AI Agent - arXivDaily 专题

1802.04697 2018-07-18 cs.AI cs.LG stat.ML 62%

Learning to Search with MCTSnets

Arthur Guez, Théophane Weber, Ioannis Antonoglou, Karen Simonyan, Oriol Vinyals, Daan Wierstra, Rémi Munos, David Silver

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

Comments ICML 2018 (camera-ready version)

1806.02448 2018-06-08 cs.LG cs.AI cs.NE stat.ML 62%

Deep Reinforcement Learning for General Video Game AI

Ruben Rodriguez Torrado, Philip Bontrager, Julian Togelius, Jialin Liu, Diego Perez-Liebana

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

Comments 8 pages, 4 figures, Accepted at the conference on Computational Intelligence and Games 2018 IEEE

1709.00503 2018-05-24 stat.ML cs.AI cs.LG 62%

Mean Actor Critic

Cameron Allen, Kavosh Asadi, Melrose Roderick, Abdel-rahman Mohamed, George Konidaris, Michael Littman

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

1803.10937 2018-03-30 cs.LG cs.AI stat.ML 62%

Best arm identification in multi-armed bandits with delayed feedback

Aditya Grover, Todor Markov, Peter Attia, Norman Jin, Nicholas Perkins, Bryan Cheong, Michael Chen, Zi Yang, Stephen Harris, William Chueh, Stefano Ermon

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

Comments AISTATS 2018

1803.08456 2018-03-23 cs.AI cs.LG stat.ML 62%

Deep Reinforcement Learning with Model Learning and Monte Carlo Tree Search in Minecraft

Stephan Alaniz

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

Comments The 3rd Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM) 2017

1707.04873 2017-11-22 cs.LG cs.AI 62%

Efficient Architecture Search by Network Transformation

Han Cai, Tianyao Chen, Weinan Zhang, Yong Yu, Jun Wang

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

Comments The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18). We change the title from "Reinforcement Learning for Architecture Search by Network Transformation" to "Efficient Architecture Search by Network Transformation"

1711.01391 2017-11-08 cs.AI cs.LG cs.RO 62%

Guiding the search in continuous state-action spaces by learning an action sampling distribution from off-target samples

Beomjoon Kim, Leslie Pack Kaelbling, Tomas Lozano-Perez

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

1710.05958 2017-10-18 cs.LG cs.AI cs.CV 62%

Gradient-free Policy Architecture Search and Adaptation

Sayna Ebrahimi, Anna Rohrbach, Trevor Darrell

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

Comments Accepted in Conference on Robot Learning, 2017

1707.03034 2017-07-12 cs.RO cs.AI cs.LG 62%

Learning Heuristic Search via Imitation

Mohak Bhardwaj, Sanjiban Choudhury, Sebastian Scherer

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

Comments 14 pages

1705.08520 2017-05-25 cs.AI cs.LG cs.NE 62%

An effective algorithm for hyperparameter optimization of neural networks

Gonzalo Diaz, Achille Fokoue, Giacomo Nannicini, Horst Samulowitz

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

1609.00777 2017-04-21 cs.CL cs.LG 62%

Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access

Bhuwan Dhingra, Lihong Li, Xiujun Li, Jianfeng Gao, Yun-Nung Chen, Faisal Ahmed, Li Deng

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

Comments Accepted at ACL 2017

1610.00388 2017-01-12 cs.CL cs.LG 62%

Learning to Translate in Real-time with Neural Machine Translation

Jiatao Gu, Graham Neubig, Kyunghyun Cho, Victor O. K. Li

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

Comments 10 pages, camera ready

1509.01644 2015-11-30 cs.AI cs.LG 62%

Reinforcement Learning with Parameterized Actions

Warwick Masson, Pravesh Ranchod, George Konidaris

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

Comments Accepted for AAAI 2016

1205.3109 2015-03-19 cs.LG cs.AI stat.ML 62%

Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search

Arthur Guez, David Silver, Peter Dayan

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

Comments 14 pages, 7 figures, includes supplementary material. Advances in Neural Information Processing Systems (NIPS) 2012

Journal ref (2012) Advances in Neural Information Processing Systems 25, pages 1034-1042

