paper-with-me

홈 › Papers

Drop the Hierarchy and Roles: How Self-Organizing LLM Agents Outperform Designed Structures

2026-03-30 · Victoria Dochkina arxiv

How much autonomy can multi-agent LLM systems sustain -- and what enables it? We present a 25,000-task computational experiment spanning 8 models, 4--256 agents, and 8 coordination protocols ranging from externally imposed hierarchy to emergent self-organization. We observe that autonomous behavior already emerges in current LLM agents: given minimal structural scaffolding (fixed ordering), agents spontaneously invent specialized roles, voluntarily abstain from tasks outside their competence, and form shallow hierarchies -- without any pre-assigned roles or external design. A hybrid protocol (Sequential) that enables this autonomy outperforms centralized coordination by 14% (p<0.001), with a 44% quality spread between protocols (Cohen's d=1.86, p<0.0001). The degree of emergent autonomy scales with model capability: strong models self-organize effectively, while models below a capability threshold still benefit from rigid structure -- suggesting that as foundation models improve, the scope for autonomous coordination will expand. The system scales sub-linearly to 256 agents without quality degradation (p=0.61), producing 5,006 unique roles from just 8 agents. Results replicate across closed- and open-source models, with open-source achieving 95% of closed-source quality at 24x lower cost. The practical implication: give agents a mission, a protocol, and a capable model -- not a pre-assigned role.

📄 PDF Abstract BibTeX arXiv:2603.28990

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Self-Organizing Agent Teams Learn to Reason Together

2026-09-19 · Aneesh Pappu, Mirac Suzgun, Yongchan Kwon, Federico Bianchi 외 hf

Collective intelligence depends not only on what team members know, but also on how they organize their work. When the structure of a solution is unknown, useful roles and divisions of labor cannot be specified in advanc…

Emergence of Hierarchies in Multi-Agent Self-Organizing Systems Pursuing a Joint Objective

2025-08-13 · Gang Chen, Guoxin Wang, Anton van Beek, Zhenjun Ming 외 arxiv

Multi-agent self-organizing systems (MASOS) exhibit key characteristics including scalability, adaptability, flexibility, and robustness, which have contributed to their extensive application across various fields. Howev…

Multi-agent Reinforcement Learning

Multi-Agent Teams Hold Experts Back

2026-02-01 · Aneesh Pappu, Batu El, Hancheng Cao, Carmelo di Nolfo 외 arxiv

Multi-agent LLM systems are increasingly deployed as autonomous collaborators, where agents interact freely rather than execute fixed, pre-specified workflows. In such settings, effective coordination cannot be fully des…

Self-organizing maps and generalization: an algorithmic description of Numerosity and Variability Effects

2018-02-26 · Valentina Gliozzi, Kim Plunkett

Category, or property generalization is a central function in the human cognition. It plays a crucial role in a variety of domains, such as learning, everyday reasoning, specialized reasoning, and decision making. Judgin…

Decision Making

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

2026-05-14 · Shihao Qi, Jie Ma, Rui Xing, Wei Guo 외 arxiv

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 syst…