. A hierarchical learning stack further enables language-conditioned visuomotor control and long-horizon task execution. We evaluate the system across hardware, data collection, and policy learning, and demonstrate mobile-manipulation behaviors requiring dexterity, active perception, navigation, and whole-body coordination. We hope that Pixel provides an integrated and extensible foundation for studying how robot hardware, data, control, and learning can be designed together for robot learning. More results at https://pixel-robot.com/pixel

cs.RO · cs.AI · cs.CV · cs.LG · eess.SY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03646

EgoActionBench: Benchmarking Dense Action Captioning for Egocentric Human Videos

Yujiao Shen, Jiahe Song, Haitian Li, Jingkang Yang, Ziwei Liu

原文摘要

Learning from human data offers a scalable path toward embodied intelligence, yet it requires models to accurately understand fine-grained human actions from egocentric observations. However, existing benchmarks remain limited in action atomicity, temporal precision, and hand-action association. We introduce EgoActionBench, a benchmark that represents continuous human manipulation as temporally localized atomic actions associated with the left hand, right hand, or both hands. EgoActionBench contains 1,407 episodes with 41,132 human-refined action annotations. To evaluate such dense predictions, we propose an evaluation protocol that retrieves temporally eligible candidates, selects a prediction by content agreement, and scores semantic fidelity and temporal overlap alongside action precision and recall, jointly capturing what happens, when it happens, and which hand performs it. We benchmark 20 baseline models and systems on EgoActionBench and further adapt two backbones, Qwen3-VL-4B and LLaVA-OneVision-2-8B, through supervised fine-tuning followed by reinforcement learning on automatically annotated training episodes. EgoAction improves EgoActionScore by 15.9 and 23.2 points on the two backbones, and both adapted models outperform all open-source baselines. Our experiments reveal substantial limitations of current models in action atomicity, temporal precision, and hand-action association, highlighting the gap between general video understanding and the action understanding required for embodied intelligence.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v6arXiv:2603.19233

Not All Features Are Created Equal: A Mechanistic Study of Vision-Language-Action Models

Bryce Grant, Xijia Zhao, Peng Wang

原文摘要

A fine-tuned Vision-Language-Action (VLA) policy can easily place the alphabet soup in the basket on command, just as it saw during fine-tuning. However, if the basket is shifted five centimeters to the left, it drops the soup off the table. We developed an interpretability pipeline to investigate what such a policy is computing. Injecting task A's activations into the action expert while the policy looks at task B's scene makes $π_{0.5}$ execute task A's motor trajectory in 99.6\% of episodes ($n{=}1{,}968$). The injected program is bound to absolute workspace coordinates and ignores the visible scene, which provides a mechanistic account of the perturbation brittleness that concurrent benchmarks report. The binding holds on a physical UR10e: directed replay redirects the commanded task in 26/26 rollouts in one direction and 18/26 in the other, with no-injection and random-direction controls at the floor, and once the source object is moved 10-15 cm the arm grasps and releases at the recorded coordinates in 50/50 trials, picking up the wrong block when one sits there and closing on empty air when none does. Applying the same interventions to five VLAs on LIBERO, MetaWorld, SimplerEnv, and ALOHA over $420{,}000+$ rollouts yields three further findings: every architecture encodes the instruction, and four of the five weight it below vision whenever the scene alone identifies the goal; under the standard replacement write-back the SAE pooling that preserves behavior is architecture-specific ($π_{0.5}$ per-token, SmolVLA indifferent), and goal selection and motor generation separate into VLM and expert pathways wherever the two are distinguishable. We release \textbf{Action Atlas} (https://action-atlas.com), an interactive platform covering all 520+ trained SAEs, 79 identified concepts, and the scored UR10e rollouts. Code: https://cwru-aism.github.io/vla-interp-page/

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03641

From Natural Language to Exact Cover: A Neuro-Symbolic Approach to Zebra Puzzles

Paulius Skaisgiris, Thomas Pammer, Veronika Semmelrock, Mykyta Ielanskyi, Maximilian Heisinger, Erich Kobler

