Paper ID: 2408.10455

IDEA: Enhancing the Rule Learning Ability of Large Language Model Agent through Induction, Deduction, and Abduction

Kaiyu He, Mian Zhang, Shuo Yan, Peilin Wu, Zhiyu Zoey Chen

While large language models (LLMs) have been thoroughly evaluated for deductive and inductive reasoning, their proficiency in abductive reasoning and holistic rule learning in interactive environments remains less explored. We introduce RULEARN, a novel benchmark specifically designed to assess the rule-learning abilities of LLM agents in interactive settings. In RULEARN, agents strategically interact with simulated environments to gather observations, discern patterns, and solve complex problems. To enhance the rule-learning capabilities for LLM agents, we propose IDEA, a novel reasoning framework that integrates the process of Induction, Deduction, and Abduction. The IDEA agent generates initial hypotheses from limited observations through abduction, devises plans to validate these hypotheses or leverages them to solve problems via deduction, and refines previous hypotheses using patterns identified from new observations through induction, dynamically establishing and applying rules that mimic human rule-learning behaviors. Our evaluation of the IDEA framework, which involves five representative LLMs, demonstrates significant improvements over the baseline. Furthermore, within this framework, our comparison with 50 human participants reveals notable discrepancies in rule-learning behaviors. LLM agents tend to generate plausible initial hypotheses but struggle to refine them through interaction. Conversely, humans, despite sometimes overlooking initial details, excel at incorporating feedback and continuously improving their hypotheses. We believe our benchmark, RULEARN, will serve as a valuable and challenging resource, and that the IDEA framework will provide crucial insights for the development of LLM agents capable of human-like rule learning in real-world scenarios. We will release our code and data upon acceptance of the paper.

Submitted: Aug 19, 2024