具有任意时间有效证书的自我进化智能体
Self-Evolving Agents with Anytime-Valid Certificates
AI总结:
提出SEA架构,通过冻结基础模型和任意时间有效门控机制,在固定错误预算内实现可控自我修改,在SWE-bench验证集上提升性能并防止退化。
摘要:
自我进化智能体违反了大多数学习理论保证背后的假设:数据、评估器、组件和假设空间都是由正在更新的策略产生的。我们提出了\textbf{SEA},一种将自我修改限制在小型转向适配器和围绕\textit{冻结}基础模型的版本化框架中的架构,并且每次修改仅通过一个任意时间有效的门控,该门控针对固定错误预算发出可审计的证书。五个循环控制器组合了已发布的保证;由于此类门控只能\textit{选择}冻结基础模型已经产生的行为,五个验证器在环机制——最佳-$N$、微步搜索、自我生成复制预言机、搜索层控制和自我修复——提供了门控所需的密集、无评分器信号,仅从问题文本计算得出。在四个基础模型上的$52$实例SWE-bench验证子集上,基础能力是主导的、无混杂效应,并且在两个强基础模型上,一个精心设计的无操作复合控制隔离了该套件的贡献,分别为$+4$和$+5$(\textsc{Glm}~5.2 $24\to28$;\textsc{Gpt} $29\to34$,即$65\%$最佳),事件日志确认其机制触发并防止了退化。结果基于昂贵评估的单次运行;确认运行间方差和调整每任务算法组合是未来的工作。
英文摘要:
Self-evolving agents violate the assumption behind most learning-theoretic guarantees: the data, evaluator, components, and hypothesis space are produced by the policy being updated. We present \textbf{SEA}, an architecture that confines self-modification to a small steering adapter and a versioned harness around a \emph{frozen} base model and admits each modification only through an anytime-valid gate that emits an auditable certificate against a fixed error budget. Five loop controllers compose published guarantees; because such gates can only \emph{select} among behaviors the frozen base already produces, five verifier-in-the-loop mechanisms -- best-of-$N$, micro-step search, self-authored reproduction oracles, search-layer control, and self-repair -- supply the dense, grader-free signal the gates require, computed from the issue text alone. On a $52$-instance SWE-bench Verified subset across four base models, base capability is the dominant, confound-free effect, and on two strong base models a deliberate no-op-composite control isolates the suite's contribution at $+4$ and $+5$ (\textsc{Glm}~5.2 $24\to28$; \textsc{Gpt} $29\to34$, the $65\%$ best), with event logs confirming that its mechanisms fire and prevent regressions. Results are single-run on expensive evaluations; confirming run-to-run variance and adapting the per-task algorithm mix are future work.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。