Graph of States: Solving Abductive Tasks with Large Language Models

2026-03-22

AI Summary

Large language models often struggle with abductive reasoning due to the absence of structured state representations and explicit control mechanisms, leading to issues such as hallucinated evidence, contextual drift, and failed backtracking. To address these challenges, this work proposes the first neuro-symbolic framework specifically designed for abductive tasks. The approach constructs a structured belief-state graph to encode causal dependencies and integrates a finite state machine to guide valid state transitions, thereby enabling controlled, backtrackable, and focused multi-agent collaborative reasoning. Evaluated on two real-world datasets, the method significantly outperforms existing baselines, achieving substantial improvements in both accuracy and robustness on complex abductive reasoning tasks.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Machine Learning: Neuro-Symbolic Learning
• Reasoning under Uncertainty: Other Foundations of Reasoning under Uncertainty

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

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://anonymous.4open.science/r/Graph-of-States-5B4E.

Problem

• abductive reasoning
• Large Language Models
• state representation
• reasoning control
• evidence fabrication

Innovation

• Graph of States
• abductive reasoning
• neuro-symbolic framework
• causal graph
• state machine