Tag: Multi-Agent
All the articles with the tag "Multi-Agent".
-
CoordField: Coordination Field for Agentic UAV Task Allocation In Low-altitude Urban Scenarios
本文提出了一种基于协调场的代理系统(CoordField),通过大型语言模型解析自然语言指令并利用动态势场实现异构无人机群在城市环境中的去中心化任务分配,实验验证了其在任务覆盖、响应时间和动态适应性方面的优越性能。
-
Agentic AI: The Era of Semantic Decoding
本文提出语义解码视角,将大型语言模型、人类和工具的协作框架化为语义空间中的优化过程,通过语义令牌的交换和语义解码算法的设计探索AI系统的新计算范式。
-
When Reasoning Beats Scale: A 1.5B Reasoning Model Outranks 13B LLMs as Discriminator
This paper demonstrates that a 1.5B parameter reasoning model (Distill-R1) outperforms larger non-reasoning LLMs as a discriminator in a text-to-SQL planning framework by leveraging a novel soft score extraction method from chain-of-thought outputs, though it struggles significantly as a generator.
-
RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning
本文提出StarPO框架和RAGEN系统,通过多轮轨迹级别强化学习训练LLM智能体,揭示了训练不稳定性(如Echo Trap)和推理能力不足的挑战,并通过StarPO-S改进稳定性和泛化性,但推理能力仍需细粒度奖励设计支持。
-
EMORL: Ensemble Multi-Objective Reinforcement Learning for Efficient and Flexible LLM Fine-Tuning
本文提出EMORL框架,通过集成学习分别训练单目标模型并在隐藏状态层聚合,结合分层网格搜索优化权重,在咨询反思生成任务中实现了与传统方法相当的性能,同时显著提升了训练效率、可扩展性和解释性。