Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2509.09790 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912584532230144 |
|---|---|
| author | Li, Yuxuan Zhong, Victor |
| author_facet | Li, Yuxuan Zhong, Victor |
| contents | Learning to plan in grounded environments typically requires carefully designed reward functions or high-quality annotated demonstrations. Recent works show that pretrained foundation models, such as large language models (LLMs) and vision language models (VLMs), capture background knowledge helpful for planning, which reduces the amount of reward design and demonstrations needed for policy learning. We evaluate how well LLMs and VLMs provide feedback across symbolic, language, and continuous control environments. We consider prominent types of feedback for planning including binary feedback, preference feedback, action advising, goal advising, and delta action feedback. We also consider inference methods that impact feedback performance, including in-context learning, chain-of-thought, and access to environment dynamics. We find that foundation models can provide diverse high-quality feedback across domains. Moreover, larger and reasoning models consistently provide more accurate feedback, exhibit less bias, and benefit more from enhanced inference methods. Finally, feedback quality degrades for environments with complex dynamics or continuous state spaces and action spaces. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_09790 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | How well can LLMs provide planning feedback in grounded environments? Li, Yuxuan Zhong, Victor Artificial Intelligence Learning to plan in grounded environments typically requires carefully designed reward functions or high-quality annotated demonstrations. Recent works show that pretrained foundation models, such as large language models (LLMs) and vision language models (VLMs), capture background knowledge helpful for planning, which reduces the amount of reward design and demonstrations needed for policy learning. We evaluate how well LLMs and VLMs provide feedback across symbolic, language, and continuous control environments. We consider prominent types of feedback for planning including binary feedback, preference feedback, action advising, goal advising, and delta action feedback. We also consider inference methods that impact feedback performance, including in-context learning, chain-of-thought, and access to environment dynamics. We find that foundation models can provide diverse high-quality feedback across domains. Moreover, larger and reasoning models consistently provide more accurate feedback, exhibit less bias, and benefit more from enhanced inference methods. Finally, feedback quality degrades for environments with complex dynamics or continuous state spaces and action spaces. |
| title | How well can LLMs provide planning feedback in grounded environments? |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2509.09790 |