Semantic-aware and Self-improving Program Reduction via Agentic Large Language Models

2026-07-04

AI Summary

This work proposes a novel paradigm for program reduction based on a dual-agent large language model framework, reframing reduction as an autonomous reasoning task. Unlike conventional approaches that rely on predefined rules and lack semantic understanding or learning capabilities, the proposed method employs one agent to analyze program semantics and generate reduction hypotheses, while a second agent iteratively refines these hypotheses through execution feedback. The system further leverages knowledge distillation to extract transferable strategies, enabling continual self-improvement. By uniquely integrating semantic awareness with experience-driven learning, the approach significantly outperforms state-of-the-art tools across 90 benchmarks spanning three programming languages, consistently producing smaller and more efficient reduced programs.

Abstract

Reducing bug-triggering programs to their minimal essential form is a fundamental task in debugging language processors such as compilers and interpreters. Existing reduction techniques are limited by their reliance on predefined, syntax-driven transformations that lack semantic understanding of the target program, and by their inability to learn from past reduction experiences. We present a new approach that recasts program reduction as an autonomous reasoning task powered by agentic Large Language Models (LLMs). Instead of applying fixed transformation rules, our method enables an LLM to analyze program semantics, formulate reduction hypotheses, and iteratively refine its approach based on execution outcomes. Successful reduction experiences are further distilled into reusable strategies, allowing the system to continuously improve over time. We realize this approach in PROJ, a framework built around two collaborative components: a reducer agent that performs semantic-aware, case-specific program reduction, and a reflector agent that extracts and accumulates transferable reduction knowledge. Extensive experiments on 90 benchmarks spanning three programming languages show that PROJ consistently produces smaller reduced programs than all existing state-of-the-art reducers while maintaining high efficiency.

Problem

• program reduction
• semantic understanding
• debugging
• language processors
• reduction experience

Innovation

• agentic LLMs
• program reduction
• semantic-aware
• self-improving
• autonomous reasoning