AI Agent - arXivDaily 专题

2505.10522 2025-05-16 cs.RO cs.AI cs.LG 62%

Knowledge capture, adaptation and composition (KCAC): A framework for cross-task curriculum learning in robotic manipulation

Xinrui Wang, Yan Jin

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

2503.04830 2025-05-14 cs.CL cs.AI 62%

Cite Before You Speak: Enhancing Context-Response Grounding in E-commerce Conversational LLM-Agents

Jingying Zeng, Hui Liu, Zhenwei Dai, Xianfeng Tang, Chen Luo, Samarth Varshney, Zhen Li, Qi He

机构 * Amazon（亚马逊）

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

2411.15100 2025-05-13 cs.CL cs.AI cs.PL 62%

XGrammar: Flexible and Efficient Structured Generation Engine for Large Language Models

Yixin Dong, Charlie F. Ruan, Yaxing Cai, Ruihang Lai, Ziyi Xu, Yilong Zhao, Tianqi Chen

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

Comments MLSys '25

2505.05863 2025-05-12 q-bio.PE cs.AI cs.CL 62%

Evolutionary ecology of words

Reiji Suzuki, Takaya Arita

机构 * Graduate School of Informatics（信息学研究生院）； Nagoya University（名古屋大学）

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

Comments 8 pages, 5 figures. Preprint of the paper published in Proceedings of 2025 IEEE Symposium on Computational Intelligence in Artificial Life and Cooperative Intelligent Systems (ALIFE-CIS)

Journal ref Proceedings of 2025 IEEE Symposium on Computational Intelligence in Artificial Life and Cooperative Intelligent Systems (ALIFE-CIS), pp. 1-7 (2025)

2405.19313 2025-05-07 cs.AI cs.CL econ.GN q-fin.EC 62%

Language Models Trained to do Arithmetic Predict Human Risky and Intertemporal Choice

Jian-Qiao Zhu, Haijiang Yan, Thomas L. Griffiths

机构 * Department of Computer Science（计算机科学系）； Princeton University（普林斯顿大学）； Department of Psychology（心理学系）； University of Warwick（沃里克大学）

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

Journal ref ICLR 2025

2411.11672 2025-05-02 cs.AI cs.LG 62%

Artificial Scientific Discovery

Antonio Norelli

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments PhD thesis, 123 pages

2303.15201 2025-05-02 cs.LG cs.AI cs.RO 62%

Learning An Active Inference Model of Driver Perception and Control: Application to Vehicle Car-Following

Ran Wei, Anthony D. McDonald, Alfredo Garcia, Gustav Markkula, Johan Engstrom, Matthew O'Kelly

机构 * Army Research Office（陆军研究办公室）

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

2504.21851 2025-05-01 cs.CL cs.AI 62%

TRUST: An LLM-Based Dialogue System for Trauma Understanding and Structured Assessments

Sichang Tu, Abigail Powers, Stephen Doogan, Jinho D. Choi

机构 * DooGood Foundation（DooGood基金会）

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

Comments 5 figures, 4 tables

2504.19933 2025-04-29 cs.AI cs.LG math.OC 62%

Automated decision-making for dynamic task assignment at scale

Riccardo Lo Bianco, Willem van Jaarsveld, Jeroen Middelhuis, Luca Begnardi, Remco Dijkman

机构 * TUE（蒂尔堡大学）

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

2504.18058 2025-04-28 cs.CL cs.AI 62%

Exploring Personality-Aware Interactions in Salesperson Dialogue Agents

Sijia Cheng, Wen-Yu Chang, Yun-Nung Chen

机构 * National Taiwan University（台湾大学）

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

Comments Accepted by IWSDS 2025

2504.17872 2025-04-28 cs.RO cs.AI cs.LG 62%

Flow Matching Ergodic Coverage

Max Muchen Sun, Allison Pinosky, Todd Murphey

机构 * Center for Robotics and Biosystems, Northwestern University（机器人与生物系统中心，西北大学）

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments 15 pages, 15 figures. Accepted to Robotics: Science and Systems (RSS) 2025. Project website: https://murpheylab.github.io/lqr-flow-matching/

