Skill Learning Using Process Mining for Large Language Model Plan Generation
This addresses efficiency and interpretability challenges in LLM-based automation and decision-making, but appears incremental as it builds on existing process mining methods.
The paper tackles the problem of limited effectiveness in large language model plan generation due to sequential execution and skill retrieval issues by integrating process mining techniques, resulting in a skill retrieval method that surpasses state-of-the-art accuracy baselines under specific conditions.
Large language models (LLMs) hold promise for generating plans for complex tasks, but their effectiveness is limited by sequential execution, lack of control flow models, and difficulties in skill retrieval. Addressing these issues is crucial for improving the efficiency and interpretability of plan generation as LLMs become more central to automation and decision-making. We introduce a novel approach to skill learning in LLMs by integrating process mining techniques, leveraging process discovery for skill acquisition, process models for skill storage, and conformance checking for skill retrieval. Our methods enhance text-based plan generation by enabling flexible skill discovery, parallel execution, and improved interpretability. Experimental results suggest the effectiveness of our approach, with our skill retrieval method surpassing state-of-the-art accuracy baselines under specific conditions.