1
Octopus v4: Graph of language models
开源社区推出Octopus v4模型，通过图结构整合多个语言模型，实现高效协作，挑战闭源巨头
arXiv:2404.19296v2 Announce Type: replace Abstract: Language models have been effective in a wide range of applications, yet the most sophisticated mo…
2
StepFinder: A Temporal Semantic Framework for Failure Attribution in Multi-Agent Systems
多智能体系统故障溯源难？基于时间语义的新框架StepFinder，被KDD 2026接收，帮系统快速定位协作失败根源。
arXiv:2606.03467v1 Announce Type: new Abstract: LLM-based multi-agent systems exhibit remarkable collaborative capabilities in complex multi-step task…
3
MediHive: A Decentralized Agent Collective for Medical Reasoning
去中心化智能体集群协作攻克医疗推理难题，开创分布式决策新范式
arXiv:2603.27150v2 Announce Type: replace Abstract: Large language models (LLMs) have revolutionized medical reasoning tasks, yet single-agent systems…
4
COOP$^2$: Defining, Observing, and Repairing Cooperation in LLM Multi-Agent Systems
提出「合作」定义与修复框架，为LLM多智能体系统协作难题提供新视角
arXiv:2603.00349v2 Announce Type: replace Abstract: Many complex tasks require extended effort, diverse capabilities, or coordinated actions beyond wh…
5
Multi-Agent Causal Discovery Using Large Language Models
多智能体协作利用LLM进行因果发现，新方法突破传统因果推断瓶颈
arXiv:2407.15073v4 Announce Type: replace Abstract: Causal discovery aims to identify causal relationships between variables and is a fundamental prob…
6
Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training
提出统一方法论，实现设备端与云端LLM高效协作推理，优化本地路由与后训练。
arXiv:2509.24050v4 Announce Type: replace Abstract: Device-cloud collaboration holds promise for deploying large language models (LLMs), leveraging li…