Prospector: Improving LLM Agents with Self-Asking and Trajectory Ranking

Byoungjip Kim, Youngsoo Jang, Lajanugen Logeswaran, Geon-Hyeong Kim, Yu Jin Kim, Honglak Lee, Moontae Lee


Abstract
Large language models (LLMs) have shown the ability to solve complex decision-making tasks beyond natural language processing tasks. LLM agents based on few-shot in-context learning (ICL) achieve surprisingly high performance without training. Despite their simplicity and generalizability, ICL-based agents are limited in their ability to incorporate feedback from an environment. In this paper, we introduce Prospector, an LLM agent that consists of two complementary LLMs, an Actor and a Critic. To elicit better instruction-aligned actions from the LLM agent, we propose AskAct prompting that performs an additional self-asking step such as goal and progress checking before generating an action. Furthermore, to implicitly incorporate the environment feedback, we propose Trajectory Ranking that orders generated trajectories by predicting the expected total reward. Prospector encourages the LLM Actor to generate diverse (creative) trajectories, and harnesses the LLM Critic to select the most rewarding trajectory. On representative decision-making benchmark environments such as ALFWorld and WebShop, we empirically demonstrate that Prospector can considerably increase the success rate of given tasks, while outperforming recent advancements such as ReAct and Reflexion.
Anthology ID:
2024.findings-emnlp.879
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
14958–14976
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.879
DOI:
Bibkey:
Cite (ACL):
Byoungjip Kim, Youngsoo Jang, Lajanugen Logeswaran, Geon-Hyeong Kim, Yu Jin Kim, Honglak Lee, and Moontae Lee. 2024. Prospector: Improving LLM Agents with Self-Asking and Trajectory Ranking. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 14958–14976, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Prospector: Improving LLM Agents with Self-Asking and Trajectory Ranking (Kim et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.879.pdf