跳到正文
实时
Hugging Face Daily Papers·· 22 小时前65

Self-Improvement Memory 推出持续递归自我改进技术

Self-Improvement Memory Enables Continual Recursive Self-Improvement

要点速览

自我改进记忆 (SIM) 通过记录优化历史,在持续递归自我改进 (CRSI) 中提升性能。在四个领域的六次跨数据集和四次 Opus-to-Gemini 比较中,完整 SIM 比仅使用 harness 或 root-cause 的延续方法得分更高,十次独立编码优化中 SIM 在九次对比较中胜出,平均提升 2.36 分 (p=0.003)。该设置要求兼容执行接口。

正文

Author affiliations (as listed in the paper): Google Cloud AI · Google DeepMind · Google Cloud AI Research · The Pennsylvania State University.

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.

📄 https://arxiv.org/abs/2611.18856

SIM-X-visual-v2
03-paired-results

来源: Hugging Face Daily Papers · huggingface.co