外观
论文arXiv 2610.2188713 天前
MetaShare：面向开放式智能体的失败感知集体自我改进
原文链接：MetaShare: Failure-Aware Collective Self-Improvement for Open-Ended Agents（arXiv 2610.21887 · 发布日期：2026-10-15）
MetaShare: Failure-Aware Collective Self-Improvement for Open-Ended Agents
MetaShare通过记录成败修改和跨谱系检索，帮助开放式智能体避开失败路径，并在多类任务实验中验证效果。
核心要点
- 开放式自改进智能体很少复用失败尝试，搜索可能收敛到冗余策略。
- 框架记录成功与失败的智能体修改，并附带有符号性能变化。
- 检索高表现策略和高置信失败，结合审计器补足类别并降低冗余。
- 实验中位性能持平或超过 DGM-Hyperagents，并以更少迭代达到自身最佳。
验证范围与局限：验证范围为论文评审、编码、数学评分、机器人奖励设计和财务审计风险评估实验。
英文摘要 (Abstract)
Humans often learn fastest not by repeating success, but by remembering which failures not to repeat. Open-ended self-improving agents can share experience across lineages, as in GEA, or edit their own improvement mechanisms, as in DGM-Hyperagents, yet failed improvement attempts are rarely retained as reusable cross-branch knowledge, and search can collapse onto redundant strategies. We introduce MetaShare, a failure-aware framework that records successful and unsuccessful agent modifications together with signed performance deltas. Before each generation, MetaShare retrieves diverse high-performing strategies alongside high-confidence failures from other lineages, letting agents reuse effective mechanisms while avoiding known dead ends. A task-blind auditor periodically injects absent or underrepresented mechanism categories, while embedding-based de-ranking limits redundancy during retrieval. Multiple meta-agents propose modifications in parallel at heterogeneous temperatures behind a deterministic selector that gates applicability, scope, compilability, and size. Experiments across paper review, coding, math grading, robotics reward design, and financial audit-risk assessment show that MetaShare's median matches or exceeds DGM-Hyperagents' final performance and reaches its own best-performing agent in 1.7--2.9$\times$ fewer evolution iterations.
作者：Vishal Bhutani, Prasang Gupta, Sumanth Chundru, Kevin Paul
来源
本页事实对应的公开页面，以原文为准。