AI Agent

QSIM: Mitigating Overestimation in Multi-Agent Reinforcement Learning via Action Similarity Weighted Q-Learning

QSIM：通过动作相似性加权Q学习缓解多智能体强化学习中的过估计

Yuanjun Li, Bin Zhang, Hao Chen, Zhouyang Jiang, Dapeng Li, Zhiwei Xu

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.AI、cs.LG；planning(comments)

AI总结 QSIM通过动作相似性加权Q学习缓解多智能体强化学习中的过估计问题，提升学习稳定性与性能。

Comments 19 pages, 15 figures, 7tables. Accepted to the 36th International Conference on Automated Planning and Scheduling (ICAPS 2026)

Toward Expert Investment Teams:A Multi-Agent LLM System with Fine-Grained Trading Tasks

迈向专家投资团队：一个具有细粒度交易任务的多智能体LLM系统

Kunihiro Miyazaki, Takanobu Kawahara, Stephen Roberts, Stefan Zohren

机构 * Japan Digital Design, Inc.（日本数字设计公司） 纠错

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.AI

AI总结 本文提出了一种多智能体LLM交易框架，通过细粒度任务分解提升风险调整后的回报，并通过分析输出与决策偏好的一致性提高系统性能。

Comments 14 pages, 3 figures

Multi-Agent Large Language Model Based Emotional Detoxification Through Personalized Intensity Control for Consumer Protection

基于多智能体大语言模型的个性化强度控制情感净化系统用于消费者保护

Keito Inoshita

机构 * Faculty of Business and Commerce（商务学院） ； Kansai University（关西大学） 纠错

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.AI

AI总结 本研究提出基于多智能体大语言模型的情感净化系统，通过个性化强度控制减少信息刺激，提升消费者情绪平衡并保持语义完整性。

Managing Uncertainty in LLM-based Multi-Agent System Operation

在基于大语言模型的多智能体系统操作中管理不确定性

Man Zhang, Tao Yue, Yihua He

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.SE

AI总结 本文提出了一种基于生命周期的不确定性管理框架，用于提升基于大语言模型的多智能体系统在安全关键领域的可靠性和可诊断性。

Robust Information Design for Multi-Agent Systems with Complementarities: Smallest-Equilibrium Threshold Policies

具有互补性的多智能体系统中鲁棒信息设计：最小均衡阈值策略

Farzaneh Farhadi, Maria Chli

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)；autonomous agent(comments)

AI总结 本文提出了一种在具有互补性的多智能体系统中实现鲁棒协调的构造性策略，通过阈值规则实现完美协调，具有可扩展性和高效性。

Comments This paper has been accepted for publication in Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2026). The final published version will be available via the ACM Digital Library

Sustainable Multi-Agent Crowdsourcing via Physics-Informed Bandits

可持续的多智能体众包：通过物理指导的老虎机

Chayan Banerjee

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)

AI总结 本文提出 FORGE 模拟器和神经-线性 UCB 分配器，通过物理指导解决众包中的冷启动、疲劳、利用和战略代理矛盾，实现高奖励与低劳动力利用的平衡。

HyperAgent: Leveraging Hypergraphs for Topology Optimization in Multi-Agent Communication

HyperAgent: 利用超图进行多智能体通信中的拓扑优化

Heng Zhang, Yuling Shi, Xiaodong Gu, Zijian Zhang, Haochen You, Lubin Gan, Yilei Yuan, Jin Huang

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)

AI总结 HyperAgent通过超图优化多智能体通信拓扑，提升协作效率与适应性。

Comments This submission has been withdrawn by the authors due to a fundamental error in the methodology that affects the validity of the main results

D3MAS: Decompose, Deduce, and Distribute for Enhanced Knowledge Sharing in Multi-Agent Systems

D3MAS：分解、推断与分配以增强多智能体系统中的知识共享

Heng Zhang, Yuling Shi, Xiaodong Gu, Haochen You, Zijian Zhang, Lubin Gan, Yilei Yuan, Jin Huang

专题命中 多智能体 ：agent(title,abstract)；multi-agent(title,abstract)

AI总结 D3MAS通过分层协调框架减少多智能体系统中的知识冗余，提升推理准确性。

Comments This submission has been withdrawn by the authors due to a fundamental error in the methodology that affects the validity of the main results

Robust Distributed Nonconvex Optimization Enabling Communication Acceleration and Privacy Protection

鲁棒分布式非凸优化：实现通信加速与隐私保护

Zichong Ou, Jie Lu

专题命中 多智能体 ：agent(abstract)；multi-agent(abstract)

AI总结 本文提出鲁棒近端对偶算法RPP，通过引入随机噪声提升分布式非凸优化的隐私保护和通信效率。

Comments 8 pages, 2 figures, accepted by ACC2026

Transformer Actor-Critic for Efficient Freshness-Aware Resource Allocation

基于Transformer的Actor-Critic用于高效的 freshness-aware 资源分配

Maryam Ansarifard, Mohit K. Sharma, Kishor C. Joshi, George Exarchakos

专题命中 多智能体 ：agent(abstract)

AI总结 本文提出基于Transformer的Actor-Critic框架，用于高效实现 freshness-aware 资源分配，通过注意力机制提升策略性能和可扩展性。

Comments \c{opyright} 2026 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses. Accepted for publication in the 2026 IEEE International Conference on Machine Learning for Communication and Networking (ICMLCN)

Scaling Inference-Time Computation via Opponent Simulation: Enabling Online Strategic Adaptation in Repeated Negotiation

通过对手模拟扩展推理时间计算：在重复谈判中实现在线战略适应

Xiangyu Liu, Di Wang, Zhe Feng, Aranyak Mehta

专题命中 多智能体 ：agent(abstract)

AI总结 本文提出通过对手模拟扩展推理时间计算，利用平滑虚构扮演机制，在重复谈判中实现在线战略适应，提升决策性能。