发现信息
- 作者:Changzhi Liu, Yilun Liu, Sikuan Yan, Volker Tresp C, Yunpu Ma
- 年份:2026
- 发表源:arXiv (Cornell University)
- OpenAlex ID:https://openalex.org/W7202216379
- DOI:https://doi.org/10.48550/arxiv.2608.07645
- arXiv:2608.07645
- 检索主题:code-evolution
- OpenAlex 引用数快照:9(2026-11-12)
摘要线索
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.
核验与筛选
- 当前状态:待筛选、去重和一手来源核验。
- OpenAlex 元数据和引用数只用于发现,不作为正式引文或质量判断。
- 记录正式版本、venue、方法细节、实验协议和局限后,才迁入稳定论文卡片。