原文摘要

Chain-of-Thought (CoT) generation has substantially improved the performance of Large Language Models (LLMs) on complex reasoning tasks, including code generation, data analysis, and exam-style question answering. Despite these advances, purely neural LLMs continue to struggle with elementary logical reasoning problems and lack the determinism, soundness, and reliability characteristic of symbolic reasoning systems. Conversely, classical symbolic methods such as SAT solving and exact cover guarantee correctness and completeness, but require problems to be expressed in highly specialized formal encodings, limiting their applicability to natural language inputs. In this work, we present a synergistic neuro-symbolic framework that bridges this gap by combining neural semantic parsing with deterministic exact cover reasoning. Given a Zebra-style logic puzzle in natural language, an LLM translates entities and constraints into structured tool calls that construct an exact cover instance. A symbolic solver then computes the solution and provides feedback to iteratively refine invalid, under- or overconstrained encodings, exploiting the uniqueness property of Zebra puzzles. We conduct a comprehensive empirical evaluation across multiple parameter scales, post-training paradigms, and LLM families. The results demonstrate that our hybrid approach consistently outperforms strong plain neural baselines, including CoT prompting, as well as recent neuro-symbolic methods.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03779

Robot-Matched Soft Fingers for UMI Data Collection: Lessons from 100 Hours of Pick and Place

Kobi Kelemen, Tomasz Niedziałkowski, Marcin Paszczak, Victoriano Montesinos

原文摘要

Training robot policies for multi-task pick and place requires demonstrations on many objects, which handheld Universal Manipulation Interfaces (UMIs) can collect quickly and cheaply. However, existing UMIs depend on external base stations, use rigid fingers that give no signal about contact forces, or use parallel-jaw fingers that limit grip strength. We present a battery-powered handheld interface, built on YUBI, whose soft, angled fingers wrap around objects, deform visibly under load as a visual proxy for force, and match the grippers of the robot. With it, we collect a 99.7-hour dataset over 53 objects, train $π_{0.5}$ policies on 49 of them, and hold out the other 4 as unseen objects. We find that a top camera raises success by 13 points even when only about half of the data includes it, and that mid-training on our multi-task data raises success after fine-tuning on unseen objects from 35% to 57%. Finger design, dataset, and data processing code: https://lute-corp.github.io/soft-yubi-site/

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03639

Quantum channel tomography: optimal bounds in the near-boundary regime

Kean Chen, Aadil Oufkir

原文摘要

Quantum channel tomography (also known as quantum process tomography) is a fundamental task in quantum information and quantum computing, aiming to learn the full description of an unknown quantum channel from black-box queries. For channels with input dimension $d_1$, output dimension $d_2$, and Kraus rank at most $r$, [CGO+26] identifies the dilation rate $τ=rd_2/d_1\geq 1$ as a key parameter governing a Heisenberg-to-classical transition in query complexity. While the optimal bounds in the boundary regime ($τ=1$) and the away-from-boundary regime ($τ\geq 1+Ω(1)$) are now known, the precise behavior in the near-boundary regime ($1<τ<1+o(1)$) has remained unresolved. In this paper, we close this gap, thereby fully settling the query complexity of quantum channel tomography. Specifically, we show that the query complexity is - $Ω(rd_1d_2/\varepsilon^2)$ for diamond norm error $\varepsilon$, matching the upper bound by [MB26, CGO+26], - $Θ(d_1^2/\varepsilon+\min\{(τ-1)d_1^2,(τ-1)^2d_1^2d_2^2\}/\varepsilon^2)$ for Choi trace norm error $\varepsilon$. Our results reveal two qualitatively different forms of the Heisenberg-to-classical transition. For diamond norm tomography, the Heisenberg scaling disappears suddenly as soon as $τ$ leaves the boundary regime. In contrast, Choi trace norm tomography exhibits a gradual transition from Heisenberg to classical scaling as $τ$ moves from the boundary regime to the away-from-boundary regime.

