孟德爾-哥德爾機器：透過比較演化實現遞迴自我改進的程式設計智能體

摘要

自我改進的編碼智能體透過迭代重寫自身原始碼，已在編碼任務上展現出令人矚目的表現。然而，現有解決方案通常一次僅從單一失敗軌跡推導自我修改，忽略了智能體不斷擴充的過往嘗試存檔中可用的豐富比較訊號。根據孟德爾受控遺傳原理，我們提出了孟德爾·哥德爾機器（MGM）。除了通用的單軌跡克隆突變之外，MGM 還包含兩種類型的自我修改，以更好地利用累積的證據：反應規範突變根據智能體在多個任務上的軌跡同時對其進行編輯，而跨譜系雜交則利用來自另一譜系的參考智能體在同一任務上的軌跡來編輯智能體。在加性適應度景觀模型下，我們從理論上證明並透過受控代理模擬展示，新策略相較於單軌跡基線能促進更快且更好的收斂。在 SWE-bench 和 Polyglot 上的實驗確認了 MGM 在效能、效率和泛化能力上的一致提升。

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.