自我改進記憶促進持續遞歸式自我改進
Self-Improvement Memory Enables Continual Recursive Self-Improvement
研究提出自我改進記憶(SIM),記錄智能體 harness 修改所針對的問題、修改理據、預測及實際結果和評估背景,供後續持續遞歸式自我改進使用。十組配對編碼測試中,SIM 在九組取得較高分數,平均提升 2.36 分(95% CI: 1.05–3.68;p = 0.003)。研究結果不代表每次遷移都能改善表現。
We started with a practical question: after spending many rounds improving an agent’s harness, what should we carry forward when the model or benchmark changes?
The code is an obvious answer. But it often leaves out why a check was added, what a prompt change was meant to fix, or which earlier attempts failed. That history can matter when the next optimizer has to decide what to keep and what to revise.
We study Continual Recursive Self-Improvement (CRSI) and introduce Self-Improvement Memory (SIM). SIM groups harness edits by the problems they address and records their rationale, predicted and observed outcomes, and evaluation context. The components proposing and selecting edits both read this history. New attempts extend it as optimization continues, while the task-solving model’s weights stay frozen.
Our comparisons start from the same source-evolved harness, with matched target tasks, policy, optimization rounds, and candidate budgets. Across four domains, full SIM achieves higher final scores than harness-only and root-cause-only continuation in the six cross-dataset and four Opus-to-Gemini comparisons we test.
We also run ten independent coding source optimizations, each followed by paired continuations with and without SIM. SIM finishes ahead in nine pairs, with a mean gain of 2.36 score points (95% CI: 1.05–3.68; p = 0.003).
The setting requires compatible execution interfaces. Most main cross-domain comparisons use one run per condition, and matching rounds does not imply equal token or runtime cost. These results support carrying optimization history into continued search; they do not guarantee improvement on every transfer.
The images below show the idea and the coding results, including the negative pair. Happy to discuss the setup or hear how others preserve this kind of experience.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co

