Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems

Hugging Face Daily Papers Papers

Summary

This survey paper provides a unified review of LLM-based multi-agent systems, focusing on collaboration, failure attribution, and self-evolution through the LIFE framework, identifying open challenges and proposing a cross-stage research agenda.

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.
Original Article
View Cached Full Text

Cached at: 05/15/26, 04:23 AM

Paper page - Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems

Source: https://huggingface.co/papers/2605.14892 Published on May 14

·

Submitted byhttps://huggingface.co/JamesMile

JieMaon May 15

Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

Multi-agent systems face challenges in sustained coordination and error propagation, requiring integrated approaches that enable continuous diagnosis, reorganization, and behavioral refinement across structured collaboration stages.

LLM-basedautonomous agentshave demonstrated strong capabilities in reasoning, planning, and tool use, yet remain limited when tasks require sustainedcoordinationacross roles, tools, and environments.Multi-agent systemsaddress this through structured collaboration among specialized agents, but tightercoordinationalso amplifies a less explored risk: errors can propagate across agents and interaction rounds, producing failures that are difficult to diagnose and rarely translate into structuralself-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 autonomousself-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-loopmulti-agent systemscapable of continuously diagnosing failures, reorganizing structures, and refining agent behaviors, extending currentcoordinationframeworks toward more self-organizing forms ofcollective 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.

View arXiv pageView PDFGitHub4Add to collection

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2605.14892 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2605.14892 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.14892 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms

Hugging Face Daily Papers

This survey paper proposes an evolutionary framework for LLM agent memory mechanisms, categorizing their development into three stages: storage, reflection, and experience. It analyzes core drivers such as long-range consistency and continual learning to provide design principles for next-generation agents.

Investigating Multi-Agent Deliberation in Law

arXiv cs.AI

This paper investigates multi-agent deliberation methods for legal reasoning tasks using LLMs, introducing two novel frameworks inspired by courtroom procedures. The experiments show that multi-agent systems achieve comparable overall performance to monolithic LLMs but produce distinct answers and can solve cases that baselines fail, highlighting the potential of multi-agent approaches for legal AI.

Rethinking Continual Experience Internalization for Self-Evolving LLM Agents

arXiv cs.CL

This paper investigates why LLM agents suffer from progressive capability collapse under multi-iteration experience internalization and proposes a robust recipe addressing experience granularity, injection patterns, and training regime. Key findings include that principle-level experience, step-wise injection, and off-policy context-distillation yield more stable and sustainable continual learning.