1306.4753 2013-06-21 cs.LG cs.AI math.OC 62%

Galerkin Methods for Complementarity Problems and Variational Inequalities

Geoffrey J. Gordon

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

1209.3818 2013-04-03 cs.AI cs.LG 62%

Evolution and the structure of learning agents

Alok Raj

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

Comments total 4 pages. Submitted to IEEE Congress on Evolutionary Computation 2013

1301.5488 2013-01-24 cs.LG cs.AI stat.ML 62%

Multi-class Generalized Binary Search for Active Inverse Reinforcement Learning

Francisco Melo, Manuel Lopes

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

1202.2112 2012-02-10 cs.AI cs.LG cs.RO 62%

Predicting Contextual Sequences via Submodular Function Maximization

Debadeepta Dey, Tian Yu Liu, Martial Hebert, J. Andrew Bagnell

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

Comments 8 pages

0909.0801 2010-12-30 cs.AI cs.IT cs.LG math.IT 62%

A Monte Carlo AIXI Approximation

Joel Veness, Kee Siong Ng, Marcus Hutter, William Uther, David Silver

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

Comments 51 LaTeX pages, 11 figures, 6 tables, 4 algorithms

0912.5029 2010-01-14 cs.LG cs.AI 62%

Complexity of stochastic branch and bound methods for belief tree search in Bayesian reinforcement learning

Christos Dimitrakakis

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

Comments 13 pages, 1 figure, ICAART 2010

cs/0610170 2009-12-01 cs.LG cs.AI 62%

Low-complexity modular policies: learning to play Pac-Man and a new framework beyond MDPs

Istvan Szita, Andras Lorincz

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

Comments 23 pages

2608.15089 2026-08-18 cs.AI 新提交 61%

StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling

StateM：通过工具链扩展在Terminal-Bench 2.1上达到95.3%的原始准确率，或实现15美元的前沿运行

Ziheng Qin, Yaxin Lu, Zhangyang Atlas Wang, Kai Wang

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

AI总结本研究提出智能体原生运行时StateM，通过工具链扩展优化智能体执行系统，在Terminal-Bench 2.1等基准上显著提升GPT-5.6、DeepSeek-V4 Flash等模型的任务准确率，大幅降低运行成本，验证了其有效性与泛化性。

Comments Harness Scaling, Semi-Self-Evolving Agent

2604.07872 2026-04-10 cs.NE cs.AI 61%

PyVRP$^+$: LLM-Driven Metacognitive Heuristic Evolution for Hybrid Genetic Search in Vehicle Routing Problems

PyVRP$^+$：基于LLM的元认知启发式进化方法用于车辆路径问题中的混合遗传搜索

Manuj Malik, Jianan Zhou, Shashank Reddy Chirra, Zhiguang Cao

机构 * Singapore Management University（新加坡管理大学）； Nanyang Technological University（南洋理工大学）； University of Oxford（牛津大学）

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

AI总结本文提出PyVRP$^+$，通过LLM驱动的元认知启发式进化方法改进混合遗传搜索算法，发现更高效的启发式策略，提升VRP问题的求解性能。

Comments 18 pages, accepted to the 25th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2026)

2602.17675 2026-02-23 cs.DC cs.AI 61%

Mind the Boundary: Stabilizing Gemini Enterprise A2A via a Cloud Run Hub Across Projects and Accounts

注意边界：通过跨项目和账户的云运行枢纽稳定Gemini Enterprise A2A

Takao Morita

机构 * Independent Researcher（独立研究者）

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

AI总结通过跨项目和账户的云运行枢纽稳定Gemini Enterprise A2A，解决边界依赖认证和UI兼容性问题，实现可靠路由和稳定响应。

Comments 7 pages. Implementation and evaluation study of cross-boundary agent orchestration for Gemini Enterprise UI

2309.10796 2025-02-25 cs.RO cs.AI 61%

Heuristic Search for Path Finding with Refuelling

Shizhe Zhao, Anushtup Nandy, Howie Choset, Sivakumar Rathinam, Zhongqiang Ren

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

Comments 8 pages, 6 figures, RA-L 2025 submission, Motion and Path Path Planning, Scheduling and Coordination, Robotics in Under-Resourced Settings

2306.04019 2023-06-08 cs.AI 61%

Learning Search-Space Specific Heuristics Using Neural Networks

Yu Liu, Ryo Kuroiwa, Alex Fukunaga

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

Comments Proceedings of ICAPS Workshop on Heuristics and Search for Domain-independent Planning (HSDIP) 2020, pp.1-8

