AI Agent

Nested Reasoning About Autonomous Agents Using Probabilistic Programs

Iris Rubi Seaman, Jan-Willem van de Meent, David Wingate

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

SPA: Verbal Interactions between Agents and Avatars in Shared Virtual Environments using Propositional Planning

Andrew Best, Sahil Narang, Dinesh Manocha

专题命中 规划决策 ：planning(title,abstract)；agent(abstract)；multi-agent(abstract)；分类 cs.CL

Path Planning Games

Yi Li, Yevgeniy Vorobeychik

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

Dynamic Real-time Multimodal Routing with Hierarchical Hybrid Planning

Shushman Choudhury, Jacob P. Knickerbocker, Mykel J. Kochenderfer

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

Comments 8 pages, 8 figures, Accepted to Intelligent Vehicles (IV) Symposium 2019

Reachability and Coverage Planning for Connected Agents: Extended Version

Tristan Charrier, Arthur Queffelec, Ocan Sankur, François Schwarzentruber

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

Efficient Evolutionary Methods for Game Agent Optimisation: Model-Based is Best

Simon M. Lucas, Jialin Liu, Ivan Bravi, Raluca D. Gaina, John Woodward, Vanessa Volz, Diego Perez-Liebana

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

Comments 8 pages, to appear in 2019 AAAI workshop on Games and Simulations for Artificial Intelligence ( https://www.gamesim.ai/ )

Assumption-Based Planning

Damien Pellier, Humbert Fiorino

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

Journal ref Proceedings of the International Conference on Advances in Intelligence Systems Theory and Applications (AISTA), 2004, November, pages 367-376, Luxembourg-Kirchberg, Luxembourg

A Gentle Introduction to Epistemic Planning: The DEL Approach

Thomas Bolander

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

Comments In Proceedings M4M9 2017, arXiv:1703.01736

Journal ref EPTCS 243, 2017, pp. 1-22

Teleo-Reactive Programs for Agent Control

N. Nilsson

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

Comments See http://www.jair.org/ for any accompanying files

Journal ref Journal of Artificial Intelligence Research, Vol 1, (1994), 139-158

Interactive POMDP Lite: Towards Practical Planning to Predict and Exploit Intentions for Interacting with Self-Interested Agents

Trong Nghia Hoang, Kian Hsiang Low

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

Comments 23rd International Joint Conference on Artificial Intelligence (IJCAI 2013), Extended version with proofs, 24 pages

OBDD-based Universal Planning for Synchronized Agents in Non-Deterministic Domains

R. M. Jensen, M. M. Veloso

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

Journal ref Journal Of Artificial Intelligence Research, Volume 13, pages 189-226, 2000

Real-time motion planning and decision-making for a group of differential drive robots under connectivity constraints using robust MPC and mixed-integer programming

Angelo Caregnato-Neto, Marcos Ricardo Omena de Albuquerque Maximo, Rubens Junqueira Magalhães Afonso

专题命中 规划决策 ：planning(title,abstract)；agent(abstract)；multi-agent(abstract)

Comments Submitted to Advanced Robotics special issue on Online Motion Planning and Model Predictive Control

Towards computing low-makespan solutions for multi-arm multi-task planning problems

Valentin N. Hartmann, Marc Toussaint

专题命中 规划决策 ：planning(title,abstract)；agent(abstract)；multi-agent(abstract)

Comments Workshop for Planning and Robotics (PlanRob), International Conference on Automated Planning and Scheduling (ICAPS), 2023

PiP: Planning-informed Trajectory Prediction for Autonomous Driving

Haoran Song, Wenchao Ding, Yuxuan Chen, Shaojie Shen, Michael Yu Wang, Qifeng Chen

专题命中 规划决策 ：planning(title,abstract)；agent(abstract)；multi-agent(abstract)

Comments European Conference on Computer Vision (ECCV) 2020; Project page at http://haoran-song.github.io/planning-informed-prediction

A Framework for Constrained and Adaptive Behavior-Based Agents

一种用于约束和自适应行为基 agent 的框架

Renato de Pontes Pereira, Paulo Martins Engel

专题命中 规划决策 ：agent(title_cn,summary_cn)；分类 cs.AI、cs.LG

AI总结 本文提出一种框架，通过强化学习节点整合到行为树中，解决约束 agent 的学习能力问题，并展示其与分层强化学习选项的关系，确保嵌套学习节点的收敛性。

Comments 2015; 15 pages

Cerberus: Multi-Agent Reasoning and Coverage-Guided Exploration for Static Detection of Runtime Errors

