多智能体LLM训练新范式：引入角色分解与跨智能体学习信号，实现高效协作与分工。
arXiv:2606.10684v1 Announce Type: cross Abstract: Modern language agents which perform multi-step reasoning have shown strong performance in knowledge…
联邦学习新范式：让多个智能体在隐私保护下协同进化技能，分布式训练不止于模型参数。
arXiv:2606.03143v1 Announce Type: cross Abstract: Modern LLM agents increasingly rely on skill libraries to handle complex tasks, making skill evoluti…
多智能体协作实现多模态感知，ACL 2026 前沿研究，看点多模态融合与共识机制如何提升感知精度。
arXiv:2601.06453v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly grounded in sensor data to perceive and reason about…
探索LLM多智能体系统如何通过协作机制实现团队级自我进化，提升整体性能与适应能力
arXiv:2605.29790v1 Announce Type: cross Abstract: LLM-based multi-agent systems (MAS) have emerged as an effective paradigm for complex and long-horiz…
多LLM协作推理新范式，TRACER用回合级后悔匹配提升合作效率与推理质量
arXiv:2605.28699v1 Announce Type: new Abstract: Large language models increasingly rely on either reinforcement learning or multi-agent prompting to i…
基于IBIS引导的多智能体协作框架，通过层级疾病关系链提升临床诊断准确率，医学AI新范式。
arXiv:2603.01131v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown promise in clinical diagnosis but remain limited by …
GRPO新变体F-TIS：通过多模型协作提升LLM后训练奖励信号多样性，突破单一策略局限。
arXiv:2605.22537v1 Announce Type: new Abstract: Reinforcement learning methods such as GRPO have seen great popularity in LLM post-training. In GRPO, …
联邦强化学习新突破：单时间尺度actor-critic框架平衡协作与个性化，适合多智能体异构环境。
arXiv:2605.14423v1 Announce Type: cross Abstract: Despite the popularity of the actor-critic method and the practical needs of collaborative policy tr…