Saved in:
Bibliographic Details
Main Authors: Lu, Siqi, Bahavarnia, Mirsaleh, Baroud, Hiba, Zhang, Yixuan, Purohit, Hemant, Mukhopadhyay, Ayan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.16524
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914581289369600
author Lu, Siqi
Bahavarnia, Mirsaleh
Baroud, Hiba
Zhang, Yixuan
Purohit, Hemant
Mukhopadhyay, Ayan
author_facet Lu, Siqi
Bahavarnia, Mirsaleh
Baroud, Hiba
Zhang, Yixuan
Purohit, Hemant
Mukhopadhyay, Ayan
contents Probabilistic search algorithms, such as Monte Carlo Tree Search (MCTS), have proven very effective in solving sequential decision-making tasks under uncertainty. However, interpreting asymmetric search trees that incorporate bandit-based tree traversal and simulation-based value estimation is difficult for end users based solely on raw tree statistics. While prior work requires hand-crafted formal logic constraints that must be updated when the problem changes, we present a framework that enables large language models (LLMs) to generate evidence-grounded explanations of MCTS decisions from recorded search traces in an end-to-end manner. Our framework maps natural-language questions to a structured set of intent categories, determines whether the existing tree contains sufficient evidence, triggers targeted expansion when needed, and generates explanations using tree statistics such as visit counts, value estimates, and risk information. Experimental results provide the first evidence that LLMs can serve as end-to-end explainers for probabilistic search, without requiring intermediate formal representations.
format Preprint
id arxiv_https___arxiv_org_abs_2605_16524
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Toward Template-Free Explainability for Monte Carlo Tree Search
Lu, Siqi
Bahavarnia, Mirsaleh
Baroud, Hiba
Zhang, Yixuan
Purohit, Hemant
Mukhopadhyay, Ayan
Human-Computer Interaction
Artificial Intelligence
Probabilistic search algorithms, such as Monte Carlo Tree Search (MCTS), have proven very effective in solving sequential decision-making tasks under uncertainty. However, interpreting asymmetric search trees that incorporate bandit-based tree traversal and simulation-based value estimation is difficult for end users based solely on raw tree statistics. While prior work requires hand-crafted formal logic constraints that must be updated when the problem changes, we present a framework that enables large language models (LLMs) to generate evidence-grounded explanations of MCTS decisions from recorded search traces in an end-to-end manner. Our framework maps natural-language questions to a structured set of intent categories, determines whether the existing tree contains sufficient evidence, triggers targeted expansion when needed, and generates explanations using tree statistics such as visit counts, value estimates, and risk information. Experimental results provide the first evidence that LLMs can serve as end-to-end explainers for probabilistic search, without requiring intermediate formal representations.
title Toward Template-Free Explainability for Monte Carlo Tree Search
topic Human-Computer Interaction
Artificial Intelligence
url https://arxiv.org/abs/2605.16524