AI Agent - arXivDaily 专题

2503.19815 2025-03-26 cs.AI cs.NE 57%

Thinking agents for zero-shot generalization to qualitatively novel tasks

Thomas Miconi, Kevin McKee, Yicong Zheng, Jed McCaleb

机构 * Astera Institute（阿斯特拉研究所）

专题命中 Agent评测：agent(abstract)；分类 cs.AI

2503.19090 2025-03-26 cs.CL 57%

LLM-Based Insight Extraction for Contact Center Analytics and Cost-Efficient Deployment

Varsha Embar, Ritvik Shrivastava, Vinay Damodaran, Travis Mehlinger, Yu-Chung Hsiao, Karthik Raghunathan

机构 * Cisco Systems（思科系统公司）

专题命中 Agent评测：agent(abstract)；分类 cs.CL

2503.18531 2025-03-25 cs.RO cs.LG cs.NE 57%

Parental Guidance: Efficient Lifelong Learning through Evolutionary Distillation

Octi Zhang, Quanquan Peng, Rosario Scalise, Bryon Boots

机构 * Paul G Allen School, University of Washington（华盛顿大学保罗·G·艾伦学院）； Shanghai Jiao Tong University（上海交通大学）

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments 4 pages, 3 figures, CoRL 2024 Workshop MAPoDeL

2411.17188 2025-03-25 cs.CV cs.CL 57%

Interleaved Scene Graphs for Interleaved Text-and-Image Generation Assessment

Dongping Chen, Ruoxi Chen, Shu Pu, Zhaoyi Liu, Yanru Wu, Caixi Chen, Benlin Liu, Yue Huang, Yao Wan, Pan Zhou, Ranjay Krishna

专题命中 Agent评测：agent(abstract)；分类 cs.CL

Comments Accepted by ICLR 2025 as Spotlight. Project homepage: https://interleave-eval.github.io/

2503.17963 2025-03-25 cs.CL 57%

Won: Establishing Best Practices for Korean Financial NLP

Guijin Son, Hyunwoo Ko, Haneral Jung, Chami Hwang

机构 * OneLineAI ； KRX（韩国交易所）

专题命中 Agent评测：agent(abstract)；分类 cs.CL

Comments The training dataset is uploaded here: https://huggingface.co/datasets/KRX-Data/Won-Instruct. The model will be updated shortly

2402.19090 2025-03-25 cs.LG 57%

Best Arm Identification with Resource Constraints

Zitian Li, Wang Chi Cheung

机构 * National University of Singapore（新加坡国立大学）

专题命中 Agent评测：agent(abstract)；分类 cs.LG

2312.01227 2025-03-25 cs.LG cs.MA cs.RO eess.SP 57%

Distributed Bayesian Estimation in Sensor Networks: Consensus on Marginal Densities

Parth Paritosh, Nikolay Atanasov, Sonia Martinez

专题命中 Agent评测：agent(abstract)；分类 cs.LG

2503.15726 2025-03-21 cs.AI 57%

Reinforcement Learning Environment with LLM-Controlled Adversary in D&D 5th Edition Combat

Joseph Emmanuel DL Dayo, Michel Onasis S. Ogbinar, Prospero C. Naval

机构 * University of the Philippines（菲律宾大学）

专题命中 Agent评测：agent(abstract)；分类 cs.AI

Comments Preprint. Submitted to the 31st International Conference on Neural Information Processing (ICONIP 2024)

2503.13772 2025-03-19 cs.DC cs.SE 57%

Do Large Language Models Understand Performance Optimization?

