# Requirements Development and Formalization for Reliable Code Generation: A Multi-Agent Vision

arXiv: https://arxiv.org/abs/2508.18675 · HTML: https://mlsanity.com/paper/2508.18675/

## 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 19 of its 48 references that are in the map.
- First posted on arXiv 26 Aug 2025.

## Placed in

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

## Builds on (most cited first, 19 of 19)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [DeepSeek LLM: Scaling Open-Source Language Models with Longtermism](https://mlsanity.com/paper/2401.02954/) (2024)
- [Autoformalization with Large Language Models](https://mlsanity.com/paper/2205.12615/) (2022)
- [Enchanting Program Specification Synthesis by Large Language Models using Static Analysis and Program Verification](https://mlsanity.com/paper/2404.00762/) (2024)
- [SpecGen: Automated Generation of Formal Program Specifications via Large Language Models](https://mlsanity.com/paper/2401.08807/) (2024)
- [Formal Specifications from Natural Language](https://mlsanity.com/paper/2206.01962/) (2022)
- [Source Code Summarization in the Era of Large Language Models](https://mlsanity.com/paper/2407.07959/) (2024)
- [Requirements are All You Need: From Requirements to Code with LLMs](https://mlsanity.com/paper/2406.10101/) (2024)
- [Elicitron: An LLM Agent-Based Simulation Framework for Design Requirements Elicitation](https://mlsanity.com/paper/2404.16045/) (2024)
- [From Informal to Formal -- Incorporating and Evaluating LLMs on Natural Language Requirements to Verifiable Formal Proofs](https://mlsanity.com/paper/2501.16207/) (2025)
- [Combining LLM Code Generation with Formal Specifications and Reactive Program Synthesis](https://mlsanity.com/paper/2410.19736/) (2024)
- [Knowledge-Based Multi-Agent Framework for Automated Software Architecture Design](https://mlsanity.com/paper/2503.20536/) (2025)

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

- [Code as Agent Harness](https://mlsanity.com/paper/2605.18747/) (2026)
- [Stop Wasting Your Tokens: Towards Efficient Runtime Multi-Agent Systems](https://mlsanity.com/paper/2510.26585/) (2025)
- [AutoICE: Automatically Synthesizing Verifiable C Code via LLM-driven Evolution](https://mlsanity.com/paper/2512.07501/) (2025)
- [Don't Guess, Just Ask: Evaluating Interactive Requirement Clarification for Repository-Level Software Development](https://mlsanity.com/paper/2610.13022/) (2026)

## Abstract (arXiv)

Automated code generation has long been considered the holy grail of software engineering. The emergence of Large Language Models (LLMs) has catalyzed a revolutionary breakthrough in this area. However, existing methods that only rely on LLMs remain inadequate in the quality of generated code, offering no guarantees of satisfying practical requirements. They lack a systematic strategy for requirements development and modeling. Recently, LLM-based agents typically possess powerful abilities and play an essential role in facilitating the alignment of LLM outputs with user requirements. In this paper, we envision the first multi-agent framework for reliable code generation based on textscrequirements textscdevelopment and textscformalization, named textscReDeFo. This framework incorporates three agents, highlighting their augmentation with knowledge and techniques of formal methods, into the requirements-to-code generation pipeline to strengthen quality assurance. The core of textscReDeFo is the use of formal specifications to bridge the gap between potentially ambiguous natural language requirements and precise executable code. textscReDeFo enables rigorous reasoning about correctness, uncovering hidden bugs, and enforcing critical properties throughout the development process. In general, our framework aims to take a promising step toward realizing the long-standing vision of reliable, auto-generated software.