言語モデルは環境フィードバックから記号プランナーの行動意味論を推論できる
Language Models can Infer Action Semantics for Symbolic Planners from Environment Feedback
LLMと記号プランナーを組み合わせ、環境からの実行結果を基に行動の意味論を自動学習するPSALMを提案。7環境で成功率を36.4%から100%に向上させた。
著者: Wang Zhu, Ishika Singh, Robin Jia, Jesse Thomason
分類: cs.AI, cs.CL, cs.RO
原文アブストラクト
Symbolic planners can discover a sequence of actions from initial to goal states given expert-defined, domain-specific logical action semantics. Large Language Models (LLMs) can directly generate such sequences, but limitations in reasoning and state-tracking often result in plans that are insufficient or unexecutable. We propose Predicting Semantics of Actions with Language Models (PSALM), which automatically learns action semantics by leveraging the strengths of both symbolic planners and LLMs. PSALM repeatedly proposes and executes plans, using the LLM to partially generate plans and to infer domain-specific action semantics based on execution outcomes. PSALM maintains a belief over possible action semantics that is iteratively updated until a goal state is reached. Experiments on 7 environments show that when learning just from one goal, PSALM boosts plan success rate from 36.4% (on Claude-3.5) to 100%, and explores the environment more efficiently than prior work to infer ground truth domain action semantics.