quant-ph · cs.IT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03636

Get Permanent Results Faster by Counting Stars

Radu Curticapean

原文摘要

We show that $n \times n$ permanents can be computed with $O^*{(2-\varepsilon)^n}$ arithmetic operations over every commutative ring, for $\varepsilon = 10^{-40}$. This solves a problem stated in Knuth's The Art of Computer Programming. Our algorithm implements the classical Binet--Minc identity with dynamic programming and careful bookkeeping. It also gives algebraic branching programs of size $O^*{(2-\varepsilon)^n}$.

cs.DS · cs.CC · math.CO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03634

WebHarbor: Docking Real Websites for Evolving GUI Agent Environments

Zhaoyang Wang, Qianhui Wu, Boyu Gou, Demi Wang, Jiacheng Zhang, Peichun Hua, Qize Li, Shi Qiu 等 57 位作者

原文摘要

GUI web agents require realistic and interactive environments that remain stable during both evaluation and training. Live website evaluation suffers from changing content, access restrictions, and limited coverage of authenticated workflows, while existing synthetic environments for training often lack functional depth and visual fidelity. We propose WebHarbor, a suite of 153 executable and dockerized website environments that faithfully reconstruct the visual interfaces, content, and functional workflows of real-world web services under deterministic control. We build WebHarbor through task-driven human-agent collaboration, where environments evolve as new tasks expand their functional scope, coding agents implement the required changes, and human contributors audit visual fidelity, functional correctness, and task validity. The resulting suite comprises 3,518 tasks spanning multi-step and post-authentication workflows, where existing works often fail to cover. Beyond reliable evaluation, WebHarbor provides high-fidelity synthetic web environments for cost-efficient reinforcement learning (RL). We demonstrate that a Qwen 4B-level GUI agent trained with RL in WebHarbor generalizes to unseen tasks and performs competitively with leading open-source GUI web agents across four benchmarks. The code and data are publicly available at https://github.com/aiming-lab/WebHarbor.

cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.16491

Drafting Agents, Not Just Tokens: Speculative Recursive Self-Improvement for Agentic Systems

Xin Xu, Ke Cheng, Hao Wang, Yangru Huang, Yanghao Xiao, Zhichao Chen, Zhisheng Zhong, Xun Liu 等 14 位作者

原文摘要

Improving an agent through successive revisions requires balancing exploration and evaluation under a limited budget. A narrow search can miss useful sequences of edits, while fully evaluating every intermediate version often exhausts the budget before those sequences yield a verified improvement. Inspired by the draft--verify principle of speculative decoding, we propose Speculative Recursive Self-Improvement (SpecRSI), a two-level framework coupling inner-loop agent search with outer-loop improver learning. SpecRSI drafts successors before their predecessors are fully evaluated, while adopting only fully evaluated, admissible versions. In the inner loop, Verification-Aware Tree Search (VATS) allocates the budget between further edits and outstanding checks using the predicted verified return of a continuation. In the outer loop, Group Verification Optimization (GVO) updates the improver from completed searches while keeping the real evaluator fixed. We evaluate SpecRSI on scientific optimization (including active queue management (AQM) for network infrastructure), coding, and general agent-system benchmarks. Under matched evaluation-call budgets, SpecRSI improves scientific terminal gain over Janus by 60.0%--96.3% and area under the budget curve by 32.1%--91.6%, while achieving higher means across all 50 scientific backbone--task pairs and outperforming MetaRSI-v1 by 1.30--2.70 percentage points (pp) in system score across twenty backbones. On instance-level comparisons, it further improves PyBaMM terminal gain by 142.6% and SWE-Pro success by 6.0 pp at 7.0% and 9.2% lower token cost, respectively. These results demonstrate the efficacy of the proposed approach.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.11435

