paper-with-me

Papers

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

2025-05-22 · Ming Shen, Raphael Shu, Anurag Pratik, James Gung, Yubin Ge, Monica Sunkara, Yi Zhang

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.

📄 PDF Abstract BibTeX arXiv:2505.16086

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Learning to Evolve: A Self-Improving Framework for Multi-Agent Systems via Textual Parameter Graph Optimization

2026-04-22 · Shan He, Runze Wang, Zhuoyun Du, Huiyu Bai 외 arxiv

Designing and optimizing multi-agent systems (MAS) is a complex, labor-intensive process of "Agent Engineering." Existing automatic optimization methods, primarily focused on flat prompt tuning, lack the structural aware…

MultiScale Contextual Bandits for Long Term Objectives

2025-03-22 · Richa Rastogi, Yuta Saito, Thorsten Joachims

The feedback that AI systems (e.g., recommender systems, chatbots) collect from user interactions is a crucial source of training data. While short-term feedback (e.g., clicks, engagement) is widely used for training, th…

Multi-Armed BanditsRecommendation SystemsText Generation

Vaiage: A Multi-Agent Solution to Personalized Travel Planning

2025-05-16 · Binwen Liu, Jiexi Ge, Jiamin Wang

Planning trips is a cognitively intensive task involving conflicting user preferences, dynamic external information, and multi-step temporal-spatial optimization. Traditional platforms often fall short - they provide sta…

A Multi-AI Agent System for Autonomous Optimization of Agentic AI Solutions via Iterative Refinement and LLM-Driven Feedback Loops

2024-12-22 · Kamer Ali Yuksel, Hassan Sawaf

Agentic AI systems use specialized agents to handle tasks within complex workflows, enabling automation and efficiency. However, optimizing these systems often requires labor-intensive, manual adjustments to refine roles…

AI Agent

Optimizing Autonomous Driving for Safety: A Human-Centric Approach with LLM-Enhanced RLHF

2024-06-06 · Yuan Sun, Navid Salami Pargoo, Peter J. Jin, Jorge Ortiz

Reinforcement Learning from Human Feedback (RLHF) is popular in large language models (LLMs), whereas traditional Reinforcement Learning (RL) often falls short. Current autonomous driving methods typically utilize either…

Autonomous Drivingreinforcement-learningReinforcement LearningReinforcement Learning (RL)