# REAgent: Requirement-Driven LLM Agents for Software Issue Resolution

arXiv: https://arxiv.org/abs/2604.06861 · HTML: https://mlsanity.com/paper/2604.06861/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 28 of its 87 references that are in the map.
- First posted on arXiv 8 Apr 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 28 of 28)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?](https://mlsanity.com/paper/2509.16941/) (2025)
- [The Impact of AI on Developer Productivity: Evidence from GitHub Copilot](https://mlsanity.com/paper/2302.06590/) (2023)
- [SWE-Bench+: Enhanced Coding Benchmark for LLMs](https://mlsanity.com/paper/2410.06992/) (2024)
- [Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling](https://mlsanity.com/paper/2507.23370/) (2025)
- [CodeR: Issue Resolving with Multi-Agent and Task Graphs](https://mlsanity.com/paper/2406.01304/) (2024)
- [RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph](https://mlsanity.com/paper/2410.14684/) (2024)
- [SpecRover: Code Intent Extraction via LLMs](https://mlsanity.com/paper/2408.02232/) (2024)
- [The Complexity Trap: Simple Observation Masking Is as Efficient as LLM Summarization for Agent Context Management](https://mlsanity.com/paper/2508.21433/) (2025)
- [RepoFusion: Training Code Models to Understand Your Repository](https://mlsanity.com/paper/2306.10998/) (2023)
- [MARE: Multi-Agents Collaboration Framework for Requirements Engineering](https://mlsanity.com/paper/2405.03256/) (2024)
- [An Empirical Study on LLM-based Agents for Automated Bug Fixing](https://mlsanity.com/paper/2411.10213/) (2024)
- [Revisit Self-Debugging with Self-Generated Tests for Code Generation](https://mlsanity.com/paper/2501.12793/) (2025)
- [BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?](https://mlsanity.com/paper/2603.03194/) (2026)
- [What Do Users Ask in Open-Source AI Repositories? An Empirical Study of GitHub Issues](https://mlsanity.com/paper/2303.09795/) (2023)
- [Aligning Requirement for Large Language Model's Code Generation](https://mlsanity.com/paper/2509.01313/) (2025)
- [TDFlow: Agentic Workflows for Test Driven Development](https://mlsanity.com/paper/2510.23761/) (2025)
- [Investigating Bias: A Multilingual Pipeline for Generating, Solving, and Evaluating Math Problems with LLMs](https://mlsanity.com/paper/2509.17701/) (2025)
- [CodeScout: Contextual Problem Statement Enhancement for Software Agents](https://mlsanity.com/paper/2603.05744/) (2026)
- [On the Effectiveness of Training Data Optimization for LLM-based Code Generation: An Empirical Study](https://mlsanity.com/paper/2512.24570/) (2025)
- [Challenges and Practices in Aligning Requirements with Verification and Validation: A Case Study of Six Companies](https://mlsanity.com/paper/2307.12489/) (2023)

## Built on by (most cited first, 4 of 4)

- [An Interactive Agent for Requirement-Driven Candidate Sourcing](https://mlsanity.com/paper/2608.23501/) (2026)
- [PYTHALAB-MERA: Validation-Grounded Memory, Retrieval, and Acceptance Control for Frozen-LLM Coding Agents](https://mlsanity.com/paper/2605.08468/) (2026)
- [You Know What I Mean: A Benchmark for Agentic Conversational Reference Grounding](https://mlsanity.com/paper/2608.29834/) (2026)
- [WiseSpec: Requirements-Driven Agents for Code Generation](https://mlsanity.com/paper/2609.00568/) (2026)

## Abstract (arXiv)

Issue resolution aims to automatically generate patches from given issue descriptions and has attracted significant attention with the rapid advancement of large language models (LLMs). However, due to the complexity of software issues and codebases, LLM-generated patches often fail to resolve corresponding issues. Although various advanced techniques have been proposed with carefully designed tools and workflows, they typically treat issue descriptions as direct inputs and largely overlook their quality (e.g., missing critical context or containing ambiguous information), which hinders LLMs from accurate understanding and resolution. To address this limitation, we draw on principles from software requirements engineering and propose REAgent, a requirement-driven LLM agent framework that introduces issue-oriented requirements as structured task specifications to better guide patch generation. Specifically, REAgent automatically constructs structured and information-rich issue-oriented requirements, identifies low-quality requirements, and iteratively refines them to improve patch correctness. We conduct comprehensive experiments on three widely used benchmarks using two advanced LLMs, comparing against five representative or state-of-the-art baselines. The results demonstrate that REAgent consistently outperforms all baselines, achieving an average improvement of 17.40% in terms of the number of successfully-resolved issues (% Resolved).