Optimizing LLM-Based Multi-Agent System with Textual Feedback: A Case Study on Software Development

arXiv 2505.16086 ↗First posted 22 May 2025cs.AI cs.CLcited by 7

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

We have seen remarkable progress in large language models (LLMs) empowered multi-agent systems solving complex tasks necessitating cooperation among experts with diverse skills. However, optimizing LLM-based multi-agent systems remains challenging. In this work, we perform an empirical case study on group optimization of role-based multi-agent systems utilizing natural language feedback for challenging software development tasks under various evaluation dimensions. We propose a two-step agent prompts optimization pipeline: identifying underperforming agents with their failure explanations utilizing textual feedback and then optimizing system prompts of identified agents utilizing failure explanations. We then study the impact of various optimization settings on system performance with two comparison groups: online against offline optimization and individual against group optimization. For group optimization, we study two prompting strategies: one-pass and multi-pass prompting optimizations. Overall, we demonstrate the effectiveness of our optimization method for role-based multi-agent systems tackling software development tasks evaluated on diverse evaluation dimensions, and we investigate the impact of diverse optimization settings on group behaviors of the multi-agent systems to provide practical insights for future development.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 48 of its 59 references that are in the map. First posted on arXiv 22 May 2025.

Builds on

48 of 59 references.

Closest ancestors · 8

Same direction, newest first

Other references · 40

2020Language Models are Few-Shot Learnerscited by 32,419
2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
2021Evaluating Large Language Models Trained on Codecited by 8,320
2020Measuring Massive Multitask Language Understandingcited by 7,963
2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,234
2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,920

28 more

2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,256
2022Large Language Models Are Human-Level Prompt Engineerscited by 1,045
2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 1,011
2023ChatDev: Communicative Agents for Software Developmentcited by 919
2023Large Language Models as Optimizerscited by 864
2023AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedbackcited by 748
2023Automatic Prompt Optimization with "Gradient Descent" and Beam Searchcited by 653
2021Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigmcited by 606
2023LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusioncited by 564
2022RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learningcited by 366
2023Large Language Models as Tool Makerscited by 303
2024TextGrad: Automatic "Differentiation" via Textcited by 273
2022Prompting GPT-3 To Be Reliablecited by 260
2023Self-collaboration Code Generation via ChatGPTcited by 258
2023PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimizationcited by 233
2024LLM Critics Help Catch LLM Bugscited by 147
2024MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolutioncited by 134
2022GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Modelscited by 127
2023Mindstorms in Natural Language-Based Societies of Mindcited by 107
2023MathChat: Converse to Tackle Challenging Math Problems with LLM Agentscited by 68
2023Prompt Engineering a Prompt Engineercited by 53
2023ChatLLM Network: More brains, More intelligencecited by 37
2024Are Large Language Models Good Prompt Optimizers?cited by 37
2023AutoHint: Automatic Prompt Optimization with Hint Generationcited by 30
2025TReMu: Towards Neuro-Symbolic Temporal Reasoning for LLM-Agents with Memory in Multi-Session Dialoguescited by 25
2023Robust Prompt Optimization for Large Language Models Against Distribution Shiftscited by 19
2022What should I Ask: A Knowledge-driven Approach for Follow-up Questions Generation in Conversational Surveyscited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 5.

7 papers.

2025SAMULE: Self-Learning Agents Enhanced by Multi-level Reflectioncited by 15
2026Recursive Multi-Agent Systemscited by 10
2026Steer, Don't Solve: Training Small Critic Models for Large Code Agentscited by 5
2026MAS-PromptBench: When Does Prompt Optimization Improve Multi-Agent LLM Systems?cited by 5
2025Designing LLM-based Multi-Agent Systems for Software Engineering Tasks: Quality Attributes, Design Patterns and Rationalecited by 3
2026Hierarchical LLM-Based Multi-Agent Framework with Prompt Optimization for Multi-Robot Task Planningcited by 2
2026Automated Summarization of Software Documents: An LLM-based Multi-Agent Approachcited by 1

Similar, not cited

Close in wording, no citation either way