Self-Improvement Memory Enables Continual Recursive Self-Improvement
Xin Yu, Fei Xia, Jiaqi Pan, Youbao Tang, Chengzhi Liu, Adams Yu, Sicong Jiang, Yanfei Chen, Lingzhou Xue, Ting Yu
Self-Improvement Memory Enables Continual Recursive Self-Improvement: 31 upvotes on Hugging Face Daily Papers, #7 of 39 papers on 2026-11-18. Day-by-day upvote history.
Upvotes over time
It had 30 upvotes by its first day, 31 upvotes by the next day, 31 upvotes by day 3, 31 upvotes by day 7, and has 31 now. It ranked #20 of 146 papers in its week and #97 of 520 in its month.
Harness optimization is often studied with a fixed policy model and benchmark. When either changes, the optimizer must decide which parts of an evolved harness to reuse or revise, but the harness alone may not explain why earlier edits were made or how they performed. In this work, we study Continual Recursive Self-Improvement (CRSI), a setting for continuing existing harness-optimization methods across compatible benchmarks or policy models. We propose Self-Improvement Memory (SIM) for the harness optimizer, rather than the task-solving policy. SIM groups edits by recurring harness problem and records their rationale, predicted and observed outcomes, and evaluation context. New attempts extend this history as optimization continues. In our experiments across four domains, SIM achieves higher final scores than harness-only and root-cause-only continuation in cross-dataset and pairwise cross-model comparisons. Across ten independent source runs in coding, paired continuations with SIM improve final scores by an average of 2.36 points over harness-only continuation (p=0.003).
Paper page on Hugging Face · arXiv
Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.