# Interactive Debugging and Steering of Multi-Agent AI Systems

arXiv: https://arxiv.org/abs/2503.02068 · HTML: https://mlsanity.com/paper/2503.02068/

## Key facts

- Cited by 68 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 14 of its 22 references that are in the map.
- First posted on arXiv 3 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, 14 of 14)

- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017)
- [On Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2005.00661/) (2020)
- [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://mlsanity.com/paper/2402.01680/) (2024)
- [WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models](https://mlsanity.com/paper/2401.13919/) (2024)
- [AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts](https://mlsanity.com/paper/2110.01691/) (2021)
- [Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models](https://mlsanity.com/paper/2101.00288/) (2021)
- [Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences](https://mlsanity.com/paper/2404.12272/) (2024)
- [PromptChainer: Chaining Large Language Model Prompts through Visual Programming](https://mlsanity.com/paper/2203.06566/) (2022)
- [ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testing](https://mlsanity.com/paper/2309.09128/) (2023)
- [EvalLM: Interactive Evaluation of Large Language Model Prompts on User-Defined Criteria](https://mlsanity.com/paper/2309.13633/) (2023)
- [Zeno: An Interactive Framework for Behavioral Evaluation of Machine Learning](https://mlsanity.com/paper/2302.04732/) (2023)
- [ConstitutionMaker: Interactively Critiquing Large Language Models by Converting Feedback into Principles](https://mlsanity.com/paper/2310.15428/) (2023)
- [On Human Intellect and Machine Failures: Troubleshooting Integrative Machine Learning Systems](https://mlsanity.com/paper/1611.08309/) (2016)

## Built on by (most cited first, 30 of 68)

- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [TRAIL: Trace Reasoning and Agentic Issue Localization](https://mlsanity.com/paper/2505.08638/) (2025)
- [Understanding Software Engineering Agents: A Study of Thought-Action-Result Trajectories](https://mlsanity.com/paper/2506.18824/) (2025)
- [MARFT: Multi-Agent Reinforcement Fine-Tuning](https://mlsanity.com/paper/2504.16129/) (2025)
- [Who is Introducing the Failure? Automatically Attributing Failures of Multi-Agent Systems via Spectrum Analysis](https://mlsanity.com/paper/2509.13782/) (2025)
- [Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments](https://mlsanity.com/paper/2602.11964/) (2026)
- [ARE: Scaling Up Agent Environments and Evaluations](https://mlsanity.com/paper/2509.17158/) (2025)
- [DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems](https://mlsanity.com/paper/2512.06749/) (2025)
- [RAFFLES: Reasoning-based Attribution of Faults for LLM Systems](https://mlsanity.com/paper/2509.06822/) (2025)
- [Automatic Failure Attribution and Critical Step Prediction Method for Multi-Agent Systems Based on Causal Inference](https://mlsanity.com/paper/2509.08682/) (2025)
- [CORRECT: COndensed eRror RECognition via knowledge Transfer in multi-agent systems](https://mlsanity.com/paper/2509.24088/) (2025)
- [A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System](https://mlsanity.com/paper/2510.09721/) (2025)
- [Towards Transparent and Incentive-Compatible Collaboration in Decentralized LLM Multi-Agent Systems: A Blockchain-Driven Approach](https://mlsanity.com/paper/2509.16736/) (2025)
- [TrajAudit: Automated Failure Diagnosis for Agentic Coding Systems](https://mlsanity.com/paper/2605.26563/) (2026)
- [Demystifying the Lifecycle of Failures in Platform-Orchestrated Agentic Workflows](https://mlsanity.com/paper/2509.23735/) (2025)
- [Traceability and Accountability in Role-Specialized Multi-Agent LLM Pipelines](https://mlsanity.com/paper/2510.07614/) (2025)
- [DiLLS: Interactive Diagnosis of LLM-based Multi-agent Systems via Layered Summary of Agent Behaviors](https://mlsanity.com/paper/2602.05446/) (2026)
- [Agentic Services Computing](https://mlsanity.com/paper/2509.24380/) (2025)
- [When Should Users Check? Modeling Confirmation Frequency in Multi-Step Agentic AI Tasks](https://mlsanity.com/paper/2510.05307/) (2025)
- [When Agents Fail: A Comprehensive Study of Bugs in LLM Agents with Automated Labeling](https://mlsanity.com/paper/2601.15232/) (2026)
- [Human oversight of agentic systems in practice: Examining the oversight work, challenges, and heuristics of developers using software agents](https://mlsanity.com/paper/2606.05391/) (2026)
- [MAS-PromptBench: When Does Prompt Optimization Improve Multi-Agent LLM Systems?](https://mlsanity.com/paper/2606.23664/) (2026)
- [AgentCheck: A Reproduce-Intervene-Mitigate Workbench for LLM Agents over MCP](https://mlsanity.com/paper/2607.11098/) (2026)
- [AI Agents Push Humans Out of the Loop](https://mlsanity.com/paper/2608.23642/) (2026)
- [The Behavioral Fabric of LLM-Powered GUI Agents: Human Values and Interaction Outcomes](https://mlsanity.com/paper/2601.16356/) (2026)
- [AppWorld-UL: Benchmarking Diverse Agent-User Interactions for Tool-Use](https://mlsanity.com/paper/2607.20536/) (2026)
- [RAG Without the Lag: Interactive Debugging for Retrieval-Augmented Generation Pipelines](https://mlsanity.com/paper/2504.13587/) (2025)
- [On the Regulatory Potential of User Interfaces for AI Agent Governance](https://mlsanity.com/paper/2512.00742/) (2025)
- [XAgen: An Explainability Tool for Identifying and Correcting Failures in Multi-Agent Workflows](https://mlsanity.com/paper/2512.17896/) (2025)
- [Are We All Using Agents the Same Way? An Empirical Study of Core and Peripheral Developers Use of Coding Agents](https://mlsanity.com/paper/2601.20106/) (2026)

## Abstract (arXiv)

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.