Primary sourcearXiv cs.AI
View sourceEvent ·Single source
ReGE框架:让智能体用自身执行记录合成经验指南
ReGE是一个把智能体历史执行记录转化为可复用经验指南的框架,其主实现ReGE-Syn只需一次coach调用即可完成记录与工件的综合,无需参数更新或更强的teacher模型。在四个基准上,ReGE让GPT平均提升9.9个百分点、Claude提升8.8个百分点。与AggAgent相比,ReGE-Syn在BrowseComp-Plus匹配子集上将GPT的指南构建token减少98.2%、Claude减少95.5%。作者称该方法可用于低成本整合并行智能体系统(如agent swarm)的执行记录。
Current read
一个很实用的agent框架:不用微调模型,只靠历史记录生成指南,GPT和Claude都能白拿近10个点的准确率提升。
2 sources38° AI heatLast updated 2026/10/24 19:05:57
Evidence
2 sourcesRelated source 1marktechpost
View sourceConflict check
Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.