GraphThink: グラフ強化LLM思考による長期的身体性タスク計画
GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning
LLMベースの身体性エージェントの計画における幻覚や長期タスクへの汎化不足を解決するため、タスクグラフとシーングラフを統合したフレームワークを提案。ALFREDベンチマークで最先端性能を達成した。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Chen Li, Sijie Cheng, Yuelin Zhang, Junxi Li, Maozhi Huang, Yang Liu, Wenbing Huang
分類: cs.AI, cs.RO
原文アブストラクト
Embodied agents using LLM-based planners often struggle with physical hallucinations, poor generalization to long-horizon tasks, and lack of environmental awareness. We propose GraphThink, a novel framework that integrates a task graph to provide structured knowledge for robust planning and a scene graph to maintain environmental memory for event-driven replanning. Specifically, the task graph guides LLM thinking through contextual prompting and iterative refinement, effectively mitigating planning hallucinations. Furthermore, within the GRPO framework, the task graph offers delicate reward design to train the LLM planner, enhancing long-horizon planning capabilities and improving generalization. Finally, an event-driven replanning module, powered by the scene graph, enables closed-loop environment awareness and error correction. GraphThink achieves state-of-the-art performance on the ALFRED benchmark. In particular, our high-level planner surpasses leading API-based LLMs on both the validation set and held-out long-horizon tasks, underscoring its robust zero-shot and few-shot capabilities. Additional evaluations further demonstrate strong out-of-distribution generalization to novel tasks and environments.
