Harness RSI 框架：不改模型权重，让智能体脚手架自我进化
Self-Evolving Agent Harness
一篇讲怎么让 agent 自己改 prompt、工具和工作流的论文，模型权重不动，还给了泛化界的理论证明，代码也开源了。
arXiv 论文 2610.18813 提出 Harness self-evolution（Harness RSI）：在模型权重固定的情况下，通过修订 prompt、记忆、工作流和可执行组件来持续改进智能体的软件脚手架。框架将更新目标、提议机制和准入机制分离，区分解释性状态修改与工具代码修订。理论部分用进化优化刻画搜索过程，并通过持续 PAC 学习给出期望泛化界和基于历史回归预算的保留界，以及用独立验证数据构造的高概率准入规则。论文长达 66 页，配套代码已在 GitHub 开源。
Self-Evolving Agent Harness
Harness self-evolution revises an agent's software scaffolding, including prompts, memory, workflows, and executable components, while keeping model weights fixed. We formalize a feedback-driven process in which accepted revisions persist across runs. The framework separates update targets from proposal and admission mechanisms. It distinguishes changes to interpreted state from revisions to tools and code, repository-level control logic, and plugin composition. We characterize search through evolutionary optimization and examine its reliability through continual PAC-learning. Under explicit assumptions, the analysis yields an expected generalization bound, a retention bound conditional on historical regression budgets, and a high-probability admission rule using fresh, independent validation data. We examine how persistent harness revisions affect knowledge sharing and organizational workflows, with implications for scientific reliability, physical safety, and institutional accountability. Cases from prior work illustrate model--harness co-design, distributed execution, and plugin reuse. Reliable deployment requires continual validation as task distributions and evaluators change, with independent safeguards for learning, runtime privileges, and consequential actions. We provide a comprehensive 66-page discussion of related work, theory, algorithms, evaluation, applications, and the broader impact of Harness RSI, together with continuously updated code and supplementary materials, at https://github.com/zgcagi/Harness-RSI.
