# Multi-Agent Debate Strategies to Enhance Requirements Engineering with Large Language Models

arXiv: https://arxiv.org/abs/2507.05981 · HTML: https://mlsanity.com/paper/2507.05981/

## Key facts

- Cited by 8 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 27 of its 42 references that are in the map.
- First posted on arXiv 8 Jul 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, 27 of 27)

- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [A Comprehensive Overview of Large Language Models](https://mlsanity.com/paper/2307.06435/) (2023)
- [Large Language Models for Software Engineering: A Systematic Literature Review](https://mlsanity.com/paper/2308.10620/) (2023)
- [ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs](https://mlsanity.com/paper/2309.13007/) (2023)
- [Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration](https://mlsanity.com/paper/2307.05300/) (2023)
- [Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?](https://mlsanity.com/paper/2402.18272/) (2024)
- [PRD: Peer Rank and Discussion Improve Large Language Model based Evaluations](https://mlsanity.com/paper/2307.02762/) (2023)
- [Improving Multi-Agent Debate with Sparse Communication Topology](https://mlsanity.com/paper/2406.11776/) (2024)
- [Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debate](https://mlsanity.com/paper/2305.11595/) (2023)
- [Solving Math Word Problems via Cooperative Reasoning induced Language Models](https://mlsanity.com/paper/2210.16257/) (2022)
- [Let Models Speak Ciphers: Multiagent Debate through Embeddings](https://mlsanity.com/paper/2310.06272/) (2023)
- [Towards Reasoning in Large Language Models via Multi-Agent Peer Review Collaboration](https://mlsanity.com/paper/2311.08152/) (2023)
- [Multi-Agent Consensus Seeking via Large Language Models](https://mlsanity.com/paper/2310.20151/) (2023)
- [Advancing Requirements Engineering through Generative AI: Assessing the Role of LLMs](https://mlsanity.com/paper/2310.13976/) (2023)
- [Learning to Break: Knowledge-Enhanced Reasoning in Multi-Agent Debate System](https://mlsanity.com/paper/2312.04854/) (2023)
- [Confidence Calibration and Rationalization for LLMs via Multi-Agent Deliberation](https://mlsanity.com/paper/2404.09127/) (2024)
- [Enhancing Diagnostic Accuracy through Multi-Agent Conversations: Using Large Language Models to Mitigate Cognitive Bias](https://mlsanity.com/paper/2401.14589/) (2024)
- [Do Advanced Language Models Eliminate the Need for Prompt Engineering in Software Engineering?](https://mlsanity.com/paper/2411.02093/) (2024)
- [Counterfactual Debating with Preset Stances for Hallucination Elimination of LLMs](https://mlsanity.com/paper/2406.11514/) (2024)
- [ERD: A Framework for Improving LLM Reasoning for Cognitive Distortion Classification](https://mlsanity.com/paper/2403.14255/) (2024)
- [Requirements Engineering using Generative AI: Prompts and Prompting Patterns](https://mlsanity.com/paper/2311.03832/) (2023)
- [Google Scholar, Microsoft Academic, Scopus, Dimensions, Web of Science, and OpenCitations' COCI: a multidisciplinary comparison of coverage via citations](https://mlsanity.com/paper/2004.14329/) (2020)
- [Debate as Optimization: Adaptive Conformal Prediction and Diverse Retrieval for Event Extraction](https://mlsanity.com/paper/2406.12197/) (2024)
- [Generating Test Scenarios from NL Requirements using Retrieval-Augmented LLMs: An Industrial Study](https://mlsanity.com/paper/2404.12772/) (2024)
- [CoEvol: Constructing Better Responses for Instruction Finetuning through Multi-Agent Cooperation](https://mlsanity.com/paper/2406.07054/) (2024)

## Built on by (most cited first, 8 of 8)

- [From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence](https://mlsanity.com/paper/2511.18538/) (2025)
- [Refine and Align: Confidence Calibration through Multi-Agent Interaction in VQA](https://mlsanity.com/paper/2511.11169/) (2025)
- [Completing Missing Annotation: Multi-Agent Debate for Accurate and Scalable Relevant Assessment for IR Benchmarks](https://mlsanity.com/paper/2602.06526/) (2026)
- [Audited Reasoning Refinement: Fine-Tuning Language Models via LLM-Guided Step-Wise Evaluation and Correction](https://mlsanity.com/paper/2509.12476/) (2025)
- [QUARE: Quality-Aware Requirements Analysis through Multi-Agent Dialectical Negotiation](https://mlsanity.com/paper/2603.11890/) (2026)
- [Fairness in Multi-Agent Systems for Software Engineering: An SDLC-Oriented Rapid Review](https://mlsanity.com/paper/2604.13103/) (2026)
- [Neuro-Symbolic Agents for Hallucination-Free Requirements Reuse](https://mlsanity.com/paper/2605.01562/) (2026)
- [Model-Driven Requirements Configuration with Three-Valued Uncertainty Scoring](https://mlsanity.com/paper/2607.26220/) (2026)

## Abstract (arXiv)

Context: Large Language Model (LLM) agents are becoming widely used for various Requirements Engineering (RE) tasks. Research on improving their accuracy mainly focuses on prompt engineering, model fine-tuning, and retrieval augmented generation. However, these methods often treat models as isolated black boxes - relying on single-pass outputs without iterative refinement or collaboration, limiting robustness and adaptability. Objective: We propose that, just as human debates enhance accuracy and reduce bias in RE tasks by incorporating diverse perspectives, different LLM agents debating and collaborating may achieve similar improvements. Our goal is to investigate whether Multi-Agent Debate (MAD) strategies can enhance RE performance. Method: We conducted a systematic study of existing MAD strategies across various domains to identify their key characteristics. To assess their applicability in RE, we implemented and tested a preliminary MAD-based framework for RE classification. Results: Our study identified and categorized several MAD strategies, leading to a taxonomy outlining their core attributes. Our preliminary evaluation demonstrated the feasibility of applying MAD to RE classification. Conclusions: MAD presents a promising approach for improving LLM accuracy in RE tasks. This study provides a foundational understanding of MAD strategies, offering insights for future research and refinements in RE applications.