paper-with-me

Papers

Interactive Debugging and Steering of Multi-Agent AI Systems

2025-03-03 · Will Epperson, Gagan Bansal, Victor Dibia, Adam Fourney, Jack Gerrits, Erkang Zhu, Saleema Amershi

Fully autonomous teams of LLM-powered AI agents are emerging that collaborate to perform complex tasks for users. What challenges do developers face when trying to build and debug these AI agent teams? In formative interviews with five AI agent developers, we identify core challenges: difficulty reviewing long agent conversations to localize errors, lack of support in current tools for interactive debugging, and the need for tool support to iterate on agent configuration. Based on these needs, we developed an interactive multi-agent debugging tool, AGDebugger, with a UI for browsing and sending messages, the ability to edit and reset prior agent messages, and an overview visualization for navigating complex message histories. In a two-part user study with 14 participants, we identify common user strategies for steering agents and highlight the importance of interactive message resets for debugging. Our studies deepen understanding of interfaces for debugging increasingly important agentic workflows.

📄 PDF Abstract BibTeX arXiv:2503.02068

Code (1)

microsoft/agdebugger 공식 구현

Tasks

AI Agent

Similar Papers 제목 키워드 기반

AutoGen Studio: A No-Code Developer Tool for Building and Debugging Multi-Agent Systems

2024-08-09 · Victor Dibia, Jingya Chen, Gagan Bansal, Suff Syed 외

Multi-agent systems, where multiple agents (generative AI models + tools) collaborate, are emerging as an effective pattern for solving long-running, complex tasks in numerous domains. However, specifying their parameter…

From Attribution to Action: A Human-Centered Application of Activation Steering

2026-04-13 · Tobias Labarta, Maximilian Dreyer, Katharina Weitz, Wojciech Samek 외 arxiv

Explainable AI (XAI) methods reveal which features influence model predictions, yet provide limited means for practitioners to act on these explanations. Activation steering of components identified via XAI offers a path…

AdaLens: Interactive Storyline for Monitoring and Steering Long-Running Agentic Data Analysis

2026-08-18 · Yangtian Liu, Yan Miao, Shuhan Liu, Yunfan Zhou 외 arxiv

Large language models are pushing data science toward increasingly autonomous and agentic workflows, with recent systems already supporting multi-step and long-running analyses. As these workflows become more autonomous,…

debug-gym: A Text-Based Environment for Interactive Debugging

2025-03-27 · Xingdi Yuan, Morgane M Moss, Charbel El Feghali, Chinmay Singh 외

Large Language Models (LLMs) are increasingly relied upon for coding tasks, yet in most scenarios it is assumed that all relevant information can be either accessed in context or matches their training data. We posit tha…

MUSE: An Interactive Meta-Agent for Understanding and Steering LLM-powered Data Science Systems

2026-08-17 · Wei-Hao Chen, Weixi Tong, Yuan Tian, Chenglong Wang 외 arxiv

Recent advances in large language models have enabled a new class of agentic data science systems that allow users to complete complex data science workflows through natural language. Although these systems can significa…