Hugging Face Papers ↗ · 2026-11-13
Self-Improvement Memory Enables Continual Recursive Self-Improvement
媒体报道 Hugging Face Papers 原文语言:中文
论文摘要(作者报告,未经本站复测):Harness optimization is often studied with a fixed policy model and benchmark.
全文
Continual recursive self-improvement lets harness optimizers reuse and revise prior edits across changing benchmarks or policy models by storing rationales, predicted and observed outcomes, and evaluation contexts in a self-improvement memory, improving final scores over continuation baselines.
正文以来源语言显示。