Gagan Bansal

Principal Researcher

Homepage

Publications

Afficher par:

- SentinelBench: A Benchmark for Long-Running Monitoring Agents
  
  Matheus Kunzler Maldaner, Adam Fourney, Amanda Swearngin, Hussein Mozannar, Gagan Bansal, Maya Murad, Rafah Hosn, Saleema Amershi
  
  June 2026
  
  arXiv | June 2026
  
  Publication
- Magentic Marketplace: An Open-Source Environment for Studying Agentic Markets
  
  Gagan Bansal, Wenyue Hua, Zezhou Huang, Adam Fourney, Amanda Swearngin, Will Epperson, Tyler Payne, Jake Hofman, Brendan Lucier, Chinmay Singh, Markus Mobius, Akshay Nambi, Archana Yadav, Kevin Gao, David Rothschild, Aleksandrs Slivkins, Daniel G. Goldstein, Hussein Mozannar, Nicole Immorlica, Maya Murad, Matthew Vogel, Subbarao Kambhampati, Eric Horvitz, Saleema Amershi
  
  MSR-TR-2025-50 | October 2025
  
  Publié par Microsoft
  
  Publication Vidéo Vidéo Accès
- Magentic-UI: Towards Human-in-the-loop Agentic Systems
  
  Hussein Mozannar, Gagan Bansal, Cheng Tan, Adam Fourney, Victor Dibia, Jingya Chen, Jack Gerrits, Tyler Payne, Matheus Kunzler Maldaner, Madeleine Grunde-McLaughlin, Eric Zhu, Griffin Bassman, Jacob Alber, Peter Chang, Ricky Loynd, Friederike Niedtner, Ece Kamar, Maya Murad, Rafah Hosn, Saleema Amershi
  
  MSR-TR-2025-40 | July 2025
  
  Publié par Microsoft
  
  Publication Projet
- Interactive Debugging and Steering of Multi-Agent AI Systems
  
  Will Epperson, Gagan Bansal, Victor Dibia, Adam Fourney (adamfo), Jack Gerrits, Erkang (Eric) Zhu, Saleema Amershi
  
  CHI 2025 | April 2025
  
  Publication
- Generation Probabilities Are Not Enough: Uncertainty Highlighting in AI Code Completions
  
  Helena Vasconcelos, Gagan Bansal, Adam Fourney, Q. Vera Liao, Jennifer Wortman Vaughan
  
  ToCHI | April 2025, Vol 32(1)
  
  Publication
- Navigating Rifts in Human-LLM Grounding: Study and Benchmark
  
  Omar Shaikh, Hussein Mozannar, Gagan Bansal, Adam Fourney, Eric Horvitz
  
  ACL | March 2025
  
  Publication
- Challenges in Human-Agent Communication
  
  Gagan Bansal, Jennifer Wortman Vaughan, Saleema Amershi, Eric Horvitz, Adam Fourney, Hussein Mozannar, Victor Dibia, Daniel S. Weld
  
  MSR-TR-2024-53 | December 2024
  
  Publié par Microsoft
  
  Publication Projet
- Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks
  
  Adam Fourney, Gagan Bansal, Hussein Mozannar, Cheng Tan, Eduardo Salinas, Erkang (Eric) Zhu, Friederike Niedtner, Grace Proebsting, Griffin Bassman, Jack Gerrits, Jacob Alber, Peter Chang, Ricky Loynd, Robert West, Victor Dibia, Ahmed Awadallah, Ece Kamar, Rafah Hosn, Saleema Amershi
  
  MSR-TR-2024-47 | November 2024
  
  Publié par Microsoft
  
  Preprint Vidéo Accès
- AutoGen Studio: A No-Code Developer Tool for Building and Debugging Multi-Agent Systems
  
  Victor Dibia, Jingya Chen, Gagan Bansal, Suff Syed, Adam Fourney, Erkang (Eric) Zhu, Chi Wang, Saleema Amershi
  
  August 2024
  
  Preprint
  
  PDF Publication Vidéo Vidéo Projet
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
  
  Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, Erkang (Eric) Zhu, Li Jiang, Xiaoyun Zhang, Shaokun Zhang, Ahmed Awadallah, Ryen W. White, Doug Burger, Chi Wang
  
  COLM 2024 | August 2024
  
  Best Paper, LLM Agents Workshop ICLR'24
  
  Publication Vidéo Vidéo Vidéo Projet
- Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming
  
  Hussein Mozannar, Gagan Bansal, Adam Fourney, Eric Horvitz
  
  CHI 2024 | May 2024
  
  Honorable Mention, CHI 2024
  
  Publication
- When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programming
  
