Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems
Shihao Qi, Jie Ma, Rui Xing, Wei Guo, Xiao Huang, Zhitao Gao, Jianhao Deng, Jun Liu, Lingling Zhang, Bifan Wei, Boqian Yang, Pinghui Wang, Jianwen Sun, Jing Tao, Yaqiang Wu, Hui Liu, Yu Yao, Tongliang Liu
Why It Matters
What makes this one worth your time
Understanding and improving coordination in multi-agent systems is crucial for developing more robust and intelligent autonomous systems capable of complex tasks.
A survey proposing a unified framework for enhancing coordination and self-improvement in multi-agent systems.
Summary
The paper surveys the integration of collaboration, failure attribution, and self-evolution in LLM-based multi-agent systems, proposing a unified framework called the LIFE progression to address coordination challenges and improve collective intelligence.
Key contributions
- Proposes the LIFE progression framework for multi-agent systems.
- Provides systematic taxonomies for each stage of the framework.
- Identifies open challenges and suggests a research agenda for self-organizing collective intelligence.
Notable insights
- The LIFE progression framework links capability foundation, collaboration, fault attribution, and self-improvement stages.
- Identifies open challenges at the boundaries of these stages, suggesting a cross-stage research agenda.
Possible limitations
- Not stated in the abstract
Abstract
arXiv:2605.14892v2 Announce Type: replace Abstract: LLM-based autonomous agents have demonstrated strong capabilities in reasoning, planning, and tool use, yet remain limited when tasks require sustained coordination across roles, tools, and environments. Multi-agent systems address this through structured collaboration among specialized agents, but tighter coordination also amplifies a less explored risk: errors can propagate across agents and interaction rounds, producing failures that are difficult to diagnose and rarely translate into structural self-improvement. Existing surveys cover individual agent capabilities, multi-agent collaboration, or agent self-evolution separately, leaving the causal dependencies among them unexamined. This survey provides a unified review organized around four causally linked stages, which we term the LIFE progression: Lay the capability foundation, Integrate agents through collaboration, Find faults through attribution, and Evolve through autonomous self-improvement. For each stage, we provide systematic taxonomies and formally characterize the dependencies between adjacent stages, revealing how each stage both depends on and constrains the next. Beyond synthesizing existing work, we identify open challenges at stage boundaries and propose a cross-stage research agenda for closed-loop multi-agent systems capable of continuously diagnosing failures, reorganizing structures, and refining agent behaviors, extending current coordination frameworks toward more self-organizing forms of collective intelligence. By bridging these previously fragmented research threads, this survey aims to offer both a systematic reference and a conceptual roadmap toward autonomous, self-improving multi-agent intelligence.