LLMs as ASP Programmers: Self-Correction Enables Task-Agnostic Nonmonotonic Reasoning
For AI researchers, this work provides a task-agnostic neuro-symbolic method for nonmonotonic reasoning that eliminates per-task engineering, though it is incremental over prior LLM+ASP approaches.
LLMs struggle with high computational costs, logical inconsistencies, and performance degradation on complex problems. The proposed LLM+ASP framework uses Answer Set Programming with a self-correction loop to achieve task-agnostic nonmonotonic reasoning, outperforming SMT-based alternatives by significant margins on nonmonotonic tasks.
Recent large language models (LLMs) have achieved impressive reasoning milestones but continue to struggle with high computational costs, logical inconsistencies, and sharp performance degradation on high-complexity problems. While neuro-symbolic methods attempt to mitigate these issues by coupling LLMs with symbolic reasoners, existing approaches typically rely on monotonic logics (e.g., SMT) that cannot represent defeasible reasoning -- essential components of human cognition. We present "LLM+ASP," a framework that translates natural language into Answer Set Programming (ASP), a nonmonotonic formalism based on stable model semantics. Unlike prior "LLM+ASP" approaches that require manually authored knowledge modules, domain-specific prompts, or evaluation restricted to single problem classes, our framework operates without any per-task engineering and applies uniformly across diverse reasoning tasks. Our system utilizes an automated self-correction loop where structured feedback from the ASP solver enables iterative refinement. Evaluating across six diverse benchmarks, we demonstrate that: (1) stable model semantics allow LLMs to naturally express default rules and exceptions, outperforming SMT-based alternatives by significant margins on nonmonotonic tasks; (2) iterative self-correction is the primary driver of performance, effectively replacing the need for handcrafted domain knowledge; (3) compact in-context reference guides substantially outperform verbose documentation, revealing a "context rot" phenomenon where excessive context hinders constraint adherence.