English(EN) Self-Improving Agents with World Model Predictive Paths

新框架通过预测路径和自我改进增强 LLM 代理

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-23 04:00

研究人员开发了一种用于大型语言模型 (LLM) 代理的新颖框架，该框架通过结合预测分析和基于经验的适应来增强其决策能力。这种受模型预测路径积分 (MPPI) 控制启发的方法允许代理在执行前使用世界模型模拟多种行动结果，并评估它们在任务进展和风险方面的表现。该系统还包含一个双分支经验记忆，以促进自我改进，同时改进候选生成和下一观测预测。在 ALFWorld 和 ScienceWorld 基准上进行的实验证明了该方法在不同 LLM 主干上的有效性。 AI

影响该框架可能带来更强大、更适应现实世界环境并能在其中学习和改进的 AI 代理。

排序理由详细介绍 AI 代理新方法的学术论文。[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 →

本文如何被排名

Signal score: 5 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍 AI 代理新方法的学术论文。[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; 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: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Haori Lu, Tianyu Gao, Yaoyao Liu, Yingying Li · 2026-10-23 04:00

Self-Improving Agents with World Model Predictive Paths

arXiv:2610.28945v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly expected to interact with environments and improve their decisions during deployment. However, how anticipating future outcomes and drawing on accumulated interaction experience can…

本文如何被排名

报道来源 [1]

Self-Improving Agents with World Model Predictive Paths

相关实体

相关话题