Interactive Debugging and Steering of Multi-Agent AI Systems
Open accessAbstract
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.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Tool-augmentation paradigms validate effectiveness in complex task decomposition while leveraging world interaction tools, with memory-enhanced agents becoming central to modern AI systems performing complex tasks through natural language integration of planning, tool use, memory, and multi-step reasoning.
“Tool-augmentation paradigms validate effectiveness in complex task decomposition while leveraging world interaction tools, with memory-enhanced agents becoming central to modern AI systems performing complex tasks through natural language integration of planning, tool use, memory, and multi-step reasoning [251, 360, 1099, 34].”
From A Survey of Context Engineering for Large Language Models (2025) · cites this paper as [251]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Lost in the Middle: How Language Models Use Long Contexts
Liu, N. F., Lin, K., Hewitt, J., Paranjape, A., Bevilacqua, M., Petroni, F., & Liang, P. (2024) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00638 · Cited by 1,612 · see citing works
On Faithfulness and Factuality in Abstractive Summarization
Maynez, J., Narayan, S., Bohnet, B., & McDonald, R. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.173 · Cited by 1,185 · see citing works
<i>Why and why not</i> explanations improve the intelligibility of context-aware intelligent systems
Lim, B. Y., Dey, A. K., & Avrahami, D. (2009) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/1518701.1519023 · Cited by 552 · see citing works
Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation With Large Language Models
Strobelt, H., Webson, A., Sanh, V., Hoover, B., Beyer, J., Pfister, H., & Rush, A. M. (2022) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2022.3209479 · Cited by 204 · see citing works
Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation with Large Language Models
Strobelt, H., Webson, A., Sanh, V., Hoover, B., Beyer, J., Pfister, H., & Rush, A. M. (2022) · arXiv · doi:10.48550/arxiv.2208.07852 · Cited by 204 · see citing works
PromptMaker: Prompt-based Prototyping with Large Language Models
Jiang, E., Olson, K., Toh, E., Molina, A., Donsbach, A., Terry, M., & Cai, C. J. (2022) · CHI Conference on Human Factors in Computing Systems Extended Abstracts · doi:10.1145/3491101.3503564 · Cited by 157 · see citing works
Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences
Shankar, S., Zamfirescu-Pereira, J. D., Hartmann, B., Parameswaran, A., & Arawjo, I. (2024) · Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology · doi:10.1145/3654777.3676450 · Cited by 151 · see citing works
ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testing
Arawjo, I., Swoopes, C., Vaithilingam, P., Wattenberg, M., & Glassman, E. (2023) · arXiv · doi:10.48550/arxiv.2309.09128 · Cited by 146
Gestalt: integrated support for implementation and analysis in machine learning
Patel, K., Bancroft, N., Drucker, S. M., Fogarty, J., Ko, A. J., & Landay, J. (2010) · Proceedings of the 23nd annual ACM symposium on User interface software and technology · doi:10.1145/1866029.1866038 · Cited by 112 · see citing works
Zeno: An Interactive Framework for Behavioral Evaluation of Machine Learning
Cabrera, Á. A., Fu, E., Bertucci, D., Holstein, K., Talwalkar, A., Hong, J. I., & Perer, A. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581268 · Cited by 51 · see citing works
Flagged first, then by citations
Research works printed but not linked: 28
