AI Agent

More Similar Values, More Trust? -- the Effect of Value Similarity on Trust in Human-Agent Interaction

Siddharth Mehrotra, Catholijn M. Jonker, Myrthe L. Tielman

专题命中 规划决策 ：agent(title,abstract)；分类 cs.AI

Comments 4th AAAI/ACM Conference on AI, Ethics, and Society

Journal ref S Mehrotra, C. M. Jonker, and M. L. Tielman. More Similar Values, More Trust? - the Effect of Value Similarity on Trust in Human-Agent Interaction in Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society (AIES 21)

Waypoint Planning Networks

Alexandru-Iosif Toma, Hussein Ali Jaafar, Hao-Ya Hsueh, Stephen James, Daniel Lenton, Ronald Clark, Sajad Saeedi

专题命中 规划决策 ：planning(title,abstract)；分类 cs.LG

Comments The Conference on Robots and Vision (CRV2021) Supplementary Website: https://sites.google.com/view/waypoint-planning-networks

Motion Planning for a Pair of Tethered Robots

Reza H. Teshnizi, Dylan A. Shell

专题命中 规划决策 ：planning(title,abstract)；分类 cs.AI

Comments Accepted to appear in Autonomous Robots Special Issue 203: Topological Methods in Robotics. Keywords: Motion Planning; Tethered Robots; Multi-Robot Coordination; A* Search

From Classical to Hierarchical: benchmarks for the HTN Track of the International Planning Competition

Damien Pellier, Humbert Fiorino

专题命中 规划决策 ：planning(title,abstract)；分类 cs.AI

Journal ref Proceedings of the International Planning Competition, ICAPS, Nancy, France, 2020

Iterative Planning with Plan-Space Explanations: A Tool and User Study

Rebecca Eifler, Jörg Hoffmann

专题命中 规划决策 ：planning(title,abstract)；分类 cs.AI

Comments Proceedings of the International Workshop of Explainable AI Planning (XAIP'20), at ICAPS'20

A Long Horizon Planning Framework for Manipulating Rigid Pointcloud Objects

Anthony Simeonov, Yilun Du, Beomjoon Kim, Francois R. Hogan, Joshua Tenenbaum, Pulkit Agrawal, Alberto Rodriguez

专题命中 规划决策 ：planning(title,abstract)；分类 cs.LG

Comments Conference on Robot Learning (CoRL 2020): Project website: https://anthonysimeonov.github.io/rpo-planning-framework/

PDDLStream: Integrating Symbolic Planners and Blackbox Samplers via Optimistic Adaptive Planning

Caelan Reed Garrett, Tomás Lozano-Pérez, Leslie Pack Kaelbling

专题命中 规划决策 ：planning(title,abstract)；分类 cs.AI

Comments International Conference on Automated Planning and Scheduling (ICAPS) 2020

Latent Space Roadmap for Visual Action Planning of Deformable and Rigid Object Manipulation

Martina Lippi, Petra Poklukar, Michael C. Welle, Anastasiia Varava, Hang Yin, Alessandro Marino, Danica Kragic

专题命中 规划决策 ：planning(title,abstract)；分类 cs.LG

Comments Project website: https://visual-action-planning.github.io/lsr/

Socially intelligent task and motion planning for human-robot interaction

Andrea Frank, Laurel Riek

专题命中 规划决策 ：planning(title,abstract)；分类 cs.AI

Comments 2 pages plus references, no figures. Presented at RSS 2019 Workshop on Robust Task and Motion Planning

