AI Agent - arXivDaily 专题

1903.04307 2020-04-15 cs.LG cond-mat.soft 70%

A cooperative game for automated learning of elasto-plasticity knowledge graphs and models with AI-guided experimentation

Kun Wang, WaiChing Sun, Qiang Du

专题命中工具调用：agent(abstract)；multi-agent(abstract)；分类 cs.LG

1911.03366 2020-03-09 cs.NI cs.LG stat.ML 70%

Deep Reinforcement Learning for Distributed Uncoordinated Cognitive Radios Resource Allocation

Ankita Tondwalkar, Dr Andres Kwasinski

专题命中工具调用：agent(abstract)；multi-agent(abstract)；分类 cs.LG

Comments This paper has been submitted in the 21st IEEE International Workshop On Signal Processing Advances In Wireless Communications (SPAWC 2020)

1903.05751 2020-03-05 stat.ML cs.LG cs.RO 70%

Trajectory Optimization for Unknown Constrained Systems using Reinforcement Learning

Kei Ota, Devesh K. Jha, Tomoaki Oiki, Mamoru Miura, Takashi Nammoto, Daniel Nikovski, Toshisada Mariyama

专题命中工具调用：agent(abstract)；planning(abstract)；分类 cs.LG

Comments 8 pages, 6 figures, Accepted to IROS 2019

1904.10090 2020-01-16 cs.LG stat.ML 70%

Non-Stationary Markov Decision Processes, a Worst-Case Approach using Model-Based Reinforcement Learning, Extended version

Erwan Lecarpentier, Emmanuel Rachelson

专题命中工具调用：agent(abstract)；planning(abstract)；分类 cs.LG

Comments Published at NeurIPS 2019, 17 pages, 3 figures

Journal ref year: 2019; page range: 7214--7223

1912.02807 2020-01-13 cs.LG stat.ML 70%

Combining Q-Learning and Search with Amortized Value Estimates

Jessica B. Hamrick, Victor Bapst, Alvaro Sanchez-Gonzalez, Tobias Pfaff, Theophane Weber, Lars Buesing, Peter W. Battaglia

专题命中工具调用：agent(abstract)；planning(abstract)；分类 cs.LG

Comments Published as a conference paper at ICLR 2020

1912.02318 2019-12-06 cs.AI cs.MA 70%

Improving Policies via Search in Cooperative Partially Observable Games

Adam Lerer, Hengyuan Hu, Jakob Foerster, Noam Brown

专题命中工具调用：agent(abstract)；multi-agent(abstract)；分类 cs.AI

Journal ref AAAI 2020

1906.08792 2019-06-24 cs.LG cs.IT math.IT stat.ML 70%

When Multiple Agents Learn to Schedule: A Distributed Radio Resource Management Framework

Navid Naderializadeh, Jaroslaw Sydir, Meryem Simsek, Hosein Nikopour, Shilpa Talwar

专题命中工具调用：agent(abstract)；multi-agent(abstract)；分类 cs.LG

Comments Submitted to IEEE Wireless Communications Magazine

1901.01855 2019-02-19 cs.AI 70%

A* Tree Search for Portfolio Management

Xiaojie Gao, Shikui Tu, Lei Xu

专题命中工具调用：agent(abstract)；planning(abstract)；分类 cs.AI

Comments The paper needs a major revision including the title

1805.08263 2018-10-01 cs.AI cs.RO 70%

Learning What Information to Give in Partially Observed Domains

Rohan Chitnis, Leslie Pack Kaelbling, Tomás Lozano-Pérez

专题命中工具调用：agent(abstract)；autonomous agent(abstract)；分类 cs.AI

Comments CoRL 2018 final version

1806.09487 2018-06-26 cs.AI 70%

Finding Optimal Solutions to Token Swapping by Conflict-based Search and Reduction to SAT