- [1][1] Saleema Amershi, Andrew Begel, Christian Bird, Robert DeLine, Harald Gall, Ece Kamar, Nachiappan Nagappan, Besmira Nushi, and Thomas Zimmermann. 2019. Software engineering for machine learning: a case study. In Proceedings of the 41st International Conference on Software Engineering: Software Engineering in Practice (Montreal, Quebec, Canada) (ICSE-SEIP '19) . IEEE Press, New York, NY, USA, 291-300. https://doi.org/10.1109/ICSE-SEIP.2019.00042 - · DOI
- [2][2] Saleema Amershi, Max Chickering, Steven M. Drucker, Bongshin Lee, Patrice Simard, and Jina Suh. 2015. ModelTracker: Redesigning Performance Analysis Tools for Machine Learning. In Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems (Seoul, Republic of Korea) (CHI '15) . Association for Computing Machinery, New York, NY, USA, 337-346. https: //doi.org/10.1145/2702123.2702509 - · DOI
- [5][5] Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems , H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., Red Hook, NY, USA, 1877-1901. https://proceedings.neurips.cc/paper\_files/paper/2020/file/ 1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf -
- [7][7] Furui Cheng, Vilém Zouhar, Robin Shing Moon Chan, Daniel Fürst, Hendrik Strobelt, and Mennatallah El-Assady. 2024. Interactive Analysis of LLMs using Meaningful Counterfactuals. arXiv:2405.00708 [cs.CL] https://arxiv.org/abs/ 2405.00708 - · arXiv
- [8][8] Yuheng Cheng, Ceyao Zhang, Zhengwen Zhang, Xiangrui Meng, Sirui Hong, Wenhao Li, Zihao Wang, Zekai Wang, Feng Yin, Junhua Zhao, and Xiuqiang He. 2024. Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects. arXiv:2401.03428 [cs.AI] https://arxiv.org/abs/2401. 03428 - · arXiv
- [10][10] Victor Dibia, Jingya Chen, Gagan Bansal, Suff Syed, Adam Fourney, Erkang Zhu, Chi Wang, and Saleema Amershi. 2024. AutoGen Studio: A No-Code Developer Tool for Building and Debugging Multi-Agent Systems. arXiv:2408.15247 [cs.SE] https://arxiv.org/abs/2408.15247 - · arXiv
- [14][14] Taicheng Guo, Xiuying Chen, Yaqi Wang, Ruidi Chang, Shichao Pei, Nitesh V. Chawla, Olaf Wiest, and Xiangliang Zhang. 2024. Large Language Model Based Multi-agents: A Survey of Progress and Challenges. In Proceedings of the ThirtyThird International Joint Conference on Artificial Intelligence, IJCAI-24 , Kate Larson (Ed.). International Joint Conferences on Artificial Intelligence Organization, Online, 8048-8057. https://doi.org/10.24963/ijcai.2024/890 Survey Track. - · DOI · Paper page
- [15][15] Hongliang He, Wenlin Yao, Kaixin Ma, Wenhao Yu, Yong Dai, Hongming Zhang, Zhenzhong Lan, and Dong Yu. 2024. WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , Lun-Wei Ku, Andre Martins, and Vivek Srikumar (Eds.). Association for Computational Linguistics, Bangkok, Thailand, 6864-6890. https://aclanthology.org/2024.acllong.371 -
- [17][17] Carlos E Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik R Narasimhan. 2024. SWE-bench: Can Language Models Resolve Real-world Github Issues? https://openreview.net/forum?id=VTF8yNQM66 -
- [18][18] Minsuk Kahng, Ian Tenney, Mahima Pushkarna, Michael Xieyang Liu, James Wexler, Emily Reif, Krystal Kallarackal, Minsuk Chang, Michael Terry, and Lucas Dixon. 2025. LLM Comparator: Interactive Analysis of Side-by-Side Evaluation of Large Language Models. IEEE Transactions on Visualization and Computer Graphics 31, 1 (2025), 503-513. https://doi.org/10.1109/TVCG.2024.3456354 - · DOI
- [19][19] Tae Soo Kim, Yoonjoo Lee, Jamin Shin, Young-Ho Kim, and Juho Kim. 2024. EvalLM: Interactive Evaluation of Large Language Model Prompts on UserDefined Criteria. In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems (Honolulu, HI, USA) (CHI '24) . Association for Computing Machinery, New York, NY, USA, Article 306, 21 pages. https://doi.org/10.1145/ 3613904.3642216 -