HDDL -- A Language to Describe Hierarchical Planning Problems

D. Höller, G. Behnke, P. Bercher, S. Biundo, H. Fiorino, D. Pellier, R. Alford

专题命中 规划决策 ：planning(title,abstract)；分类 cs.AI

Comments International Workshop on HTN Planning (ICAPS), 2019

End-to-End Motion Planning of Quadrotors Using Deep Reinforcement Learning

Efe Camci, Erdal Kayacan

专题命中 规划决策 ：planning(title,abstract)；分类 cs.AI

Comments IROS 2019 Workshop, Learning Representations for Planning and Control

Hierarchical Planning in the IPC

D. Höller, G. Behnke, P. Bercher, S. Biundo, H. Fiorino, D. Pellier, R. Alford

专题命中 规划决策 ：planning(title,abstract)；分类 cs.AI

Journal ref Workshop on the International Planning Competition (ICAPS), 2019

Towards Explainable AI Planning as a Service

Michael Cashmore, Anna Collins, Benjamin Krarup, Senka Krivic, Daniele Magazzeni, David Smith

专题命中 规划决策 ：planning(title,abstract)；分类 cs.AI

Comments 2nd ICAPS Workshop on Explainable Planning (XAIP-2019)

Learning STRIPS Action Models with Classical Planning

Diego Aineto, Sergio Jiménez, Eva Onaindia

专题命中 规划决策 ：planning(title,abstract)；分类 cs.AI

Comments 8+1 pages, 4 figures, 6 tables

Journal ref Twenty-Eighth International Conference on Automated Planning and Scheduling (ICAPS 2018), pp. 399-407, Year 2018

Toward a language-theoretic foundation for planning and filtering

Fatemeh Zahra Saberifar, Shervin Ghasemlou, Dylan A. Shell, Jason M. O'Kane

专题命中 规划决策 ：planning(title,abstract)；分类 cs.AI

Comments Accepted to appear in IJRR Special Issue on WAFR'16. Keywords: planning; combinatorial filter; design automation

Safe learning-based optimal motion planning for automated driving

Zlatan Ajanovic, Bakir Lacevic, Georg Stettinger, Daniel Watzenig, Martin Horn

专题命中 规划决策 ：planning(title,abstract)；分类 cs.LG

Comments 3 pages, 1 figure, 1 pseudocode, extended abstract accepted to ICML / IJCAI / AAMAS 2018 Workshop on Planning and Learning (PAL-18)

Knowledge Engineering for Planning-Based Hypothesis Generation

Shirin Sohrabi, Octavian Udrea, Anton V. Riabov

专题命中 规划决策 ：planning(title,abstract)；分类 cs.AI

Comments This paper appears in the Proceedings of the Automated Planning and Scheduling (ICAPS) Workshop on Knowledge Engineering for Planning and Scheduling (KEPS)

A Complete Parameterized Complexity Analysis of Bounded Planning

Christer Baeckstroem, Peter Jonsson, Sebastian Ordyniak, Stefan Szeider

专题命中 规划决策 ：planning(title,abstract)；分类 cs.AI

Comments The paper is a combined and extended version of the papers "The Complexity of Planning Revisited - A Parameterized Analysis" (AAAI 2012, arXiv:1208.2566) and "Parameterized Complexity and Kernel Bounds for Hard Planning Problems" (CIAC 2013, arXiv:1211.0479)

Journal ref Proc. AAAI'12, pp. 1735-1741, AAAI Press 2012 and Proc. CIAC'13, pp. 13-24, Springer

Towards Combining HTN Planning and Geometric Task Planning

Lavindra de Silva, Amit Kumar Pandey, Mamoun Gharbi, Rachid Alami

专题命中 规划决策 ：planning(title,abstract)；分类 cs.AI

Comments RSS Workshop on Combined Robot Motion Planning and AI Planning for Practical Applications, June 2013

Logic Programming for Describing and Solving Planning Problems

Maurice Bruynooghe

专题命中 规划决策 ：planning(title,abstract)；分类 cs.AI

Comments 8 pages, no figures, Eighth International Workshop on Nonmonotonic Reasoning, special track on Representing Actions and Planning

PILOT Technical Report

PILOT技术报告

Jiuning Lin, Ruiquan Lan, Xiaodong Zhu, Bin Zhang, Chengyu Lai, Chuxin Chen, Dimin Wang, Han Zhu, Hongtao Cheng, Jialin Zhu, Lingqing Zhang, Shuai Zhong, Tao Wang, Weipeng Huang, Yinjiang Cai, Yinnan Song, Yuan Liu, Zhibo Xiao, Zhixin Ma, Zihong Huang