Agent Skill Evaluation and Evolution: Frameworks and Benchmarks

Kexin Ding, Yang Zhou, Can Jin, Feng Tong, Mu Zhou, Dimitris N. Metaxas

原文摘要

The growth of agent skills has transformed how agentic systems are built, evaluated, and deployed. As skill libraries continue to scale, rigorous evaluation becomes critical to ensuring their utility, quality, and safety in real-world applications. Consequently, the field is undergoing an emerging paradigm shift from isolated skill creation to automated, evaluation-driven skill evolution. In this survey, we systematically examine the landscape of skill evolution and evaluation beyond foundational skill creation. We categorize evolution into four distinct paradigms, spanning execution feedback, trajectory distillation, compression, and reinforcement learning, showing how each element contributes to improving skill utility and reliability. We also provide an analysis of six skill-centric benchmark categories, identifying structural gaps in benchmark coverage, trade-offs, and metric richness to advance skill research. Finally, we identify open directions for building skill ecosystems that are generalizable, efficient, and verifiably safe. The project URL is https://github.com/Cassie07/AgentSkill_Survey

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03631

Supporting Viewpoint Coordination for Compliance by Design with an Artifact Model for Regulatory Requirements Engineering

Oleksandr Kosenkov, Davide Fucci, Michael Unterkalmsteiner, Daniel Mendez

原文摘要

Regulatory compliance has become an essential software requirement Legal demands for compliance by design CbD call for requirements engineering RE approaches that derive requirements and support compliance implementation in subsequent software engineering SE processes such as software design The complexity of the legal knowledge demanded in regulatory RE makes it important to involve legal experts and ensure the relevant specifications are valid and usable for them Regulatory requirements must support compliance implementation in software design However there is a lack of approaches bridging legal and SE viewpoints and interaction challenges between the two persist To address engineeringlegal coordination in specification of regulatory requirements we propose the Artifact Model for Regulatory Requirements Engineering AM4RRE operationalized through templates AM4RRE was positively evaluated by most of the 37 practitioners for coordination in regulatory RE and for supporting requirements quality Results from a quasiexperiment with 34 of them in 10 groups indicated that templateguided coordination was associated with on average shorter total specification time when executed first and higher requirements quality in most groups in which it varied Existing RE research and practice provide little attention and support for viewpoint coordination in regulatory RE for CbD Artifactoriented approaches such as AM4RRE have the potential to guide coordination in RE for better RE results and contribute to concretizing the role and contribution of RE to CbD

cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2607.23811

Memory Efficient Audio Synthesis with Decoupled Temporal Depth Diffusion Transformers

Dongseong Hwang, Prasanth Yadla, Kaan Elgin, Shifas Padinjaru Veettil, Sivanand Achanta, Dipjyoti Paul, Ramya Rasipuram, Tyler Johnson 等 11 位作者

原文摘要

Siri Expressive Voices synthesize rich, configurable speech in real time and entirely on device, powered by AFM 3 Core Advanced, Apple's most powerful on-device foundation model. This work presents the memory-efficient audio synthesis architecture behind that capability: a detokenizer that converts the semantic audio tokens emitted by the foundation model into high-fidelity audio within the tight compute and memory budget of the Scalable Matrix Extension (SME). We convert semantic audio tokens to a residual vector quantization (RVQ) representation with a three-component design, a streaming encoder, a temporal decoder, and a depth decoder, that systematically decouples temporal and depth processing. A single reusable depth decoder with Diffusion Transformer (DiT)-style stage conditioning generates all RVQ levels autoregressively, replacing the dedicated per-level decoders of prior multi-decoder architectures, while causal sliding window attention with fixed-window key-value caching yields constant memory complexity independent of sequence length. Deployed on the AMX, the detokenizer sustains roughly 10 ms per generation step, about 16x faster than real time, with a peak runtime memory of only 21 MB and 329 MB of on-device assets, enabling continuous streaming synthesis of 20-320 seconds of audio. This constant, small footprint replaces the linear and quadratic memory scaling of conventional transformer- and GAN-based approaches. Ablation studies validate the key architectural components, and audio quality assessment confirms that the architecture maintains synthesis fidelity while achieving efficiency gains over existing methods. Operating at a 1-billion-parameter activation size within AFM 3 Core Advanced, it improves Mean Opinion Score by +0.28 overall (4.15 vs. 3.87) and by +0.42 on conversational speech (4.24 vs. 3.82) over the prior on-device text-to-speech system.

