AI Agent - arXivDaily 专题

2507.04396 2025-07-08 cs.LG eess.SP 57%

Inverse Reinforcement Learning using Revealed Preferences and Passive Stochastic Optimization

Vikram Krishnamurthy

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments arXiv admin note: text overlap with arXiv:2006.11674

2409.05255 2025-07-08 physics.med-ph cs.CV cs.LG 57%

Label-free evaluation of lung and heart transplant biopsies using tissue autofluorescence-based virtual staining

Yuzhu Li, Nir Pillar, Tairan Liu, Guangdong Ma, Yuxuan Qi, Kevin de Haan, Yijie Zhang, Xilin Yang, Adrian J. Correa, Guangqian Xiao, Kuang-Yu Jen, Kenneth A. Iczkowski, Yulun Wu, William Dean Wallace, Aydogan Ozcan

专题命中 Agent评测：workflow(abstract)；分类 cs.LG

Comments 25 Pages, 5 Figures

Journal ref BME Frontiers, AAAS (2025)

2303.06572 2025-07-08 cs.LG cs.CV 57%

Continual Visual Reinforcement Learning with A Life-Long World Model

Minting Pan, Wendong Zhang, Geng Chen, Xiangming Zhu, Siyu Gao, Yunbo Wang, Xiaokang Yang

机构 * MoE Key Lab of Artificial Intelligence（人工智能MOE重点实验室）； AI Institute（人工智能学院）； Shanghai Jiao Tong University（上海交通大学）

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments Accepted by ECML 2025

2507.03477 2025-07-08 cs.AI 57%

REAL: Benchmarking Abilities of Large Language Models for Housing Transactions and Services

Kexin Zhu, Yang Han

专题命中 Agent评测：agent(abstract)；分类 cs.AI

2410.04360 2025-07-08 cs.MA cs.AI 57%

GenSim: A General Social Simulation Platform with Large Language Model based Agents

Jiakai Tang, Heyang Gao, Xuchen Pan, Lei Wang, Haoran Tan, Dawei Gao, Yushuo Chen, Xu Chen, Yankai Lin, Yaliang Li, Bolin Ding, Jingren Zhou, Jun Wang, Ji-Rong Wen

机构 * Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学全球化人工智能学院）； University College London（伦敦大学学院）； Alibaba Group（阿里巴巴集团）

专题命中 Agent评测：agent(abstract)；分类 cs.AI

Comments NAACL 2025 Demo Track

2507.02365 2025-07-04 cs.LG 57%

Deep Reinforcement Learning-Based DRAM Equalizer Parameter Optimization Using Latent Representations

Muhammad Usama, Dong Eui Chang

机构 * Control Laboratory, School of Electrical Engineering, KAIST（控制实验室，电气工程学院，韩国科学技术院）

专题命中 Agent评测：agent(abstract)；分类 cs.LG

2507.01923 2025-07-04 cs.CL 57%

Decision-Oriented Text Evaluation

Yu-Shiang Huang, Chuan-Ju Wang, Chung-Chi Chen

机构 * National Institute of Advanced Industrial Science and Technology（国家先进工业科学与技术研究院）

专题命中 Agent评测：agent(abstract)；分类 cs.CL

2507.01823 2025-07-03 cs.LG cs.RO 57%

TD-MPC-Opt: Distilling Model-Based Multi-Task Reinforcement Learning Agents

Dmytro Kuzmenko, Nadiya Shvai

机构 * Department of Multimedia Systems, NaUKMA（多媒体系统系，NaUKMA）； Department of Mathematics, NaUKMA（数学系，NaUKMA）

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments Preprint of a manuscript submitted for peer review

2503.09320 2025-07-03 cs.CV cs.LG cs.RO 57%

2HandedAfforder: Learning Precise Actionable Bimanual Affordances from Human Videos

Marvin Heidinger, Snehal Jauhri, Vignesh Prasad, Georgia Chalvatzaki

机构 * Computer Science Department, Technische Universität Darmstadt（德意志联邦共和国达姆施塔特技术大学计算机科学系）