专题命中 规划决策 ：agent(abstract,abstract_cn)；planning(abstract)；agentic(abstract)

AI总结 该研究针对现有推荐系统优化智能体方法的反应式缺陷，提出PILOT框架，通过三类角色构建控制循环，在淘宝平台对比ROAM验证，实现多项指标提升且搜索效率显著提高，无需人工干预。

Comments Technical Report, 42 pages, 10 figures

Key-Frame Reasoning with SAM3: Third Place Solution for the MeViS-Text Track of the 8th LSVOS Challenge

基于SAM3的关键帧推理：第8届LSVOS挑战赛MeViS-Text赛道第三名解决方案

Ce Bian, Xusheng He, Jinrong Zhang, Canyang Wu, Xianjing Han, Jianlong Wu

机构 * Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳）） ； Nanyang Technological University（南洋理工大学） ； Shenzhen Loop Area Institute（深圳河套学院） 纠错

专题命中 规划决策 ：agent(summary_cn,abstract)

AI总结 该研究提出两阶段无训练方案，依托Gemini-3.1 Pro分解视频事件选关键帧，用SAM3-agent生成掩码并双向传播，获第8届LSVOS挑战赛MeViS-Text赛道第三名。

Involution game with migration and spatial heterogeneity of social resources

自反游戏与迁移及社会资源空间异质性

Bo Li, Qiwen Ge, Yong Shi

专题命中 规划决策 ：agent(summary_cn,abstract)

AI总结 本文提出一个包含 agent 迁移和资源分布空间异质性的自反博弈模型，探讨迁移和资源分配条件对自反动态的影响，发现总资源恒定时相似资源水平抑制自反，而总资源增加会加剧自反，并识别努力比和效用乘数的阈值效应。

Comments 20 pages, 7figures

S1-DeepResearch: Beyond Search, Toward Real-World Long-Horizon Research Agents

S1-DeepResearch：超越搜索，迈向真实世界的长周期研究智能体

Yao Dong, Xinglin Xiao, Liwei Dong, Xinlong Jin, Zhengbo Li, Heng Zhang, Duyun Wang, Nan Xu

机构 * XScience Lab（XScience实验室） ； Wenge AI（问格人工智能） 纠错

专题命中 规划决策 ：agent(abstract)；planning(abstract)；agentic(abstract)；分类 cs.AI、cs.CL、cs.LG

AI总结 提出统一轨迹构建范式，结合封闭式问答与开放式探索，通过图基任务构建、智能体轨迹生成和多维验证，合成高质量长链推理轨迹，训练出在20个基准上达到开源最优的32B模型。

CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing

CRANE：通过空域编辑实现代码代理的约束推理注入

Mingzhi Zhu, Michele Merler, Raju Pavuluri, Stacy Patterson

机构 * Rensselaer Polytechnic Institute（拉特格斯理工学院） ； IBM Research（IBM研究院） 纠错

专题命中 规划决策 ：agent(abstract)；tool-use(abstract)；planning(abstract)；分类 cs.AI、cs.CL、cs.SE

AI总结 CRANE通过空域编辑技术，结合推理和工具使用能力，提升代码代理性能，在多个基准测试中取得显著成果。

Less Context, Better Agents: Efficient Context Engineering for Long-Horizon Tool-Using LLM Agents

更少上下文，更优智能体：面向长周期工具使用LLM智能体的高效上下文工程

Abhilasha Lodha, Mahsa Pahlavikhah Varnosfaderani, Abir Chakraborty, Abhinav Mithal

机构 * Microsoft（微软） 纠错

专题命中 规划决策 ：autonomous agent(abstract)；tool-use(abstract)；workflow(abstract)；分类 cs.AI、cs.LG、cs.SE