- [20][20] Todd Kulesza, Margaret Burnett, Weng-Keen Wong, and Simone Stumpf. 2015. Principles of Explanatory Debugging to Personalize Interactive Machine Learning. In Proceedings of the 20th International Conference on Intelligent User Interfaces (Atlanta, Georgia, USA) (IUI '15) . Association for Computing Machinery, New York, NY, USA, 126-137. https://doi.org/10.1145/2678025.2701399 - · DOI · Paper page
- [22][22] Guohao Li, Hasan Abed Al Kader Hammoud, Hani Itani, Dmitrii Khizbullin, and Bernard Ghanem. 2023. CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society. arXiv:2303.17760 [cs.AI] https://arxiv.org/ abs/2303.17760 - · arXiv
- [24][24] Greg Little, Lydia B. Chilton, Max Goldman, and Robert C. Miller. 2010. TurKit: human computation algorithms on mechanical turk. In Proceedings of the 23nd Annual ACM Symposium on User Interface Software and Technology (New York, New York, USA) (UIST '10) . Association for Computing Machinery, New York, NY, USA, 57-66. https://doi.org/10.1145/1866029.1866040 - · DOI
- [28][28] Besmira Nushi, Ece Kamar, Eric Horvitz, and Donald Kossmann. 2017. On human intellect and machine failures: troubleshooting integrative machine learning systems. In Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (San Francisco, California, USA) (AAAI'17) . AAAI Press, New York, NY, USA, 1017-1025. -
- [30][30] Deokgun Park, Steven M. Drucker, Roland Fernandez, and Niklas Elmqvist. 2018. Atom: A Grammar for Unit Visualizations. IEEE Transactions on Visualization and Computer Graphics 24, 12 (2018), 3032-3043. https://doi.org/10.1109/TVCG. 2017.2785807 - · DOI
- [32][32] Savvas Petridis, Benjamin D Wedin, James Wexler, Mahima Pushkarna, Aaron Donsbach, Nitesh Goyal, Carrie J Cai, and Michael Terry. 2024. ConstitutionMaker: Interactively Critiquing Large Language Models by Converting Feedback into Principles. In Proceedings of the 29th International Conference on Intelligent User Interfaces (Greenville, SC, USA) (IUI '24) . Association for Computing Machinery, New York, NY, USA, 853-868. https://doi.org/10.1145/3640543.3645144 - · DOI · Paper page
- [35][35] Marco Tulio Ribeiro and Scott Lundberg. 2022. Adaptive Testing and Debugging of NLP Models. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , Smaranda Muresan, Preslav Nakov, and Aline Villavicencio (Eds.). Association for Computational Linguistics, Dublin, Ireland, 3253-3267. https://doi.org/10.18653/v1/2022.acl-long.230 - · DOI
- [39][39] Ian Tenney, Ryan Mullins, Bin Du, Shree Pandya, Minsuk Kahng, and Lucas Dixon. 2024. Interactive Prompt Debugging with Sequence Salience. arXiv:2404.07498 [cs.CL] https://arxiv.org/abs/2404.07498 - · arXiv
- [40][40] Sandra Wachter, Brent D. Mittelstadt, and Chris Russell. 2017. Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR. arXiv:1711.00399 http://arxiv.org/abs/1711.00399 - · arXiv
- [41][41] Xingyao Wang, Boxuan Li, Yufan Song, Frank F. Xu, Xiangru Tang, Mingchen Zhuge, Jiayi Pan, Yueqi Song, Bowen Li, Jaskirat Singh, Hoang H. Tran, Fuqiang Li, Ren Ma, Mingzhang Zheng, Bill Qian, Yanjun Shao, Niklas Muennighoff, Yizhe Zhang, Binyuan Hui, Junyang Lin, Robert Brennan, Hao Peng, Heng Ji, and Graham Neubig. 2024. OpenDevin: An Open Platform for AI Software Developers as Generalist Agents. arXiv:2407.16741 [cs.SE] https://arxiv.org/abs/2407.16741 - · arXiv
- [42][42] James Wexler, Mahima Pushkarna, Tolga Bolukbasi, Martin Wattenberg, Fernanda B. Viégas, and Jimbo Wilson. 2020. The What-If Tool: Interactive Probing of Machine Learning Models. IEEE Trans. Vis. Comput. Graph. 26, 1 (2020), 56-65. https://doi.org/10.1109/TVCG.2019.2934619 - · DOI