cs.SD · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03627

Not All Reasoning Generalizes: A Case Study on Learning Generalizable Reasoning Strategies in RLVR

Ziqi Pang, Yu-Xiong Wang

原文摘要

Reinforcement learning with verifiable rewards (RLVR) can enable generalizable improvement for large language model (LLM) reasoning. This paper studies how to incentivize such generalization via reasoning strategies. We study this question with a controllable equation-solving framework: finding multiple inputs x for equations f(x)=y, where f is a non-bijective string function. This setting makes reasoning strategies observable while supporting a clear definition of easy-to-hard out-of-distribution (OOD) shifts, e.g., more solutions, longer y, etc. We uncover a subtle RLVR failure: it teaches the model to solve in-distribution tasks with high accuracy and structured step-by-step derivation, yet under OOD shifts, the same model abandons derivation and collapses to ineffective brute-force enumeration, causing sharp accuracy drops. This observation reveals the deeper challenges of RLVR generalization as it is neither incapable base model nor reward hacking, since the model succeeds in-distribution with the correct reasoning strategy. The key to mitigating this failure is an indirect intervention that surprisingly helps: co-training with bijective inversion tasks. Although these bijective tasks are actually not uniformly harder and even further from the non-bijective OOD evaluation, they make derivation more certain and substantially restore the correct strategy and accuracy under OOD shifts. This effect further motivates our theoretical analysis: outcome-only RLVR can shape reasoning processes through implicitly crediting the effective reasoning strategies more, even without process supervision. To conclude, our analysis framework and findings systematically reveal the crucial role and incentivization of reasoning strategies in RLVR generalization under OOD shifts. Code is available at https://github.com/ziqipang/rl_meta_thinking.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03626

Isekai3D SDG: A Platform for Diverse Synthetic Gameplay Visual Data

Rafal Karp, Gene Liu, Shih-Hsin Li, Eric Courtemanche, Shengze Wang, Josef Spjut, David Pankratz, Mischa Kolbe 等 13 位作者

原文摘要

We present Isekai3D Synthetic Data Generation (SDG), a platform for simulating and capturing synthetic 3D gameplay for research in vision and world models, neural graphics, gameplay agents, and other applications. The platform combines reusable environment and character assets with Unreal Engine plugins in a two-stage workflow. First, world simulation generates gameplay while recording the world state, character movements, actions, and camera tracks needed for replay. Second, the recorded simulation is replayed to capture selected outputs, such as rendered video, images, and depth maps, at a specified resolution and frame rate under selected rendering and camera configurations. Separating simulation from capture allows the same recorded gameplay to produce multiple output variants without repeating the original simulation. Visual outputs are accompanied by frame-aligned camera, character, and action metadata. The platform uploads generated data directly in a training-friendly format, reducing intermediate storage, preparation time, and manual processing. This report describes the design of our overall system, including the platform's assets, plugins, and their functionality, explaining how they work together to generate diverse synthetic gameplay data.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2606.30613

Sequential Planning via Anchored Robotic Keypoints

Bryce Grant, Aryeh Rothenberg, Logan Senning, Zonghe Chua, Zach Patterson, Peng Wang

