Graph of States: Solving Abductive Tasks with Large Language Models

TL;DR

This paper introduces Graph of States (GoS), a neuro-symbolic framework that enhances abductive reasoning in large language models by explicitly modeling logical dependencies and guiding the reasoning process.

Contribution

GoS is a novel structured framework that improves abductive reasoning in LLMs by using a causal graph and state machine for better state management and reasoning accuracy.

Findings

GoS significantly outperforms baseline methods on real-world datasets.

The framework effectively reduces Evidence Fabrication and Context Drift.

Dynamic alignment with symbolic constraints leads to more accurate abductive reasoning.

Abstract

Logical reasoning encompasses deduction, induction, and abduction. However, while Large Language Models (LLMs) have effectively mastered the former two, abductive reasoning remains significantly underexplored. Existing frameworks, predominantly designed for static deductive tasks, fail to generalize to abductive reasoning due to unstructured state representation and lack of explicit state control. Consequently, they are inevitably prone to Evidence Fabrication, Context Drift, Failed Backtracking, and Early Stopping. To bridge this gap, we introduce Graph of States (GoS), a general-purpose neuro-symbolic framework tailored for abductive tasks. GoS grounds multi-agent collaboration in a structured belief states, utilizing a causal graph to explicitly encode logical dependencies and a state machine to govern the valid transitions of the reasoning process. By dynamically aligning the reasoning focus with these symbolic constraints, our approach transforms aimless, unconstrained exploration into a convergent, directed search. Extensive evaluations on two real-world datasets demonstrate that GoS significantly outperforms all baselines, providing a robust solution for complex abductive tasks. Code repo and all prompts: https://github.com/gaorch85/Graph-of-States.