Bowen Cui, Tejas Ramesh, Oscar Hernandez, Keren Zhou

专题命中 Agent评测：agent(abstract)；分类 cs.SE

Comments First two authors have equal contributions

2501.18291 2025-03-19 cs.AI cs.HC 57%

CueTip: An Interactive and Explainable Physics-aware Pool Assistant

Sean Memery, Kevin Denamganai, Jiaxin Zhang, Zehai Tu, Yiwen Guo, Kartic Subr

机构 * University of Edinburgh（爱丁堡大学）； Lightspeed Studios（光速工作室）； Independent Researcher（独立研究者）

专题命中 Agent评测：agent(abstract)；分类 cs.AI

2503.12814 2025-03-18 cs.GR cs.AI cs.RO 57%

Versatile Physics-based Character Control with Hybrid Latent Representation

Jinseok Bae, Jungdam Won, Donggeun Lim, Inwoo Hwang, Young Min Kim

机构 * Seoul National University（首尔大学）

专题命中 Agent评测：agent(abstract)；分类 cs.AI

2306.12037 2025-03-18 math.OC cs.LG cs.MA 57%

Distributed Random Reshuffling Methods with Improved Convergence

Kun Huang, Linli Zhou, Shi Pu

机构 * School of Data Science, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）数据科学学院）

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments 16 pages, 8 figures, a short version would appear in IEEE TAC

2503.10697 2025-03-17 cs.CV cs.AI eess.IV 57%

Zero-Shot Subject-Centric Generation for Creative Application Using Entropy Fusion

Kaifeng Zou, Xiaoyi Feng, Peng Wang, Tao Huang, Zizhou Huang, Zhang Haihang, Yuntao Zou, Dagang Li

机构 * Link-To ； Macau University of Science and Technology（澳门科技大学）； Huazhong University of Science and Technology（华中科技大学）

专题命中 Agent评测：agent(abstract)；分类 cs.AI

Comments 8 pages, 8 figure

2503.09533 2025-03-14 cs.LG 57%

Large Language Models for Multi-Facility Location Mechanism Design

Nguyen Thach, Fei Liu, Houyu Zhou, Hau Chan

机构 * University of Nebraska-Lincoln（内布拉斯加大学林肯分校）； City University of Hong Kong（香港城市大学）

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments Under Review

2503.09586 2025-03-13 cs.AI cs.CR 57%

Auspex: Building Threat Modeling Tradecraft into an Artificial Intelligence-based Copilot

Andrew Crossman, Andrew R. Plummer, Chandra Sekharudu, Deepak Warrier, Mohammad Yekrangian

机构 * JP Morgan Chase（摩根大通）

专题命中 Agent评测：agent(abstract)；分类 cs.AI

2501.17202 2025-03-13 cs.SD cs.CL eess.AS 57%

Audio Large Language Models Can Be Descriptive Speech Quality Evaluators

Chen Chen, Yuchen Hu, Siyin Wang, Helin Wang, Zhehuai Chen, Chao Zhang, Chao-Han Huck Yang, Eng Siong Chng

机构 * Nanyang Technological University（南洋理工大学）； NVIDIA（英伟达）； Tsinghua University（清华大学）； Johns Hopkins University（约翰斯·霍普金斯大学）

专题命中 Agent评测：agent(abstract)；分类 cs.CL

Comments ICLR 2025

2412.08014 2025-03-12 cs.CV cs.AI 57%

MAGIC: Mastering Physical Adversarial Generation in Context through Collaborative LLM Agents

Yun Xing, Nhat Chung, Jie Zhang, Yue Cao, Ivor Tsang, Yang Liu, Lei Ma, Qing Guo

专题命中 Agent评测：agent(abstract)；分类 cs.AI

2408.08761 2025-03-12 cs.LG 57%

Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct Optimization

Sascha Marton, Tim Grams, Florian Vogt, Stefan Lüdtke, Christian Bartelt, Heiner Stuckenschmidt

机构 * University of Mannheim（曼海姆大学）； Technical University of Clausthal（克劳斯塔尔工业大学）； University of Rostock（罗斯托克大学）

专题命中 Agent评测：agent(abstract)；分类 cs.LG

2405.04732 2025-03-12 cs.RO cs.AI 57%

Is the House Ready For Sleeptime? Generating and Evaluating Situational Queries for Embodied Question Answering

Vishnu Sashank Dorbala, Prasoon Goyal, Robinson Piramuthu, Michael Johnston, Reza Ghanadhan, Dinesh Manocha