原文摘要

Changes to what a robot can see do not mean that there is a change in the problem it is trying to solve, and many language-conditioned manipulation systems struggle with this distinction. When something in a scene moves, the robot might need to execute its actions in different places, but its manipulation plan can stay the same. We propose Sequential Planning via Anchored Robotic Keypoints (SPARK), which describes a task as a symbolic behavior tree that we anchor to the current 3D observations when each action is called. By verifying the plan at runtime we can recover from failures locally and anchor the objects to the scene again. We ask for a new plan only if this fails. We isolate this concept by taking a fixed plan and moving objects in the scene while executing. When displacing objects by $10$\,cm we were still able to complete $66.7\%$ of trials with scene-diff verification and layered recovery, and we did not have to change the plan. Without practicing on the tasks being tested or using ground-truth object poses from the simulator during rollouts, we test our full system (with one open-weight 27B planner with 4-bit weights) on LIBERO-PRO. Under this protocol SPARK achieves a mean success of $75.1\%$ across the 6 position and task settings and $69.7\%$ on the held-out language and object settings. We also achieve a $68\%$ success rate across 11 physical task-embodiment settings on 3 different robots. Our work demonstrates that for an important class of failures, the robot does not need to ask for a new plan for its task. It can be enough to update the system's view of the world. Code and videos can be found at https://cwru-aism.github.io/spark-page/

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03622

D&A: Decoupling Description and Assessment Enables VLMs as Zero-Shot Robotic Reward Models

Marius Memmel, Shawn Yin, Urvi Rutia, Angad Wadhwa, Eldon Li, Gavin Angeloff, Ankit Goyal, Jesse Zhang 等 12 位作者

原文摘要

Vision-Language Models (VLMs) hold promise for zero-shot video task-progress estimation in robot learning, yet existing frameworks frequently suffer from confirmation bias, hallucinating progress in failed executions due to implicit success assumptions or relative temporal ranking designs. Naive prompting of frontier models collapses into a binary success detector that fails to capture nuanced, non-linear progress and failures. While post-training approaches can mitigate this through explicit training, they demand expensive real-world robotics data and require computationally intensive post-training for every individual base model. To resolve these limitations, we introduce D&A (Describe & Assess): our approach decouples progress estimation into an objective, task-grounded textual description of scene dynamics followed by an assessment phase using explicit rubrics. By compelling the VLM to synthesize an explicit, text-based definition of absolute success before scoring, the framework anchors evaluations to an external, global criterion rather than the video's internal timeline. Empirical results demonstrate that our method calibrates zero-shot estimates and mitigates confirmation bias, providing fine-grained, partial progress metrics that accurately penalize failed executions while correctly interpolating successful runs. Being purely prompt-based, D&A generalizes across tasks, embodiments, and benchmarks---matching or surpassing post-trained reward models---and its reward estimates enable efficient downstream reinforcement learning.

cs.RO · cs.AI · cs.CL · cs.LG · eess.SY

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.00446

CRAD: Class-wise Reliability-Aware Distillation for Decentralized Heterogeneous Federated Learning

Baraa Bilbeisi, Mengchen Fan, Baocheng Geng, Qing Tian

原文摘要

Conventional federated learning (FL) relies on parameter averaging, which forces clients to be doubly homogeneous: it demands an identical architecture and degrades under non-IID data. Real-world deployments usually break both assumptions. We sidestep both by building a decentralized knowledge distillation framework in which each client evaluates its peers' model snapshots on its own local data and distills from the resulting soft predictions. Because knowledge is transferred through the shared class posterior, clients are free to run different architectures; and because every teacher is evaluated on the student's own device, raw data never leaves the client, with no central server or public dataset required. Within this setting, we identify and address an under-examined problem: how to combine the peer teacher predictions. Existing methods, like uniform averaging, ignore how knowledge reliability varies across teachers and classes. We propose Class-wise Reliability-Aware Distillation (CRAD), which, per class, first discards teachers that disagree with the peer consensus and then takes a weighted average of the rest, weighting each teacher by its per-class reliability (precision, or inverse variance). Since the variance of an accuracy from $n$ samples scales as $1/n$, support enters automatically: among the teachers that survive filtering, a teacher is trusted for a class to the degree that it is both accurate and well-evidenced for it. On CIFAR-10, CIFAR-100, and PathMNIST, across heterogeneous architectures under severe non-IID skew, CRAD consistently outperforms competing methods in global accuracy. Our code is publicly available at https://github.com/bbilbeis/CRAD.