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments ICCV 2025

2507.00265 2025-07-02 cs.LG q-bio.NC 57%

Examining Reject Relations in Stimulus Equivalence Simulations

Alexis Carrillo, Asieh Abolpour Mofrad, Anis Yazidi, Moises Betancort

机构 * Dep de Ps Clín, Psbiol y Metod Universidad de la Laguna（心理临床、心理学与方法学大学拉古纳大学）； Department of Informatics University of Bergen（信息学院卑尔根大学）； Department of Computer Science Oslo Metropolitan University（计算机科学学院奥斯陆 Metropolitan 大学）

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments 18 pages, 6 figures

2502.11733 2025-06-30 cs.CL 57%

Plant in Cupboard, Orange on Rably, Inat Aphone. Benchmarking Incremental Learning of Situation and Language Model using a Text-Simulated Situated Environment

Jonathan Jordan, Sherzod Hakimov, David Schlangen

机构 * Computational Linguistics, Department of Linguistics University of Potsdam（语言学系计算语言学部门波恩大学）； German Research Center for Artificial Intelligence (DFKI), Berlin（德国人工智能研究中心（DFKI）柏林）

专题命中 Agent评测：agent(abstract)；分类 cs.CL

Comments Accepted at The 28th International Conference of Text, Speech and Dialogue (TSD2025)

2411.00119 2025-06-30 cs.MA cs.LG 57%

Soft Condorcet Optimization for Ranking of General Agents

Marc Lanctot, Kate Larson, Michael Kaisers, Quentin Berthet, Ian Gemp, Manfred Diaz, Roberto-Rafael Maura-Rivero, Yoram Bachrach, Anna Koop, Doina Precup

机构 * Google DeepMind（谷歌DeepMind）； Google DeepMind, University of Waterloo（谷歌深Mind、多伦多大学）； Mila, University of Montreal（Mila、蒙特利尔大学）； Google DeepMind, LSE（谷歌深Mind、伦敦政治经济学院）； Meta$^1$（Meta）

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Journal ref AAMAS 2025

2506.21037 2025-06-27 cs.LG cs.CV 57%

RL-Selector: Reinforcement Learning-Guided Data Selection via Redundancy Assessment

Suorong Yang, Peijia Li, Furao Shen, Jian Zhao

机构 * Nanjing University（南京大学）

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments ICCV 2025

Journal ref ICCV 2025

2410.09942 2025-06-27 cs.CL cs.IR 57%

Learning to Rank for Multiple Retrieval-Augmented Models through Iterative Utility Maximization

Alireza Salemi, Hamed Zamani

机构 * University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）

专题命中 Agent评测：agent(abstract)；分类 cs.CL

2506.19527 2025-06-25 cs.CL 57%

KnowMap: Efficient Knowledge-Driven Task Adaptation for LLMs

Kelin Fu, Kaigui Bian

机构 * School of Computer Science（计算机科学学院）

专题命中 Agent评测：agent(abstract)；分类 cs.CL

2504.14412 2025-06-24 eess.SY cs.LG cs.SY 57%

Quantum-Enhanced Reinforcement Learning for Power Grid Security Assessment

Benjamin M. Peter, Mert Korkali

机构 * Department of Electrical Engineering and Computer Science（电气工程与计算机科学系）； University of Missouri（密苏里大学）

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments 6 pages, 6 figures, 3 tables. Submitted to the 57th North American Power Symposium (NAPS) 2025

2502.03424 2025-06-24 cs.LG 57%

Prediction of the Most Fire-Sensitive Point in Building Structures with Differentiable Agents for Thermal Simulators

Yuan Xinjie, Khalid M. Mosalam

机构 * Shenzhen International Graduate School Tsinghua University（深圳国际研究生院清华大学）； Pacific Earthquake Engineering Research (PEER) Center University of California, Berkeley（太平洋地震工程研究中心加州大学伯克利分校）； University of California, Berkeley（加州大学伯克利分校）

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments This paper has been accepted by journal Computer-Aided Civil and Infrastructure Engineering

Journal ref Computer-Aided Civil and Infrastructure Engineering: Volume 40, Issue 18. 2025 July

2506.17375 2025-06-24 q-bio.NC cs.AI 57%

Challenges in Grounding Language in the Real World

Peter Lindes, Kaoutar Skiker

专题命中 Agent评测：agent(abstract)；分类 cs.AI

Comments 14 pages, 2 figures

2506.15253 2025-06-19 cs.CR cs.AI 57%

RAS-Eval: A Comprehensive Benchmark for Security Evaluation of LLM Agents in Real-World Environments