Pavel Surynek

专题命中工具调用：agent(abstract)；multi-agent(abstract)；分类 cs.AI

1803.00259 2018-03-02 cs.AI 70%

Deep Reinforcement Learning for Sponsored Search Real-time Bidding

Jun Zhao, Guang Qiu, Ziyu Guan, Wei Zhao, Xiaofei He

专题命中工具调用：agent(abstract)；multi-agent(abstract)；分类 cs.AI

1702.06915 2017-02-24 cs.AI 70%

Solving DCOPs with Distributed Large Neighborhood Search

Ferdinando Fioretto, Agostino Dovier, Enrico Pontelli, William Yeoh, Roie Zivan

专题命中工具调用：agent(abstract)；multi-agent(abstract)；分类 cs.AI

1612.04876 2016-12-16 cs.AI 70%

Collaborative creativity with Monte-Carlo Tree Search and Convolutional Neural Networks

Memo Akten, Mick Grierson

专题命中工具调用：agent(abstract)；autonomous agent(abstract)；分类 cs.AI

Comments Presented at the Constructive Machine Learning workshop at NIPS 2016 as a poster and spotlight talk. 8 pages including 2 page references, 2 page appendix, 3 figures. Blog post (including videos) at https://medium.com/@memoakten/collaborative-creativity-with-monte-carlo-tree-search-and-convolutional-neural-networks-and-other-69d7107385a0

1503.04193 2015-09-07 cs.LO cs.AI 70%

Non-normal modalities in variants of Linear Logic

Daniele Porello, Nicolas Troquard

专题命中工具调用：agent(abstract)；multi-agent(abstract)；分类 cs.AI

1505.01629 2015-05-08 cs.LO cs.AI cs.MA cs.MS 70%

LeoPARD --- A Generic Platform for the Implementation of Higher-Order Reasoners

Max Wisniewski, Alexander Steen, Christoph Benzmüller

专题命中工具调用：agent(abstract)；multi-agent(abstract)；分类 cs.AI

Comments 6 pages, to appear in the proceedings of CICM'2015 conference

1405.1734 2014-05-16 cs.MA cs.AI 70%

Logic and Constraint Logic Programming for Distributed Constraint Optimization

Tiep Le, Enrico Pontelli, Tran Cao Son, William Yeoh

专题命中工具调用：agent(abstract)；multi-agent(abstract)；分类 cs.AI

Comments To appear in Theory and Practice of Logic Programming (TPLP)

1402.0587 2014-02-05 cs.AI 70%

Asymmetric Distributed Constraint Optimization Problems

Tal Grinshpoun, Alon Grubshtein, Roie Zivan, Arnon Netzer, Amnon Meisels

专题命中工具调用：agent(abstract)；multi-agent(abstract)；分类 cs.AI

Journal ref Journal Of Artificial Intelligence Research, Volume 47, pages 613-647, 2013

1401.3857 2014-01-17 cs.AI 70%

Case-Based Subgoaling in Real-Time Heuristic Search for Video Game Pathfinding

Vadim Bulitko, Yngvi Björnsson, Ramon Lawrence

专题命中工具调用：agent(abstract)；planning(abstract)；分类 cs.AI

Journal ref Journal Of Artificial Intelligence Research, Volume 39, pages 269-300, 2010

1207.1832 2012-07-11 cs.AI cs.LO 70%

Minimal Proof Search for Modal Logic K Model Checking

Abdallah Saffidine

专题命中工具调用：agent(abstract)；multi-agent(abstract)；分类 cs.AI

Comments Extended version of the JELIA 2012 paper with the same title

1110.4076 2011-10-19 cs.AI 70%

Learning in Real-Time Search: A Unifying Framework

V. Bulitko, G. Lee

专题命中工具调用：agent(abstract)；planning(abstract)；分类 cs.AI

Journal ref Journal Of Artificial Intelligence Research, Volume 25, pages 119-157, 2006

1110.2209 2011-10-12 cs.AI 70%

Bin Completion Algorithms for Multicontainer Packing, Knapsack, and Covering Problems

A. S. Fukunaga, R. E. Korf

专题命中工具调用：agent(abstract)；multi-agent(abstract)；分类 cs.AI

Journal ref Journal Of Artificial Intelligence Research, Volume 28, pages 393-429, 2007