cs.LG · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03620

Adjacency Labeling Schemes of Size $\log n+O(\log\log^* n)$ for Graphs of Bounded Treewidth

Noy Rotbart

原文摘要

Gavoille and Labourel (ESA 2007) gave an adjacency labeling scheme of size $\log n+O(k\log\log n)$ for graphs of treewidth at most $k$, and asked whether $\log n+O(k)$ bits suffice. We give a labeling scheme of size $\log n+O(\log\log^* n)$ for every fixed $k$, the first improvement of the second-order term for any $k\ge 2$. Equivalently, there is an induced-universal graph with $n(\log^* n)^{O_k(1)}$ vertices for this family. We work with laminar families of intervals, in which a vertex finds each earlier neighbor as the owner of an interval of a given nesting depth around it. As long as every subtree occupies consecutive positions, the nesting depth must be logarithmic, and $\log\log n$ bits per neighbor follow. We give up contiguity. Heavy subtrees are moved out, which brings the depth down to $O(\log^* n)$; the intervals broken by the moves are repaired with $2^{O(k^3)}$ additional intervals per vertex; and the bits needed to find these intervals are paid for by the moved subtrees.

cs.DS · cs.DM

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03618

Strategist: Evolving Reasoning with Agents

Taiming Lu, Qi Xu, Zhigang Hua, Zhuang Liu

原文摘要

A model is only half of an AI agent system. The other half is the inference strategy: the reasoning procedure that turns model calls into a response. Today that second half is written by hand, and the experience of building one strategy never carries to the next. We introduce Strategist, a meta-agent that evolves inference strategies across tasks. Each strategy is written as a blueprint,executable code that other strategies can reuse, and together the blueprints form a library. Given a task and a small development set, Strategist retrieves related blueprints, writes candidate strategies, tests them on real samples, and revises them from the results. Every candidate then enters the library, so later tasks build on earlier discoveries. On 30 benchmarks, Strategist beats the strongest baseline on 24 and matches its average accuracy (74.7% vs.74.0%) at 39% lower inference cost. Its strategies also transfer to unseen tasks and other models without further search. The part of an AI system that is not improved on its own now does.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.21609

HierFlow: Hierarchical Coupled Dual-Space Search for Automatic Agentic Workflow Generation

Dong Li, Yanchi Liu, Xujiang Zhao, Wei Cheng, Zhengzhang Chen, Xintao Wu, Zhong Chen, Haifeng Chen 等 9 位作者

原文摘要

Although structured workflows empower Large Language Models (LLMs) to tackle complex problems, automating their creation is severely hindered by a vast combinatorial search space, frequently resulting in inflexible and resource-heavy offline training dependencies. To address this, we conceptualize workflow generation as an intertwined topology-and-execution search paradigm, where the broader topological layer dictates subtask boundaries and lower-level execution outcomes actively reshape the topology itself. Building on this foundation, we introduce HierFlow, a training-free, test-time hierarchical search architecture that automates agentic workflow design by merging feedback-guided topology adjustments with a fast, MCTS-inspired tree search for sub-workflow optimization. HierFlow maximizes efficiency through an intelligent gating module that selectively triggers execution-level searches based on contextual necessity, a mechanism we further support with an in-depth analysis detailing how varying degrees of cross-task coupling impact the effectiveness of hierarchical splitting. Comprehensive testing across question answering, mathematical reasoning, and code generation benchmarks confirms that HierFlow consistently outperforms strong baselines, delivering an optimal balance of high-quality results and computational efficiency without any additional training overhead.

cs.AI

查看论文
arXiv ↗PDF ↗