2408.14837 2025-04-25 cs.LG cs.AI cs.CV 62%

Diffusion Models Are Real-Time Game Engines

Dani Valevski, Yaniv Leviathan, Moab Arar, Shlomi Fruchter

机构 * Google Research（谷歌研究）； Google DeepMind（谷歌DeepMind）； Tel Aviv University（特拉维夫大学）

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments ICLR 2025. Project page: https://gamengen.github.io/

2504.15099 2025-04-22 cs.LG cs.AI 62%

Fast-Slow Co-advancing Optimizer: Toward Harmonious Adversarial Training of GAN

Lin Wang, Xiancheng Wang, Rui Wang, Zhibo Zhang, Minghang Zhao

机构 * School of Ocean Engineering（海洋工程学院）； Harbin Institute of Technology（哈尔滨工业大学）； Technical Center, Bogie Development Department（技术中心，转向架开发部）； CRRC Qingdao Sifang Locomotive and Rolling Stock Co., Ltd（CRRC 青岛四方机车车辆有限公司）

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

2410.14586 2025-04-22 cs.LG cs.AI 62%

Neural Combinatorial Clustered Bandits for Recommendation Systems

Baran Atalar, Carlee Joe-Wong

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

2408.12022 2025-04-21 cs.CL cs.AI 62%

Understanding Epistemic Language with a Language-augmented Bayesian Theory of Mind

Lance Ying, Tan Zhi-Xuan, Lionel Wong, Vikash Mansinghka, Joshua B. Tenenbaum

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

Comments 23 pages; Published at the Transactions of the Association for Computational Linguistics (TACL); Presented at NAACL 2025

2504.12562 2025-04-18 cs.AI cs.CL 62%

ZeroSumEval: Scaling LLM Evaluation with Inter-Model Competition

Haidar Khan, Hisham A. Alyahya, Yazeed Alnumay, M Saiful Bari, Bülent Yener

专题命中 Agent评测：planning(abstract)；分类 cs.AI、cs.CL

2503.10673 2025-04-18 cs.CL cs.AI 62%

ZeroSumEval: An Extensible Framework For Scaling LLM Evaluation with Inter-Model Competition

Hisham A. Alyahya, Haidar Khan, Yazeed Alnumay, M Saiful Bari, Bülent Yener

专题命中 Agent评测：planning(abstract)；分类 cs.AI、cs.CL

2504.11645 2025-04-17 cs.LG cs.AI cs.SY eess.SY math.OC 62%

Achieving Tighter Finite-Time Rates for Heterogeneous Federated Stochastic Approximation under Markovian Sampling

Feng Zhu, Aritra Mitra, Robert W. Heath

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

2501.14122 2025-04-16 cs.LG cs.AI cs.CR cs.CV 62%

Reinforcement Learning Platform for Adversarial Black-box Attacks with Custom Distortion Filters

Soumyendu Sarkar, Ashwin Ramesh Babu, Sajad Mousavi, Vineet Gundecha, Sahand Ghorbanpour, Avisek Naug, Ricardo Luna Gutierrez, Antonio Guillen

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments Accepted at the 2025 AAAI Conference on Artificial Intelligence Proceedings

Journal ref Proceedings of the AAAI Conference on Artificial Intelligence, Volume 39, 2025

2504.10167 2025-04-15 cs.CL cs.AI 62%

C-FAITH: A Chinese Fine-Grained Benchmark for Automated Hallucination Evaluation

Xu Zhang, Zhifei Liu, Jiahao Wang, Huixuan Zhang, Fan Xu, Junzhe Zhang, Xiaojun Wan

专题命中 Agent评测：agentic(abstract)；分类 cs.AI、cs.CL

2407.10989 2025-04-15 cs.CL cs.AI cs.HC 62%

Can Large Language Models Detect Verbal Indicators of Romantic Attraction?

Sandra C. Matz, Heinrich Peters, Moran Cerf, Eric Grunenberg, Paul W. Eastwick, Mitja D. Back, Eli J. Finkel

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

2504.08943 2025-04-15 cs.LG cs.AI 62%

Investigating the Treacherous Turn in Deep Reinforcement Learning

Chace Ashcraft, Kiran Karra, Josh Carney, Nathan Drenkow

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

2409.07703 2025-04-14 cs.AI cs.CL 62%

DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?

