Fact-Augmented Lookahead Planning for LLM Agents
面向LLM智能体的事实增强前瞻规划
机构 * University of Cambridge(剑桥大学)
AI总结 提出LWM-Planner框架,通过从轨迹中提取关键事实并用于条件化动作提议、世界模型模拟和状态值估计,实现无需参数更新的在线规划改进,在多个环境上优于ReAct/Reflexion和纯搜索基线。
Comments Accepted at the 29th International Conference on Artificial Intelligence and Statistics (AISTATS 2026). Camera-ready version. 9-page main text plus appendices (63 pages total), 1 figure