Cerberus：多智能体推理与覆盖引导探索用于运行时错误的静态检测

Hridya Dhulipala, Xiaokai Rong, Tien N. Nguyen

机构 * University of Texas at Dallas（德克萨斯大学达拉斯分校） 纠错

专题命中 规划决策 ：agent(title)；multi-agent(title)；分类 cs.LG、cs.SE

AI总结 Cerberus通过多智能体推理和覆盖引导探索，实现无执行的运行时错误静态检测，提高测试效率和错误发现能力。

An Adaptive, Data-Integrated Agent-Based Modeling Framework for Explainable and Contestable Policy Design

一种适应性强且数据集成的基于代理的建模框架，用于可解释且可争议的政策设计

Roberto Garrone

机构 * Faculty of Pure and Applied Sciences Open University of Cyprus（塞浦路斯开放大学纯科学与应用科学学院） 纠错

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

AI总结 本文提出了一种适应性强且数据集成的基于代理的建模框架，用于可解释且可争议的政策设计，通过整合动态制度、信息论诊断、结构因果模型等方法，实现对多代理系统动态行为的系统分析与比较。

Comments 27 pages, 2 case studies (emissions and smart grids). Preprint prepared during the author's PhD research at the Open University of Cyprus and the University of Milano-Bicocca. Introduces a unified framework for adaptive multi-agent learning with information-theoretic, causal, and clustering diagnostics

SFR-DeepResearch: Towards Effective Reinforcement Learning for Autonomously Reasoning Single Agents

Xuan-Phi Nguyen, Shrey Pandit, Revanth Gangi Reddy, Austin Xu, Silvio Savarese, Caiming Xiong, Shafiq Joty

机构 * Salesforce AI Research（Salesforce AI研究院） 纠错

专题命中 规划决策 ：agent(abstract)；tool-use(abstract)；workflow(abstract)；agentic(abstract)

Comments Technical Report

Project Riley: Multimodal Multi-Agent LLM Collaboration with Emotional Reasoning and Voting

Ana Rita Ortigoso, Gabriel Vieira, Daniel Fuentes, Luis Frazão, Nuno Costa, António Pereira

机构 * Polytechnic University of Leiria（莱里亚理工大学） 纠错

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

Comments 28 pages, 5 figures. Submitted for review to Information Fusion

Hierarchical Multi-Agent Framework for Carbon-Efficient Liquid-Cooled Data Center Clusters

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

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

Flow-DPO: Improving LLM Mathematical Reasoning through Online Multi-Agent Learning

Yihe Deng, Paul Mineiro

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

Comments 5 pages, 4 figures, 1 table

Multi-Agent Reinforcement Learning with Common Policy for Antenna Tilt Optimization

Adriano Mendo, Jose Outes-Carnero, Yak Ng-Molina, Juan Ramiro-Moreno

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

Comments 7 pages and 13 figures, submitted to IAENG International Journal of Computer Science for publication consideration. The paper has been accepted with minor changes. This is the latest submitted version

Reason-Plan-ReAct: A Reasoner-Planner Supervising a ReAct Executor for Complex Enterprise Tasks

原因-计划-行动：一种监督ReAct执行器的推理-规划器用于复杂企业任务

Gianni Molinari, Fabio Ciravegna

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

AI总结 RP-ReAct通过分离战略规划与低层执行，提升企业复杂任务处理的可靠性和效率。

Comments 11 pages, 1 figure, 2 tables, Workshop AAAI 2026 agentic AI Benchmarks and Applications for Enterprise Tasks

Physically Constrained Agentic AI for Energy Scheduling

面向能源调度的物理约束智能体AI

Dafnag Zhao, Yang Deng, Zhengmao Li

专题命中 规划决策 ：agentic(title,abstract)；agent(abstract)；workflow(abstract)

AI总结 该研究提出分层式ReAct能源管理系统，通过分离物理授权与语言生成，实现智能体能源调度，在Qwen 3.5检查点上验证了多模型耦合调度的可行性与成本表现。

Comments 5 pages, 2 fiugres, IEEE PES IM

A Self-Triggered Agentic Push Recommendation System

一种自触发智能推送推荐系统

Zhao-Yu Zhang, Qingying Chen, Chunyuan Zheng, Jing Zhou, Jian Sun, Siqi Chen, Leiying Chen, Chuan Zhou, Huiyou Jiang, Xin Tao, Haoxuan Li, Zhouchen Lin