Liqiang Jing, Zhehui Huang, Xiaoyang Wang, Wenlin Yao, Wenhao Yu, Kaixin Ma, Hongming Zhang, Xinya Du, Dong Yu

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

2504.05639 2025-04-09 cs.CL cs.AI q-fin.PR 62%

DBOT: Artificial Intelligence for Systematic Long-Term Investing

Vasant Dhar, João Sedoc

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

2504.05407 2025-04-09 cs.RO cs.AI cs.LG 62%

TRATSS: Transformer-Based Task Scheduling System for Autonomous Vehicles

Yazan Youssef, Paulo Ricardo Marques de Araujo, Aboelmagd Noureldin, Sidney Givigi

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments 9 pages

2504.05019 2025-04-08 cs.LG cs.CL 62%

Mixture-of-Personas Language Models for Population Simulation

Ngoc Bui, Hieu Trung Nguyen, Shantanu Kumar, Julian Theodore, Weikang Qiu, Viet Anh Nguyen, Rex Ying

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

2504.03211 2025-04-07 cs.LG cs.AI cs.GT econ.TH 62%

Persuasive Calibration

Yiding Feng, Wei Tang

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

2504.02891 2025-04-07 cs.CL cs.AI 62%

Automated Survey Collection with LLM-based Conversational Agents

Kurmanbek Kaiyrbekov, Nicholas J Dobbins, Sean D Mooney

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

2503.20871 2025-04-04 cs.CV cs.AI cs.CL 62%

VinaBench: Benchmark for Faithful and Consistent Visual Narratives

Silin Gao, Sheryl Mathew, Li Mi, Sepideh Mamooler, Mengjie Zhao, Hiromi Wakaki, Yuki Mitsufuji, Syrielle Montariol, Antoine Bosselut

专题命中 Agent评测：planning(abstract)；分类 cs.AI、cs.CL

Comments Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2025)

2410.14582 2025-03-31 cs.AI cs.CL 62%

Do LLMs estimate uncertainty well in instruction-following?

Juyeon Heo, Miao Xiong, Christina Heinze-Deml, Jaya Narain

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

1. Agent评测 15756 篇

Knowledge capture, adaptation and composition (KCAC): A framework for cross-task curriculum learning in robotic manipulation

Cite Before You Speak: Enhancing Context-Response Grounding in E-commerce Conversational LLM-Agents

XGrammar: Flexible and Efficient Structured Generation Engine for Large Language Models

Evolutionary ecology of words

Language Models Trained to do Arithmetic Predict Human Risky and Intertemporal Choice

Artificial Scientific Discovery

Learning An Active Inference Model of Driver Perception and Control: Application to Vehicle Car-Following

TRUST: An LLM-Based Dialogue System for Trauma Understanding and Structured Assessments

Automated decision-making for dynamic task assignment at scale

Exploring Personality-Aware Interactions in Salesperson Dialogue Agents

Flow Matching Ergodic Coverage

Diffusion Models Are Real-Time Game Engines

Fast-Slow Co-advancing Optimizer: Toward Harmonious Adversarial Training of GAN

Neural Combinatorial Clustered Bandits for Recommendation Systems

Understanding Epistemic Language with a Language-augmented Bayesian Theory of Mind

ZeroSumEval: Scaling LLM Evaluation with Inter-Model Competition

ZeroSumEval: An Extensible Framework For Scaling LLM Evaluation with Inter-Model Competition

Achieving Tighter Finite-Time Rates for Heterogeneous Federated Stochastic Approximation under Markovian Sampling

Reinforcement Learning Platform for Adversarial Black-box Attacks with Custom Distortion Filters

C-FAITH: A Chinese Fine-Grained Benchmark for Automated Hallucination Evaluation

Can Large Language Models Detect Verbal Indicators of Romantic Attraction?

Investigating the Treacherous Turn in Deep Reinforcement Learning

DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?

DBOT: Artificial Intelligence for Systematic Long-Term Investing

TRATSS: Transformer-Based Task Scheduling System for Autonomous Vehicles

Mixture-of-Personas Language Models for Population Simulation

Persuasive Calibration

Automated Survey Collection with LLM-based Conversational Agents

VinaBench: Benchmark for Faithful and Consistent Visual Narratives

Do LLMs estimate uncertainty well in instruction-following?