1004.2880 2010-04-19 cs.AI cs.MA 70%

GRASP for the Coalition Structure Formation Problem

Nicola Di Mauro, Teresa M. A. Basile, Stefano Ferilli, Floriana Esposito

专题命中工具调用：agent(abstract)；multi-agent(abstract)；分类 cs.AI

Comments 12 pages, Submitted to an International Conference

cs/0509071 2009-12-01 cs.GT cs.AI 70%

CP-nets and Nash equilibria

Krzysztof R. Apt, Francesca Rossi, K. Brent Venable

专题命中工具调用：agent(abstract)；multi-agent(abstract)；分类 cs.AI

Comments 6 pages. in: roc. of the Third International Conference on Computational Intelligence, Robotics and Autonomous Systems (CIRAS '05). To appear

2608.05519 2026-08-07 cs.AI cs.CL cs.LG 新提交 69%

EcoAgent-Bench: Evaluating Economic Decision-Making in Budget-Constrained LLM Agents

EcoAgent-Bench：评估预算约束下大语言模型智能体的经济决策能力

Jie Wu, Ming Gong, Feixiang Cheng, Qinqin Zhao

专题命中工具调用：agent(abstract,comments)；分类 cs.AI、cs.CL、cs.LG

AI总结本文提出EcoAgent-Bench基准，评估大语言模型智能体在预算约束下的经济决策能力，发现现有智能体在该任务上表现不佳，发布了相关研究资源。

Comments 8 pages, 3 figures, 4 tables. Benchmark, dataset (304 budget-conditioned agent tasks), and evaluation harness; artifacts to be released

2505.03771 2026-08-19 cs.AR cs.MA 版本更新 67%

OneDSE: Metric-Conditioned Inverse Modeling and Active Search for Sample-Efficient DSE

OneDSE：面向样本高效设计空间探索的指标条件逆建模与主动搜索

Ritik Raj, Akshat Ramachandran, Danny Samuel, Jeff Nye, Shashank Nemawarkar, Tushar Krishna

专题命中工具调用：agent(abstract)；multi-agent(abstract)

AI总结 OneDSE通过MIND与SAIL统一CPU设计的短视距预测和长视距优化，在TailBench等测试中大幅减少评估次数，性能优于ArchGym遗传算法等基线，还可扩展到其他硬件设计场景。

2608.14846 2026-08-18 q-bio.QM q-bio.BM 新提交 67%

MultiStructRNA: a Python package for multi-algorithm RNA secondary structure prediction, ensemble analysis, and visualization

MultiStructRNA：用于多算法RNA二级结构预测、集成分析与可视化的Python包

Yashrajsinh Jadeja, Haining Lin, Mihir Metkar

专题命中工具调用：agent(abstract)；workflow(abstract)

AI总结 MultiStructRNA是一款统一Python工具包，整合多种RNA二级结构预测算法，解决工具碎片化等问题，支持集成分析与可视化，简化RNA结构分析，助力相关工作流程应用。

2510.18135 2026-08-18 cs.CV 版本更新 67%

World-in-World: World Models in a Closed-Loop World

世界中的世界：闭环世界中的世界模型

Jiahan Zhang, Muqing Jiang, Nanru Dai, Taiming Lu, Arda Uzunoglu, Shunchi Zhang, Yana Wei, Jiahao Wang, Vishal M. Patel, Paul Pu Liang, Daniel Khashabi, Cheng Peng, Rama Chellappa, Tianmin Shu, Alan Yuille, Yilun Du, Jieneng Chen

机构 * JHU（约翰·霍普金斯大学）； PKU（北京大学）； Princeton（普林斯顿大学）； MIT（麻省理工学院）； Harvard（哈佛大学）

专题命中工具调用：agent(abstract)；planning(abstract)

AI总结研究人员推出首个具身场景闭环世界模型基准平台World-in-World，发现视觉质量不保障任务成功，后训练缩放比升级预训练视频生成器更有效，增加推理计算可提升闭环性能。

Comments ICLR 2026 Oral. Add acknowledgement in arxiv v2. Code is at https://github.com/World-In-World/world-in-world

2608.12458 2026-08-14 astro-ph.GA 新提交 67%

The Ĝ Infrared Search for Extraterrestrial Civilizations with Large Energy Supplies. V. When Galaxies Glow with Industry

Ĝ红外搜寻拥有大型能源供应的地外文明。V. 当星系因工业而发光时

Olivia Curtis, Aidan J. Rowland, Jason T. Wright, Caryl Gronwall, Jakob M. Helton, Joel Leja