1706.03254 2017-11-13 cs.AI cs.DC 61%

On Hash-Based Work Distribution Methods for Parallel Best-First Search

Yuu Jinnai, Alex Fukunaga

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

Comments Source code of domain-specific solvers in multicore environment: https://github.com/jinnaiyuu/Parallel-Best-First-Searches Source code of classical planning in distributed environment: https://github.com/jinnaiyuu/distributed-fast-downward

Journal ref Yuu Jinnai and Alex Fukunaga. (2017). On Hash-Based Work Distribution Methods for Parallel Best-First Search. Journal of Artificial Intelligence Research (JAIR), 60, 491-548

2309.12589 2023-09-25 cs.RO 60%

A Multi-Robot Task Assignment Framework for Search and Rescue with Heterogeneous Teams

Hamid Osooli, Paul Robinette, Kshitij Jerath, S. Reza Ahmadzadeh

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

Comments The 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2023 Advances in Multi-Agent Learning - Coordination, Perception, and Control Workshop)

2608.18727 2026-08-20 cs.LG cs.IR 新提交 57%

Visual-Aware Representation of Web Pages for Machine Learning Applications

面向机器学习应用的网页视觉感知表示

Radek Burget, Radek Hranický

机构 * Brno University of Technology（布尔诺理工大学）； Faculty of Information Technology（信息技术学院）

专题命中工具调用：workflow(abstract)；分类 cs.LG

AI总结本文提出基于FitLayout的网页视觉感知表示与机器学习平台，支持数据集准备、机器学习输入获取，可用于训练图神经网络识别网页关键内容元素，保障结果可复现。

2608.17546 2026-08-19 cs.SE 新提交 57%

REST API Testing with Verified LLM-Inferred Dependencies and Response-Driven Refinement

基于经验证的LLM推断依赖关系与响应驱动优化的REST API测试

Tu Nguyen, Thanh Nguyen, Huy Nguyen, Viet Nguyen, Tien N. Nguyen, Vu Nguyen

专题命中工具调用：workflow(abstract)；分类 cs.SE

AI总结本文提出APIPilot框架，通过执行验证LLM推断的REST API依赖关系，结合响应驱动优化，在16个真实API上实现高覆盖率与成功率，优于现有基线。

Comments Submitted to ICSE 2027

1. 工具调用 5059 篇

Learning to Search with MCTSnets

Deep Reinforcement Learning for General Video Game AI

Mean Actor Critic

Best arm identification in multi-armed bandits with delayed feedback

Deep Reinforcement Learning with Model Learning and Monte Carlo Tree Search in Minecraft

Efficient Architecture Search by Network Transformation

Guiding the search in continuous state-action spaces by learning an action sampling distribution from off-target samples

Gradient-free Policy Architecture Search and Adaptation

Learning Heuristic Search via Imitation

An effective algorithm for hyperparameter optimization of neural networks

Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access

Learning to Translate in Real-time with Neural Machine Translation

Reinforcement Learning with Parameterized Actions

Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search

Galerkin Methods for Complementarity Problems and Variational Inequalities

Evolution and the structure of learning agents

Multi-class Generalized Binary Search for Active Inverse Reinforcement Learning

Predicting Contextual Sequences via Submodular Function Maximization

A Monte Carlo AIXI Approximation

Complexity of stochastic branch and bound methods for belief tree search in Bayesian reinforcement learning

Low-complexity modular policies: learning to play Pac-Man and a new framework beyond MDPs

StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling

PyVRP$^+$: LLM-Driven Metacognitive Heuristic Evolution for Hybrid Genetic Search in Vehicle Routing Problems

Mind the Boundary: Stabilizing Gemini Enterprise A2A via a Cloud Run Hub Across Projects and Accounts

Heuristic Search for Path Finding with Refuelling

Learning Search-Space Specific Heuristics Using Neural Networks

On Hash-Based Work Distribution Methods for Parallel Best-First Search

A Multi-Robot Task Assignment Framework for Search and Rescue with Heterogeneous Teams

Visual-Aware Representation of Web Pages for Machine Learning Applications

REST API Testing with Verified LLM-Inferred Dependencies and Response-Driven Refinement