孟德尔·哥德尔机器：通过比较进化实现递归自改进编码智能体

摘要

自我改进的编码智能体通过迭代式地重写自身源代码，已在编码任务上展现出令人瞩目的性能。然而，现有方案通常每次仅从单条失败轨迹中推导自我修改，忽视了智能体不断扩展的过往尝试档案中丰富的比较信号。根据孟德尔受控遗传原理，我们提出了孟德尔-哥德尔机（MGM）。除了常见的单轨迹克隆突变外，MGM 还引入了两种能够更好利用累积证据的新型自我修改方式：反应规范突变基于智能体在多个任务上的轨迹同时对其进行修改；跨谱系杂交则利用同一任务上另一谱系参考智能体的轨迹来修改智能体。在加性适应度景观模型下，我们从理论上证明并通过受控替代仿真演示，相较于单轨迹基线，新策略能够实现更快、更好的收敛。在 SWE-bench 和 Polyglot 上的实验证实，MGM 在性能、效率和泛化能力上均有持续提升。

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.