专题命中工具调用：agent(abstract,abstract_cn)

AI总结本研究基于恒星族群合成，对129个近邻星系开展戴森球相关技术废热搜寻，未检测到戴森球成分，设定了上限并给出群体约束，还开发了未来技术信号搜寻的框架，指出宁静星系外围是最佳搜寻区域。

Comments 34 pages, 16 figures, 4 tables, submitted to ApJ

2608.11552 2026-08-13 cs.CL cs.AI cs.LG 新提交 67%

Beyond Single-Turn Confidence: Trajectory-Adapted Uncertainty Quantification for LLM Agents

超越单轮置信度：面向大语言模型智能体的轨迹适配不确定性量化

Dylan Bouchard, Mohit Singh Chauhan

专题命中工具调用：tool-use(abstract)；分类 cs.AI、cs.CL、cs.LG

AI总结本研究探讨单轮UQ方法能否迁移至LLM智能体的交互式轨迹场景，评估三类UQ方法在多轮工具使用数据集上的表现，发现黑盒自一致性通常最优，提示需在轨迹层面重新验证单轮UQ方法。

2608.10694 2026-08-13 cs.LG cs.AI cs.CL cs.NE 版本更新 67%

Optimize Cheap, Deploy Strong: Cost-Aware Cross-Tier Transfer for Evolutionary Optimization

优化低成本部署强模型：面向进化优化的成本感知跨层迁移

Tal Oved, Roi Pony, Oshri Naparstek, Udi barzelay

机构 * IBM Research（IBM研究院）

专题命中工具调用：agentic(abstract)；分类 cs.AI、cs.CL、cs.LG

AI总结该研究提出成本感知跨层迁移方法，解耦LLM角色，在低成本层级完成大部分搜索，跨层部署提示词，在多任务多模型上实现成本大幅降低且性能不劣于同层级优化。

1. 工具调用 5047 篇

A cooperative game for automated learning of elasto-plasticity knowledge graphs and models with AI-guided experimentation

Deep Reinforcement Learning for Distributed Uncoordinated Cognitive Radios Resource Allocation

Trajectory Optimization for Unknown Constrained Systems using Reinforcement Learning

Non-Stationary Markov Decision Processes, a Worst-Case Approach using Model-Based Reinforcement Learning, Extended version

Combining Q-Learning and Search with Amortized Value Estimates

Improving Policies via Search in Cooperative Partially Observable Games

When Multiple Agents Learn to Schedule: A Distributed Radio Resource Management Framework

A* Tree Search for Portfolio Management

Learning What Information to Give in Partially Observed Domains

Finding Optimal Solutions to Token Swapping by Conflict-based Search and Reduction to SAT

Deep Reinforcement Learning for Sponsored Search Real-time Bidding

Solving DCOPs with Distributed Large Neighborhood Search

Collaborative creativity with Monte-Carlo Tree Search and Convolutional Neural Networks

Non-normal modalities in variants of Linear Logic

LeoPARD --- A Generic Platform for the Implementation of Higher-Order Reasoners

Logic and Constraint Logic Programming for Distributed Constraint Optimization

Asymmetric Distributed Constraint Optimization Problems

Case-Based Subgoaling in Real-Time Heuristic Search for Video Game Pathfinding

Minimal Proof Search for Modal Logic K Model Checking

Learning in Real-Time Search: A Unifying Framework

Bin Completion Algorithms for Multicontainer Packing, Knapsack, and Covering Problems

GRASP for the Coalition Structure Formation Problem

CP-nets and Nash equilibria

EcoAgent-Bench: Evaluating Economic Decision-Making in Budget-Constrained LLM Agents

OneDSE: Metric-Conditioned Inverse Modeling and Active Search for Sample-Efficient DSE

MultiStructRNA: a Python package for multi-algorithm RNA secondary structure prediction, ensemble analysis, and visualization

World-in-World: World Models in a Closed-Loop World

The Ĝ Infrared Search for Extraterrestrial Civilizations with Large Energy Supplies. V. When Galaxies Glow with Industry

Beyond Single-Turn Confidence: Trajectory-Adapted Uncertainty Quantification for LLM Agents

Optimize Cheap, Deploy Strong: Cost-Aware Cross-Tier Transfer for Evolutionary Optimization