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

arXiv: https://arxiv.org/abs/2607.03766 · HTML: https://mlsanity.com/paper/2607.03766/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 14 of its 46 references that are in the map.
- First posted on arXiv 4 Jul 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)
- Synthetic data and self-improvement for LLMs / [Self-evolving LLM agents](https://mlsanity.com/synth/self-evolving-llm-agents/)

## Builds on (most cited first, 14 of 14)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [WhiteFox: White-Box Compiler Fuzzing Empowered by Large Language Models](https://mlsanity.com/paper/2310.15991/) (2023)
- [LLM-Vectorizer: LLM-based Verified Loop Vectorizer](https://mlsanity.com/paper/2406.04693/) (2024)
- [LPR: Large Language Models-Aided Program Reduction](https://mlsanity.com/paper/2312.13064/) (2023)
- [LPO: Discovering Missed Peephole Optimizations with Large Language Models](https://mlsanity.com/paper/2508.16125/) (2025)
- [FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention](https://mlsanity.com/paper/2606.09079/) (2026)
- [Interleaving Large Language Models for Compiler Testing](https://mlsanity.com/paper/2508.18955/) (2025)
- [Agentic Harness for Real-World Compilers](https://mlsanity.com/paper/2603.20075/) (2026)
- [Leveraging Large Language Models for Generalizing Peephole Optimizations](https://mlsanity.com/paper/2603.18477/) (2026)
- [Toward a Better Understanding of Probabilistic Delta Debugging](https://mlsanity.com/paper/2408.04735/) (2024)
- [WDD: Weighted Delta Debugging](https://mlsanity.com/paper/2411.19410/) (2024)

## Abstract (arXiv)

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.