群体进化智能体：通过经验共享实现开放式自我提升

摘要

开放式自我改进智能体能够通过自主调整自身结构设计来提升能力，突破预定义架构的限制，从而减少对人类干预的依赖。我们提出群体进化智能体（GEA）这一新型开放式自我改进范式，将智能体群体作为基本进化单元，实现进化过程中群体内经验的显式共享与复用。与现有采用树状进化结构的开放式自进化范式不同，GEA克服了因进化分支孤立导致的探索多样性利用效率低下的局限。在具有挑战性的编程基准测试中，GEA显著优于当前最先进的自进化方法（SWE-bench Verified任务上71.0%对56.7%，Polyglot任务上88.3%对68.3%），并与顶尖人工设计智能体框架性能持平或更优（两项基准测试分别达到71.8%和52.0%）。分析表明，GEA能更有效地将早期探索多样性转化为持续的长期进步，在同等进化代数下实现更强性能。此外，GEA展现出跨编程模型的稳定迁移性和更强鲁棒性，平均仅需1.4次迭代即可修复框架级错误，而自进化方法需要5次迭代。

English

Open-ended self-improving agents can autonomously modify their own structural designs to advance their capabilities and overcome the limits of pre-defined architectures, thus reducing reliance on human intervention. We introduce Group-Evolving Agents (GEA), a new paradigm for open-ended self-improvements, which treats a group of agents as the fundamental evolutionary unit, enabling explicit experience sharing and reuse within the group throughout evolution. Unlike existing open-ended self-evolving paradigms that adopt tree-structured evolution, GEA overcomes the limitation of inefficient utilization of exploratory diversity caused by isolated evolutionary branches. We evaluate GEA on challenging coding benchmarks, where it significantly outperforms state-of-the-art self-evolving methods (71.0% vs. 56.7% on SWE-bench Verified, 88.3% vs. 68.3% on Polyglot) and matches or exceeds top human-designed agent frameworks (71.8% and 52.0% on two benchmarks, respectively). Analysis reveals that GEA more effectively converts early-stage exploratory diversity into sustained, long-term progress, achieving stronger performance under the same number of evolved agents. Furthermore, GEA exhibits consistent transferability across different coding models and greater robustness, fixing framework-level bugs in 1.4 iterations on average, versus 5 for self-evolving methods.

群体进化智能体：通过经验共享实现开放式自我提升

Group-Evolving Agents: Open-Ended Self-Improvement via Experience Sharing

摘要

Support