Combining LLMs with Logic-Based Framework to Explain MCTS

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: An, Ziyan, Wang, Xia, Baier, Hendrik, Chen, Zirong, Dubey, Abhishek, Johnson, Taylor T., Sprinkle, Jonathan, Mukhopadhyay, Ayan, Ma, Meiyi
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910924817825792
author An, Ziyan
Wang, Xia
Baier, Hendrik
Chen, Zirong
Dubey, Abhishek
Johnson, Taylor T.
Sprinkle, Jonathan
Mukhopadhyay, Ayan
Ma, Meiyi
author_facet An, Ziyan
Wang, Xia
Baier, Hendrik
Chen, Zirong
Dubey, Abhishek
Johnson, Taylor T.
Sprinkle, Jonathan
Mukhopadhyay, Ayan
Ma, Meiyi
contents In response to the lack of trust in Artificial Intelligence (AI) for sequential planning, we design a Computational Tree Logic-guided large language model (LLM)-based natural language explanation framework designed for the Monte Carlo Tree Search (MCTS) algorithm. MCTS is often considered challenging to interpret due to the complexity of its search trees, but our framework is flexible enough to handle a wide range of free-form post-hoc queries and knowledge-based inquiries centered around MCTS and the Markov Decision Process (MDP) of the application domain. By transforming user queries into logic and variable statements, our framework ensures that the evidence obtained from the search tree remains factually consistent with the underlying environmental dynamics and any constraints in the actual stochastic control process. We evaluate the framework rigorously through quantitative assessments, where it demonstrates strong performance in terms of accuracy and factual consistency.
format Preprint
id arxiv_https___arxiv_org_abs_2505_00610
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Combining LLMs with Logic-Based Framework to Explain MCTS
An, Ziyan
Wang, Xia
Baier, Hendrik
Chen, Zirong
Dubey, Abhishek
Johnson, Taylor T.
Sprinkle, Jonathan
Mukhopadhyay, Ayan
Ma, Meiyi
Artificial Intelligence
In response to the lack of trust in Artificial Intelligence (AI) for sequential planning, we design a Computational Tree Logic-guided large language model (LLM)-based natural language explanation framework designed for the Monte Carlo Tree Search (MCTS) algorithm. MCTS is often considered challenging to interpret due to the complexity of its search trees, but our framework is flexible enough to handle a wide range of free-form post-hoc queries and knowledge-based inquiries centered around MCTS and the Markov Decision Process (MDP) of the application domain. By transforming user queries into logic and variable statements, our framework ensures that the evidence obtained from the search tree remains factually consistent with the underlying environmental dynamics and any constraints in the actual stochastic control process. We evaluate the framework rigorously through quantitative assessments, where it demonstrates strong performance in terms of accuracy and factual consistency.
title Combining LLMs with Logic-Based Framework to Explain MCTS
topic Artificial Intelligence
url https://arxiv.org/abs/2505.00610