PulseAugur
实时 08:32:49
English(EN) Improving Language Agents through BREW: Bootstrapping expeRientially-learned Environmental knoWledge

新的BREW框架使LLM代理能够从经验中学习

研究人员开发了BREW,这是一个新颖的框架,旨在使基于大型语言模型(LLM)的代理能够从过去的经验中学习。与每次会话都重新开始学习的当前代理不同,BREW将交互轨迹提炼成结构化的自然语言食谱知识库。该知识库捕获有关任务执行、适用性和潜在陷阱的基本信息。该系统利用扩展和收集蒙特卡洛树搜索算法来高效地构建和检索知识,并结合了事后重新标记,将不成功的尝试转化为学习机会。在OSWorld和tau^2-Bench等基准测试的评估中,与基线代理和现有的内存增强系统相比,BREW在任务成功率方面取得了显著的改进,并减少了执行步骤。 AI

影响 该框架通过使AI代理能够保留和利用过去的学习成果,有可能显著提高其效率和能力。

排序理由 该集群包含一篇详细介绍LLM代理新框架的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

新的BREW框架使LLM代理能够从经验中学习

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群包含一篇详细介绍LLM代理新框架的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, model release, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
52 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准

报道来源 [1]

  1. arXiv cs.AI TIER_1 English(EN) · Shashank Kirtania, Param Biyani, Priyanshu Gupta, Yasharth Bajpai, Roshni Iyer, Sumit Gulwani, Gustavo Soares ·

    通过BREW:引导式指数学习环境知识来改进语言代理

    arXiv:2511.20297v2 Announce Type: replace Abstract: Large Language Model (LLM)-based agents are increasingly capable of complex, multi-step tasks such as GUI automation, tool use, and data manipulation, yet they cannot learn from experience: each new session rediscovers solutions…