# DebFlow: Automating Agent Creation via Agent Debate

arXiv: https://arxiv.org/abs/2503.23781 · HTML: https://mlsanity.com/paper/2503.23781/

## Key facts

- Cited by 10 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 36 references that are in the map.
- First posted on arXiv 31 Mar 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, 28 of 28)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs](https://mlsanity.com/paper/1903.00161/) (2019)
- [Large Language Models as Optimizers](https://mlsanity.com/paper/2309.03409/) (2023)
- [Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models](https://mlsanity.com/paper/2310.04406/) (2023)
- [Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution](https://mlsanity.com/paper/2309.16797/) (2023)
- [LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models](https://mlsanity.com/paper/2212.04088/) (2022)
- [AFlow: Automating Agentic Workflow Generation](https://mlsanity.com/paper/2410.10762/) (2024)
- [Automated Design of Agentic Systems](https://mlsanity.com/paper/2408.08435/) (2024)
- [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)
- [Data Interpreter: An LLM Agent For Data Science](https://mlsanity.com/paper/2402.18679/) (2024)
- [Symbolic Learning Enables Self-Evolving Agents](https://mlsanity.com/paper/2406.18532/) (2024)
- [AutoFlow: Automated Workflow Generation for Large Language Model Agents](https://mlsanity.com/paper/2407.12821/) (2024)
- [Archon: An Architecture Search Framework for Inference-Time Techniques](https://mlsanity.com/paper/2409.15254/) (2024)
- [MobileExperts: A Dynamic Tool-Enabled Agent Team in Mobile Devices](https://mlsanity.com/paper/2407.03913/) (2024)
- [HAIChart: Human and AI Paired Visualization System](https://mlsanity.com/paper/2406.11033/) (2024)
- [SurrealDriver: Designing LLM-powered Generative Driver Agent Framework based on Human Drivers' Driving-thinking Data](https://mlsanity.com/paper/2309.13193/) (2023)
- [VerifAI: Verified Generative AI](https://mlsanity.com/paper/2307.02796/) (2023)

## Built on by (most cited first, 10 of 10)

- [Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents](https://mlsanity.com/paper/2505.22954/) (2025)
- [Can LLM Agents Really Debate? A Controlled Study of Multi-Agent Debate in Logical Reasoning](https://mlsanity.com/paper/2511.07784/) (2025)
- [From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents](https://mlsanity.com/paper/2603.22386/) (2026)
- [MermaidFlow: Redefining Agentic Workflow Generation via Safety-Constrained Evolutionary Programming](https://mlsanity.com/paper/2505.22967/) (2025)
- [A2Flow: Automating Agentic Workflow Generation via Self-Adaptive Abstraction Operators](https://mlsanity.com/paper/2511.20693/) (2025)
- [ProRefine: Inference-Time Prompt Refinement with Textual Feedback](https://mlsanity.com/paper/2506.05305/) (2025)
- [Tournament of Prompts: Evolving LLM Instructions Through Structured Debates and Elo Ratings](https://mlsanity.com/paper/2506.00178/) (2025)
- [JudgeFlow: Agentic Workflow Optimization via Block Judge](https://mlsanity.com/paper/2601.07477/) (2026)
- [HyEvo: Self-Evolving Hybrid Agentic Workflows for Efficient Reasoning](https://mlsanity.com/paper/2603.19639/) (2026)
- [AgentPSO: Evolving Agent Reasoning Skill via Multi-agent Particle Swarm Optimization](https://mlsanity.com/paper/2605.08704/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have demonstrated strong potential and impressive performance in automating the generation and optimization of workflows. However, existing approaches are marked by limited reasoning capabilities, high computational demands, and significant resource requirements. To address these issues, we propose DebFlow, a framework that employs a debate mechanism to optimize workflows and integrates reflexion to improve based on previous experiences. We evaluated our method across six benchmark datasets, including HotpotQA, MATH, and ALFWorld. Our approach achieved a 3% average performance improvement over the latest baselines, demonstrating its effectiveness in diverse problem domains. In particular, during training, our framework reduces resource consumption by 37% compared to the state-of-the-art baselines. Additionally, we performed ablation studies. Removing the Debate component resulted in a 4% performance drop across two benchmark datasets, significantly greater than the 2% drop observed when the Reflection component was removed. These findings strongly demonstrate the critical role of Debate in enhancing framework performance, while also highlighting the auxiliary contribution of reflexion to overall optimization.