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

AI总结 本文提出端到端自触发智能推送系统STEPS，含规划、执行、过滤智能体，已在抖音部署，可提升用户活跃天数、降低权限禁用率并减少计算开销。

Beacon: Knowing When and How to Perform Agentic Visual Reasoning

Beacon：智能体何时及如何执行智能体视觉推理

Qixun Wang, Yang Shi, Letian Cheng, Zhuoran Zhang, Yan He, Yuqi Tang, Qi Zhang, Xinlei Yu, Ruizhe Chen, Tianrun Xu, Yuanxing Zhang, Pengfei Wan, Haotian Wang, Xianghua Ying

机构 * Peking University（北京大学） ； Kling Team（Kling团队） ； HKUST(GZ)（香港科技大学（广州）） ； CUHK（香港中文大学） ； ZJU（浙江大学） ； THU（清华大学） 纠错

专题命中 规划决策 ：agentic(title,abstract)；tool use(abstract)；tool-use(abstract)

AI总结 本研究针对现有智能体视觉推理模型模式适应性有限、工具增益被损害抵消的问题，提出Beacon模型，通过强化学习相关机制提升性能与适应性，在多基准上表现优异。

Comments 33 pages

Domain-Aware Machine Learning for Accelerating MILP-Based Motion Planning with Temporal Logic and Chance Constraints

神经符号加速基于MILP的运动规划与时间逻辑和随机约束

Junyang Cai, Weimin Huang, Brendan Long, Matthew Cleaveland, Jyotirmoy V. Deshmukh, Lars Lindemann, Bistra Dilkina

专题命中 规划决策 ：planning(title,abstract)；agent(abstract)；multi-agent(abstract)

AI总结 本文提出利用神经符号方法加速MILP运动规划，通过机器学习指导求解器的符号搜索，提升处理时间逻辑、随机约束等复杂规划问题的效率和可扩展性。

SG-CoT: An Ambiguity-Aware Robotic Planning Framework using Scene Graph Representations

SG-CoT：一种基于场景图表示的模糊性感知机器人规划框架

Akshat Rana, Peeyush Agarwal, K. P. S. Rana, Amarjit Malhotra

机构 * Netaji Subhas University of Technology（纳塔贾·萨哈大学） 纠错

专题命中 规划决策 ：planning(title,abstract)；agent(abstract)；multi-agent(abstract)

AI总结 SG-CoT通过构建场景图并利用LLM迭代查询以检测和澄清模糊性，提升机器人规划在模糊环境中的可靠性，实验表明其在单机和多机环境中均优于现有方法。

Comments This work has been submitted to the journal Autonomous Robots for possible publication

SGTP: Sampling-based Game-Theoretic Planning for Real-Time Multi-Vehicle Autonomous Racing

SGTP：基于采样的博弈论实时多车辆自主赛车规划

Zhouheng Li, Fangguo Zhao, Mattia Piccinini, Baha Zarrouki, Yuan Gao, Zitong Shan, Johannes Betz, Chen Lv, Lei Xie

机构 * Zhejiang University（浙江大学） ； Nanyang Technological University（南洋理工大学） ； Technical University of Munich（慕尼黑工业大学） 纠错

专题命中 规划决策 ：planning(title,abstract)；agent(abstract)；multi-agent(abstract)

AI总结 针对自主多车辆赛车中平衡战略多样性与计算效率的难题，提出基于采样的博弈论规划（SGTP）框架，结合博弈论推理与GPU加速采样，经可行性选择确保安全过渡，模拟显示其在多智能体场景表现良好，还开源代码及基准促进研究。

Recursive Governance: A Graph-Theoretic Framework for Risk Propagation and Drift Detection in Agentic AI Systems

递归治理：智能体人工智能系统中风险传播与漂移检测的图论框架

Sriram Nagaraj, Advaith Nila Narayanan

专题命中 规划决策 ：agentic(title,abstract)；agent(abstract)；autonomous agent(abstract)

AI总结 针对金融机构模型风险管理问题，提出动态IaC治理循环，贡献包括引入校准DoA得分、构建DAG定义算法、开发轨迹监测协议及解决版本变化等实际复杂性问题，用于智能体人工智能系统风险传播与漂移检测。