arXiv：cs.CL· Seojin Hwang, Youngmin Choi, Hwanhee Lee·· 16 小时前
AGORA：社会脚手架如何塑造自进化多智能体系统
Evolve Together, Fall into Place: How Social Scaffolding Shapes Self-Evolving Multi-Agent Systems
AI 导读
研究提出 AGORA（Agents Growing through Organization and Relational Arrangements）框架，可在三种进化机制下独立调整团队组成与相互依赖结构（协作、从众或竞争）。在网页搜索、代码库理解和文档问答任务中，单独进化很少带来提升，而合适的脚手架最多可超越单独进化的强智能体 25 分；其方式是让能力最强的成员获得主导权、其余成员退居辅助。
正文
Abstract:Recent work lets LLM agents evolve their own harness, up to the team itself. Yet in human groups, the same abilities achieve different outcomes under different social conditions. Borrowing the notion of scaffolding from developmental psychology, we investigate whether the social scaffolding of a self-evolving multi-agent system (MAS), namely its team composition and structure of interdependence (e.g., collaboration, conformity, or competition), shapes how the team evolves. We present AGORA (Agents Growing through Organization and Relational Arrangements), a framework that varies the two axes independently across three evolution mechanisms. Across web search, codebase understanding, and document QA, we find that (1) evolution alone rarely helps, while the right scaffolding surpasses a strong agent evolved alone by up to 25 points; (2) it does so by moving authority to the most capable member while the others step back; and (3) this member, having grown within the team, outperforms the same model alone. Designing a self-evolving MAS thus requires designing its social scaffolding, which shapes not only how its agents learn, but who gets to lead.
| Comments: | 35 pages, 27 tables, Figure 2 |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.19799 [cs.CL] |
| (or arXiv:2610.19799v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.19799 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Seojin Hwang [view email]
[v1]
Wed, 14 Oct 2026 08:42:05 UTC (882 KB)
来源：arXiv：cs.CL · arxiv.org