LLM-Guided Monte Carlo Tree Search over Knowledge Graphs: Composing Mechanistic Explanations for Drug-Disease Pairs

TL;DR

This paper introduces TESSERA, a neuro-symbolic framework combining LLMs, knowledge graphs, and MCTS to generate multi-step mechanistic explanations for drug-disease pairs, addressing challenges in combinatorial reasoning.

Contribution

The paper presents a novel neuro-symbolic approach that leverages LLMs for local judgments within a structured search over knowledge graphs, improving multi-step explanation generation.

Findings

TESSERA accurately elucidates drug mechanisms consistent with curated biology.

Both LLM components significantly contribute to the framework's performance.

The approach surfaces coherent alternative mechanisms in complex biological reasoning.

Abstract

Extracting multi-step explanations from knowledge graphs poses a combinatorial challenge requiring both heuristic guidance (as candidates proliferate with depth) and credit assignment (as path quality emerges over extended sequences). Frontier LLMs, strong on knowledge/reasoning benchmarks, offer a compelling source of such heuristics, yet their knowledge comes sans guarantees and compositional performance degrades as chains lengthen. We thus present TESSERA, a 3-part neuro-symbolic framework that uses LLMs in a circumscribed role: for local discriminative judgement rather than autonomous multi-step generation; the knowledge graph then defines the hypothesis space enforcing hard structural constraints, and MCTS coordinates the long-horizon search with principled credit assignment via backpropagation. LLMs perform dual roles as a prior policy biasing exploration and a comparative state evaluator supplying reward signals. Evaluation on drug mechanism elucidation across two complementary knowledge graphs demonstrates fidelity to curated biology while surfacing coherent alternative mechanisms, with ablations confirming discriminative contribution from both LLM components. Beyond its current application, our framework offers a general paradigm for compositional reasoning over structured knowledge.