Tag
该论文提出通过学习索引策略（indexical policies）形式的搜索控制，使规划搜索在多项式空间内完成，代价是时间仅随选择深度指数增长；结合语言模型的反例引导学习循环，在IPC 2023学习赛道等基准上解决了1,709/1,890个测试任务，优于LAMA、BFWS和Levitron。
This paper introduces an approach for automatically generating generalized plans in Lean with formal proofs of completeness using LLMs, evaluated on benchmark domains showing significant advancements in automatic plan verification.
This paper investigates coding agents for automated generalized task and motion planning, showing they outperform traditional methods with higher success rates and efficiency in simulated environments.
This paper introduces HCL-GP, a dynamic policy-learning framework that integrates generalized planning and hierarchical task decomposition to enable LLM-based agents to learn and reuse executable policy components, significantly improving performance on the AppWorld benchmark.