机构 * Amazon AGI（亚马逊AGI）； University of Maryland, College Park（马里兰大学帕克分校）

专题命中 Agent评测：agent(abstract)；分类 cs.AI

Comments 10 Pages

2503.06803 2025-03-11 cs.HC cs.AI 57%

Actionable AI: Enabling Non Experts to Understand and Configure AI Systems

Cécile Boulard, Sruthi Viswanathan, Wanda Fey, Thierry Jacquin

机构 * Naver Labs Europe（Naver 欧洲实验室）； University of Oxford（牛津大学）； AltAI ego

专题命中 Agent评测：agent(abstract)；分类 cs.AI

2410.04460 2025-03-11 eess.IV cs.CV cs.LG 57%

U-net based prediction of cerebrospinal fluid distribution and ventricular reflux grading

Melanie Rieff, Fabian Holzberger, Oksana Lapina, Geir Ringstad, Lars Magnus Valnes, Bogna Warsza, Kent-Andre Mardal, Per Kristian Eide, Barbara Wohlmuth

机构 * Technical University of Munich（慕尼黑工业大学）； Oslo University Hospital Rikshospitalet（奥斯陆大学医院理克斯医院）； Sorlandet Hospital（索兰医院）； University of Oslo（奥斯陆大学）； Simula Research Laboratory（Simula研究实验室）

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments 13 pages, 7 figures

2312.07929 2025-03-11 cs.GT cs.LG 57%

Robust and Performance Incentivizing Algorithms for Multi-Armed Bandits with Strategic Agents

Seyed A. Esmaeili, Suho Shin, Aleksandrs Slivkins

专题命中 Agent评测：agent(abstract)；分类 cs.LG

2503.05563 2025-03-10 cs.LG math.OC stat.ML 57%

Tractable Representations for Convergent Approximation of Distributional HJB Equations

Julie Alhosh, Harley Wiltzer, David Meger

机构 * Mila（米拉研究所）

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments Accepted to RLDM 2025

2503.05322 2025-03-10 cs.CV cs.AI eess.IV 57%

Attenuation artifact detection and severity classification in intracoronary OCT using mixed image representations

Pierandrea Cancian, Simone Saitta, Xiaojin Gu, Rudolf L. M. van Herten, Thijs J. Luttikholt, Jos Thannhauser, Rick H. J. A. Volleberg, Ruben G. A. van der Waerden, Joske L. van der Zande, Clarisa I. Sánchez, Bram van Ginneken, Niels van Royen, Ivana Išgum

机构 * Amsterdam UMC（阿姆斯特丹大学医学中心）； University of Amsterdam（阿姆斯特丹大学）； Amsterdam Cardiovascular Sciences（阿姆斯特丹心血管科学中心）； Radboud University Medical Center（拉德堡德大学医学中心）

专题命中 Agent评测：agent(abstract)；分类 cs.AI

2503.05274 2025-03-10 cs.RO cs.AI 57%

Evidential Uncertainty Estimation for Multi-Modal Trajectory Prediction

Sajad Marvi, Christoph Rist, Julian Schmidt, Julian Jordan, Abhinav Valada

机构 * Mercedes-Benz AG（梅赛德斯-奔驰公司）； University of Freiburg（弗赖堡大学）； TU Delft（代尔夫特理工大学）

专题命中 Agent评测：agent(abstract)；分类 cs.AI

2501.10605 2025-03-10 cs.LG cs.SY eess.SY stat.ML 57%

Wasserstein Adaptive Value Estimation for Actor-Critic Reinforcement Learning

Ali Baheri, Zahra Shahrooei, Chirayu Salgarkar

机构 * Rochester Institute of Technology（罗切斯特理工学院）

专题命中 Agent评测：agent(abstract)；分类 cs.LG

2503.04629 2025-03-07 cs.CL 57%

SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing

Xiangchao Yan, Shiyang Feng, Jiakang Yuan, Renqiu Xia, Bin Wang, Bo Zhang, Lei Bai

机构 * Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）； Fudan University（复旦大学）； Shanghai Jiao Tong University（上海交通大学）

专题命中 Agent评测：agent(abstract)；分类 cs.CL

Comments Code and dataset are available for downloading at: https://github.com/Alpha-Innovator/SurveyForge 22 pages, 10 figures