Yuchuan Fu, Xiaohan Yuan, Dongxia Wang

机构 * Zhejiang University（浙江大学）

专题命中 Agent评测：agent(abstract)；分类 cs.AI

Comments 12 pages, 8 figures

2506.15225 2025-06-19 cs.AI eess.SP 57%

Joint Computation Offloading and Resource Allocation for Uncertain Maritime MEC via Cooperation of UAVs and Vessels

Jiahao You, Ziye Jia, Chao Dong, Qihui Wu, Zhu Han

机构 * College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics（电子与信息工程学院，南京航空航天大学）； National Mobile Communications Research Laboratory, Southeast University（南京东南大学国家移动通信研究中心）； University of Houston（休斯顿大学）； Department of Computer Science and Engineering, Kyung Hee University（计算机科学与工程系，庆熙大学）

专题命中 Agent评测：agent(abstract)；分类 cs.AI

2506.14285 2025-06-18 cs.CL 57%

From What to Respond to When to Respond: Timely Response Generation for Open-domain Dialogue Agents

Seongbo Jang, Minjin Jeon, Jaehoon Lee, Seonghyeon Lee, Dongha Lee, Hwanjo Yu

专题命中 Agent评测：agent(abstract)；分类 cs.CL

Comments Work in progress

2505.11368 2025-06-18 cs.CL 57%

GuideBench: Benchmarking Domain-Oriented Guideline Following for LLM Agents

Lingxiao Diao, Xinyue Xu, Wanxuan Sun, Cheng Yang, Zhuosheng Zhang

机构 * School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机科学学院）； Zhiyuan college, Shanghai Jiao Tong University（上海交通大学智远学院）； ByteDance Inc（字节跳动公司）

专题命中 Agent评测：autonomous agent(abstract)；分类 cs.CL

Comments ACL 2025 Main Conference

1604.00644 2025-06-18 cs.NE cs.AI 57%

An electronic-game framework for evaluating coevolutionary algorithms

Karine da Silva Miras de Araújo, Fabrício Olivetti de França

机构 * Center of Mathematics, Computer e Cognition (CMCC) Federal University of ABC (UFABC) Santo André, Brazil（数学、计算机与认知中心（CMCC）巴西联邦亚比安大学（UFABC）圣安德烈）

专题命中 Agent评测：agent(abstract)；分类 cs.AI

Comments This paper is a translation of \cite{karine2015}, published in Portuguese at Brazilian Congress on Computational Intelligence, 2015

2506.13153 2025-06-17 cs.NI cs.LG 57%

Dynamic Preference Multi-Objective Reinforcement Learning for Internet Network Management

DongNyeong Heo, Daniela Noemi Rim, Heeyoul Choi

机构 * Handong Global University（韩东全球大学）

专题命中 Agent评测：agent(abstract)；分类 cs.LG

2503.17454 2025-06-17 cs.LG 57%

Collaborative Value Function Estimation Under Model Mismatch: A Federated Temporal Difference Analysis

Ali Beikmohammadi, Sarit Khirirat, Peter Richtárik, Sindri Magnússon

机构 * Department of Computer and Systems Sciences（计算机与系统科学系）； Stockholm University（斯德哥尔摩大学）； King Abdullah University of Science and Technology（国王阿卜杜勒阿齐兹科技大学）

专题命中 Agent评测：agent(abstract)；分类 cs.LG

2502.16328 2025-06-17 cs.LG 57%

Optimal Transport-Guided Safety in Temporal Difference Reinforcement Learning

Zahra Shahrooei, Ali Baheri

机构 * Department of Mechanical Engineering, Rochester Institute of Technology（机械工程系，罗切斯特理工学院）

专题命中 Agent评测：agent(abstract)；分类 cs.LG

2411.10768 2025-06-17 econ.EM cs.CE cs.LG 57%

Building Interpretable Climate Emulators for Economics

Aryan Eftekhari, Doris Folini, Aleksandra Friedl, Felix Kübler, Simon Scheidegger, Olaf Schenk