- [44][44] Tongshuang Wu, Ellen Jiang, Aaron Donsbach, Jeff Gray, Alejandra Molina, Michael Terry, and Carrie J Cai. 2022. PromptChainer: Chaining Large Language Model Prompts through Visual Programming. In Extended Abstracts of the 2022 CHI Conference on Human Factors in Computing Systems (New Orleans, LA, USA) (CHI EA '22) . Association for Computing Machinery, New York, NY, USA, Article 359, 10 pages. https://doi.org/10.1145/3491101.3519729 - · DOI · Paper page
- [45][45] Tongshuang Wu, Marco Tulio Ribeiro, Jeffrey Heer, and Daniel Weld. 2021. Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) , Chengqing Zong, Fei Xia, Wenjie Li, and Roberto Navigli (Eds.). Association for Computational Linguistics, Online, 6707-6723. https://doi.org/10.18653/v1/2021.acl-long.523 - · DOI
- [46][46] Tongshuang Wu, Michael Terry, and Carrie Jun Cai. 2022. AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts. In Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems (New Orleans, LA, USA) (CHI '22) . Association for Computing Machinery, New York, NY, USA, Article 385, 22 pages. https://doi.org/10.1145/3491102. 3517582 - · DOI
- [47][47] Zhiyong Wu, Chengcheng Han, Zichen Ding, Zhenmin Weng, Zhoumianze Liu, Shunyu Yao, Tao Yu, and Lingpeng Kong. 2024. OS-Copilot: Towards Generalist Computer Agents with Self-Improvement. arXiv:2402.07456 [cs.AI] https: //arxiv.org/abs/2402.07456 - · arXiv
- [48][48] J.D. Zamfirescu-Pereira, Richmond Y. Wong, Bjoern Hartmann, and Qian Yang. 2023. Why Johnny Can't Prompt: How Non-AI Experts Try (and Fail) to Design LLM Prompts. In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (Hamburg, Germany) (CHI '23) . Association for Computing Machinery, New York, NY, USA, Article 437, 21 pages. https://doi.org/10.1145/ 3544548.3581388 -
- [49][49] Shuyan Zhou, Frank F. Xu, Hao Zhu, Xuhui Zhou, Robert Lo, Abishek Sridhar, Xianyi Cheng, Tianyue Ou, Yonatan Bisk, Daniel Fried, Uri Alon, and Graham Neubig. 2024. WebArena: A Realistic Web Environment for Building Autonomous Agents. https://openreview.net/forum?id=oKn9c6ytLx
Cited by
Sorted by citations
Why Do Multi-Agent LLM Systems Fail?
Cemri, M., Pan, M. Z., Yang, S., Agrawal, L. A., Chopra, B., Tiwari, R., Keutzer, K., Parameswaran, A., Klein, D., Ramchandran, K., et al. (2025) · arXiv · doi:10.48550/arxiv.2503.13657 · Cited by 15 · see citing works
“Further related efforts aim to improve MAS through different approachs: AgentEval [31], AGDebugger [32], MAS debugger Zhang et al. [33].”
A Survey of Context Engineering for Large Language Models
Mei, L., Yao, J., Ge, Y., Wang, Y., Bi, B., Cai, Y., Liu, J., Li, M., Li, Z.-Z., Zhang, D., et al. (2025) · arXiv · doi:10.48550/arxiv.2507.13334 · Cited by 13 · see citing works
MARFT: Multi-Agent Reinforcement Fine-Tuning
Liao, J., Wen, M., Wang, J., & Zhang, W. (2025) · arXiv · doi:10.48550/arxiv.2504.16129
- Authors
- Epperson, W., Bansal, G., Dibia, V. C., Fourney, A., Gerrits, J., Zhu, E. (., & Amershi, S.
- Affiliations
- Carnegie Mellon University (US)
- Microsoft (United States) (US)
- ORCID
- Venue
- Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems
- Publisher
- ACM
- Published
- 2025-04-25
- Pages
- 1-15
- OpenAlex
- W4409736285
- Cited by
- 35
- References
- 10
- Citations by year
- 2026: 28 · 2025: 7
- FWCI
- 27.36
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- CHI Conference on Human Factors in Computing Systems (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Software › Software Testing and Debugging Techniques
- Physical Sciences › Computer Science › Human-Computer Interaction › Usability and User Interface Design
- Physical Sciences › Computer Science › Information Systems › Software Engineering Techniques and Practices
- Keywords
- multi-agent systems, interactive debugging, LLM agents, agent configuration, error localization, software development tools, user study
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