2503.04170 2025-03-07 cs.ET cs.AI 57%

Towards Intelligent Transportation with Pedestrians and Vehicles In-the-Loop: A Surveillance Video-Assisted Federated Digital Twin Framework

Xiaolong Li, Jianhao Wei, Haidong Wang, Li Dong, Ruoyang Chen, Changyan Yi, Jun Cai, Dusit Niyato, Xuemin, Shen

机构 * Xiangjiang Laboratory（湘江实验室）； Hunan University of Technology and Business（湖南工商大学）； College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics（南京航空航天大学计算机科学与技术学院）； University of Concordia（康考迪亚大学）； College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）； University of Waterloo（滑铁卢大学）

专题命中 Agent评测：agent(abstract)；分类 cs.AI

2309.10953 2025-03-07 math.OC cs.LG 57%

Deep Reinforcement Learning for Infinite Horizon Mean Field Problems in Continuous Spaces

Andrea Angiuli, Jean-Pierre Fouque, Ruimeng Hu, Alan Raydan

机构 * Prime Machine Learning Team, Amazon（亚马逊Prime机器学习团队）； University of California, Santa Barbara（加州大学圣巴巴拉分校）

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments Revisions made in accordance with reviewer's wishes. The revision primarily includes more results and plots from new simulations to show robustness of the method. 40 pages; 19 figures

2503.00320 2025-03-05 q-fin.TR cs.AI cs.MA 57%

Shifting Power: Leveraging LLMs to Simulate Human Aversion in ABMs of Bilateral Financial Exchanges, A bond market study

Alicia Vidler, Toby Walsh

机构 * UNSW（新南威尔士大学）

专题命中 Agent评测：agent(abstract)；分类 cs.AI

Comments 9 pages

1. Agent评测 15866 篇

Thinking agents for zero-shot generalization to qualitatively novel tasks

LLM-Based Insight Extraction for Contact Center Analytics and Cost-Efficient Deployment

Parental Guidance: Efficient Lifelong Learning through Evolutionary Distillation

Interleaved Scene Graphs for Interleaved Text-and-Image Generation Assessment

Won: Establishing Best Practices for Korean Financial NLP

Best Arm Identification with Resource Constraints

Distributed Bayesian Estimation in Sensor Networks: Consensus on Marginal Densities

Reinforcement Learning Environment with LLM-Controlled Adversary in D&D 5th Edition Combat

Do Large Language Models Understand Performance Optimization?

CueTip: An Interactive and Explainable Physics-aware Pool Assistant

Versatile Physics-based Character Control with Hybrid Latent Representation

Distributed Random Reshuffling Methods with Improved Convergence

Zero-Shot Subject-Centric Generation for Creative Application Using Entropy Fusion

Large Language Models for Multi-Facility Location Mechanism Design

Auspex: Building Threat Modeling Tradecraft into an Artificial Intelligence-based Copilot

Audio Large Language Models Can Be Descriptive Speech Quality Evaluators

MAGIC: Mastering Physical Adversarial Generation in Context through Collaborative LLM Agents

Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct Optimization

Is the House Ready For Sleeptime? Generating and Evaluating Situational Queries for Embodied Question Answering

Actionable AI: Enabling Non Experts to Understand and Configure AI Systems

U-net based prediction of cerebrospinal fluid distribution and ventricular reflux grading

Robust and Performance Incentivizing Algorithms for Multi-Armed Bandits with Strategic Agents

Tractable Representations for Convergent Approximation of Distributional HJB Equations

Attenuation artifact detection and severity classification in intracoronary OCT using mixed image representations

Evidential Uncertainty Estimation for Multi-Modal Trajectory Prediction

Wasserstein Adaptive Value Estimation for Actor-Critic Reinforcement Learning

SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing

Towards Intelligent Transportation with Pedestrians and Vehicles In-the-Loop: A Surveillance Video-Assisted Federated Digital Twin Framework

Deep Reinforcement Learning for Infinite Horizon Mean Field Problems in Continuous Spaces

Shifting Power: Leveraging LLMs to Simulate Human Aversion in ABMs of Bilateral Financial Exchanges, A bond market study