机构 * Institute of Computing, Università della Svizzera italiana（瑞士大学计算研究所）； Institute for Atmospheric and Climate Science, ETHZ（大气与气候科学研究所）； ifo Institute, Ludwig-Maximilian University of Munich（ifo研究所，慕尼黑莱布尼茨大学）； Department for Banking and Finance, University of Zürich（金融学院，苏黎世大学）； Department of Economics, University of Lausanne（经济学系，洛桑大学）； Grantham Research Institute, London School of Economics（格兰塔姆研究所，伦敦政治经济学院）

专题命中 Agent评测：agent(abstract)；分类 cs.LG

2506.11967 2025-06-16 cs.LG cs.CV 57%

Visual Pre-Training on Unlabeled Images using Reinforcement Learning

Dibya Ghosh, Sergey Levine

专题命中 Agent评测：agent(abstract)；分类 cs.LG

2506.11751 2025-06-16 stat.ME cs.CY cs.LG physics.soc-ph 57%

Bias and Identifiability in the Bounded Confidence Model

Claudio Borile, Jacopo Lenti, Valentina Ghidini, Corrado Monti, Gianmarco De Francisci Morales

机构 * CENTAI ； Sapienza University（Sapienza大学）； Euler Institute（Euler研究所）

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments 13 pages, 8 figures

2506.11065 2025-06-16 cs.CL 57%

Smotrom tvoja pa ander drogoj verden! Resurrecting Dead Pidgin with Generative Models: Russenorsk Case Study

Alexey Tikhonov, Sergei Shteiner, Anna Bykova, Ivan P. Yamshchikov

机构 * CAIRO, THWS Würzburg, Germany（THWS魏尔茨堡德国）； Berlin, Germany（柏林德国）； St. Petersburg, Russia（圣彼得堡俄罗斯）

专题命中 Agent评测：agent(abstract)；分类 cs.CL

Comments ACL Findings 2025

1. Agent评测 15866 篇

Inverse Reinforcement Learning using Revealed Preferences and Passive Stochastic Optimization

Label-free evaluation of lung and heart transplant biopsies using tissue autofluorescence-based virtual staining

Continual Visual Reinforcement Learning with A Life-Long World Model

REAL: Benchmarking Abilities of Large Language Models for Housing Transactions and Services

GenSim: A General Social Simulation Platform with Large Language Model based Agents

Deep Reinforcement Learning-Based DRAM Equalizer Parameter Optimization Using Latent Representations

Decision-Oriented Text Evaluation

TD-MPC-Opt: Distilling Model-Based Multi-Task Reinforcement Learning Agents

2HandedAfforder: Learning Precise Actionable Bimanual Affordances from Human Videos

Examining Reject Relations in Stimulus Equivalence Simulations

Plant in Cupboard, Orange on Rably, Inat Aphone. Benchmarking Incremental Learning of Situation and Language Model using a Text-Simulated Situated Environment

Soft Condorcet Optimization for Ranking of General Agents

RL-Selector: Reinforcement Learning-Guided Data Selection via Redundancy Assessment

Learning to Rank for Multiple Retrieval-Augmented Models through Iterative Utility Maximization

KnowMap: Efficient Knowledge-Driven Task Adaptation for LLMs

Quantum-Enhanced Reinforcement Learning for Power Grid Security Assessment

Prediction of the Most Fire-Sensitive Point in Building Structures with Differentiable Agents for Thermal Simulators

Challenges in Grounding Language in the Real World

RAS-Eval: A Comprehensive Benchmark for Security Evaluation of LLM Agents in Real-World Environments

Joint Computation Offloading and Resource Allocation for Uncertain Maritime MEC via Cooperation of UAVs and Vessels

From What to Respond to When to Respond: Timely Response Generation for Open-domain Dialogue Agents

GuideBench: Benchmarking Domain-Oriented Guideline Following for LLM Agents

An electronic-game framework for evaluating coevolutionary algorithms

Dynamic Preference Multi-Objective Reinforcement Learning for Internet Network Management

Collaborative Value Function Estimation Under Model Mismatch: A Federated Temporal Difference Analysis

Optimal Transport-Guided Safety in Temporal Difference Reinforcement Learning

Building Interpretable Climate Emulators for Economics

Visual Pre-Training on Unlabeled Images using Reinforcement Learning

Bias and Identifiability in the Bounded Confidence Model

Smotrom tvoja pa ander drogoj verden! Resurrecting Dead Pidgin with Generative Models: Russenorsk Case Study