AI总结 针对企业工具使用场景中上下文过长导致的问题，提出选择性保留最近工具交互并添加紧凑摘要的方法，在费用明细任务上将完成率从71.0%提升至91.6%，同时大幅降低token消耗和运行时间。

Comments 17 pages, 3 figures, 8 tables

Payoff scaling shapes cooperation in LLM agents across languages

收益规模塑造跨语言LLM代理的合作行为

Trung-Kiet Huynh, Dao-Sy Duy-Minh, Thanh-Bang Cao, Phong-Hao Le, Hong-Dan Nguyen, Phu-Quy Nguyen-Lam, Minh-Luan Nguyen-Vo, Hong-Phat Pham, Phu-Hoa Pham, Thien-Kim Than, Chi-Nguyen Tran, Huy Tran, Gia-Thoai Tran-Le, Alessio Buscemi, Le Hong Trang, The Anh Han

机构 * Faculty of Information Technology, University of Science (HCMUS), Ho Chi Minh City, Vietnam（信息技术学院，科学大学（HCMUS），胡志明市，越南） ； Faculty of Computer Science and Engineering, Ho Chi Minh City University of Technology (HCMUT), Ho Chi Minh City, Vietnam（计算机科学与工程学院，胡志明市技术大学（HCMUT），胡志明市，越南） ； Vietnam National University – Ho Chi Minh City (VNU-HCM), Ho Chi Minh City, Vietnam（越南国家大学——胡志明市（VNU-HCM），胡志明市，越南） ； Luxembourg Institute of Science and Technology (LIST), Luxembourg（卢森堡科学与技术研究所（LIST），卢森堡） ； School of Computing, Engineering and Digital Technologies, Teesside University, Middlesbrough, United Kingdom（计算、工程与数字技术学院，泰赛德大学，米德尔斯布罗，英国） 纠错

专题命中 规划决策 ：agent(abstract)；autonomous agent(abstract)；multi-agent(abstract)；分类 cs.AI、cs.CL、cs.LG

AI总结 通过监督分类器识别重复囚徒困境中的策略，结合演化博弈论基线，发现随着收益增加，LLM反而更合作，与演化预测相反，表明对齐训练和人类推理模式的影响。

Comments 44 pages, 17 figures, 4 tables

Compromise by "multimatum"

通过“multimatum”达成妥协

Federico Echenique, Matías Núñez

专题命中 规划决策 ：agent(summary_cn,abstract)

AI总结 本文提出了一种解决两agent社会选择问题的机制，通过构建共同的偏好基数化来实现两agent间的高效妥协，展示了multimatum在政治经济学、其他关照偏好和设施选址中的应用价值。

Non-Local Macroeconomic Transactions and Credits-Loans Surface-Like Waves

非局部宏观经济交易与信贷-贷款类表面波

Victor Olkhov

专题命中 规划决策 ：agent(summary_cn,abstract)

AI总结 本文研究了经济空间中信贷-贷款交易的表面波特性，通过agent风险评级作为坐标，利用交易行为描述宏观变量演化，并通过流体动力学方程建模交易演变，揭示了表面波可能引发的宏观不稳定性。

Comments 20 pages

Training Deliberative Monitors for Black-Box Scheming Detection

训练审慎监控器用于黑箱策划检测

Aditya Sinha, Akshat Naik, Victor Gillioz, Simon Storf, Kilian Merkelbach, Rich Barton-Cooper, Axel Højmark, Marius Hobbhahn

机构 * Independent（独立） ； MATS Research（MATS研究） ； Astra Fellowship ； Apollo Research（Apollo研究） 纠错

专题命中 规划决策 ：agent(abstract)；autonomous agent(abstract)；agentic(abstract)；分类 cs.AI、cs.CL、cs.LG

AI总结 提出一种基于行动轨迹的审慎监控方法，通过蒸馏前沿模型的推理过程训练开源模型，以低成本高精度检测智能体的策划与破坏行为。