通过比较多个任务轨迹，让代码自进化代理更快更优地自我改进。
Mendel Gödel Machine: Recursive Self-Improving Coding Agents via Comparative Evolution
- 基于多任务轨迹的反应范式突变，整合历史经验。
- 在SWE-bench和Polyglot上性能、效率与泛化能力全面提升。
- 适合研究自进化系统、智能编程代理的开发者参考。
能够迭代重写自身源码的自进化代码代理在编程任务中表现优异。然而，现有方法通常仅基于单一失败轨迹进行自修改，忽略了代理积累的丰富比较信号。根据孟德尔式可控遗传原理，我们提出孟德尔哥德尔机器（Mendel Gödel Machine, MGM）。除通用单轨迹克隆突变外，MGM引入两种新自修改机制：反应范式突变同时基于代理在多个任务上的轨迹进行编辑；跨谱系杂交则利用另一谱系代理在同一任务上的轨迹进行编辑。在可加性适应度景观模型下，理论证明并经受控模拟验证，新策略比单轨迹基线收敛更快、效果更好。在SWE-bench和Polyglot上的实验进一步证实MGM在性能、效率与泛化性上持续提升。
原文摘要 · Abstract (English)
Self-improving coding agents that iteratively rewrite their own source code have demonstrated impressive performance on coding tasks. However, existing solutions generally derive self-modification from a single failure trajectory at a time, overlooking rich comparative signals available in the agent's expanding archive of past attempts. According to Mendelian principles of controlled inheritance, we introduce Mendel Gödel Machine (MGM). In addition to the general single-trajectory clonal mutation, MGM includes two new types of self-modification that better utilizes evidences accumulated: the reaction-norm mutation edits an agent based on its trajectories on multiple tasks simultaneously, and the cross-lineage hybridization edits an agent using the trajectory of a reference agent from another lineage on the same task. Under an additive fitness landscape model, we prove theoretically and demonstrate via controlled surrogate simulation that the new strategies facilitate a faster and better convergence over single-trajectory baselines. Experiments on SWE-bench and Polyglot confirm MGM's consistent improvement in performance, efficiency, and generalizability.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。