Abstract
Recent large language models (LLMs) are promising for making decisions in grounded environments. However, LLMs frequently fail in complex decision-making tasks due to the misalignment between the pre-trained knowledge in LLMs and the actual rules in the environment. Existing methods require either costly gradient computation or lengthy in-context demonstrations. In this paper, we propose AutoPlan, an approach to guide LLM-based agents to accomplish interactive decision-making tasks. AutoPlan augments the LLM prompt with a task-solving plan and optimizes it through iterative experience collection and reflection. Our experiments show that AutoPlan, though using no in-context demonstrations, achieves success rates on par with the baselines using human-written demonstrations on ALFWorld and even outperforms them by 8% on HotpotQA. The code is available at https://github.com/owaski/AutoPlan.- Anthology ID:
- 2023.findings-emnlp.205
- Original:
- 2023.findings-emnlp.205v1
- Version 2:
- 2023.findings-emnlp.205v2
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2023
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3114–3128
- Language:
- URL:
- https://aclanthology.org/2023.findings-emnlp.205
- DOI:
- 10.18653/v1/2023.findings-emnlp.205
- Cite (ACL):
- Siqi Ouyang and Lei Li. 2023. AutoPlan: Automatic Planning of Interactive Decision-Making Tasks With Large Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 3114–3128, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- AutoPlan: Automatic Planning of Interactive Decision-Making Tasks With Large Language Models (Ouyang & Li, Findings 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2023.findings-emnlp.205.pdf