  Hussein Mozannar, Gagan Bansal, Adam Fourney, Eric Horvitz
  
  AAAI 2024 | January 2024
  
  PDF Publication
- Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanations
  
  Valerie Chen, Q. Vera Liao, Jennifer Wortman Vaughan, Gagan Bansal
  
  Proc. ACM Hum.-Comput. Interact. | October 2023, Vol 7
  
  Article 370
  
  PDF Projet
- Aligning Offline Metrics and Human Judgments of Value for Code Generation Models
  
  Victor Dibia, Adam Fourney, Gagan Bansal, Forough Poursabzi, Han Liu, Saleema Amershi
  
  ACL 2023 | June 2023
  
  Publication
- Generation Probabilities are Not Enough: Improving Error Highlighting for AI Code Suggestions
  
  Helena Vasconcelos, Gagan Bansal, Adam Fourney, Q. Vera Liao, Jennifer Wortman Vaughan
  
  NeurIPS Workshop on Human-Centered AI | October 2022
  
  Publication
- Aligning Offline Metrics and Human Judgments of Value of AI-Pair Programmers
  
  Victor Dibia, Adam Fourney, Gagan Bansal, Forough Poursabzi, Han Liu, Saleema Amershi
  
  ACL 2023 | October 2022
  
  Preprint
- Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance
  
  Gagan Bansal, Tongshuang Wu, Joyce Zhou, Raymond Fok, Besmira Nushi, Ece Kamar, Marco Tulio Ribeiro, Daniel S. Weld
  
  CHI | May 2021
  
  Publication
- Is the Most Accurate AI the Best Teammate? Optimizing AI for Teamwork
  
  Gagan Bansal, Besmira Nushi, Ece Kamar, Eric Horvitz, Dan Weld
  
  AAAI 2021 | February 2021
  
  Publication
- Beyond Accuracy: The Role of Mental Models in Human-AI Team Performance
  
  Gagan Bansal, Besmira Nushi, Ece Kamar, Walter Lasecki, Dan Weld, Eric Horvitz
  
  HCOMP 2019 | October 2019
  
  PDF
- Updates in Human-AI Teams: Understanding and Addressing the Performance/Compatibility Tradeoff
  
  Gagan Bansal, Besmira Nushi, Ece Kamar, Dan Weld, Walter Lasecki, Eric Horvitz
  
  AAAI Conference on Artificial Intelligence | January 2019
  
  Publication Github Projet
- The Challenge of Crafting Intelligible Intelligence
  
  Daniel S. Weld, Gagan Bansal
  
  Communications of ACM | October 2018
  
  Publication

- SentinelBench: A Benchmark for Long-Running Monitoring Agents
  
  Matheus Kunzler Maldaner, Adam Fourney, Amanda Swearngin, Hussein Mozannar, Gagan Bansal, Maya Murad, Rafah Hosn, Saleema Amershi
  
  June 2026
  
  arXiv | June 2026
  
  Publication
- Magentic Marketplace: An Open-Source Environment for Studying Agentic Markets
  
  Gagan Bansal, Wenyue Hua, Zezhou Huang, Adam Fourney, Amanda Swearngin, Will Epperson, Tyler Payne, Jake Hofman, Brendan Lucier, Chinmay Singh, Markus Mobius, Akshay Nambi, Archana Yadav, Kevin Gao, David Rothschild, Aleksandrs Slivkins, Daniel G. Goldstein, Hussein Mozannar, Nicole Immorlica, Maya Murad, Matthew Vogel, Subbarao Kambhampati, Eric Horvitz, Saleema Amershi
  
  MSR-TR-2025-50 | October 2025
  
  Publié par Microsoft
  
  Publication Vidéo Vidéo Accès
- Magentic-UI: Towards Human-in-the-loop Agentic Systems
  
  Hussein Mozannar, Gagan Bansal, Cheng Tan, Adam Fourney, Victor Dibia, Jingya Chen, Jack Gerrits, Tyler Payne, Matheus Kunzler Maldaner, Madeleine Grunde-McLaughlin, Eric Zhu, Griffin Bassman, Jacob Alber, Peter Chang, Ricky Loynd, Friederike Niedtner, Ece Kamar, Maya Murad, Rafah Hosn, Saleema Amershi
  
  MSR-TR-2025-40 | July 2025
  
  Publié par Microsoft
  
  Publication Projet
- Interactive Debugging and Steering of Multi-Agent AI Systems
  
  Will Epperson, Gagan Bansal, Victor Dibia, Adam Fourney (adamfo), Jack Gerrits, Erkang (Eric) Zhu, Saleema Amershi
  
  CHI 2025 | April 2025
  
  Publication
- Generation Probabilities Are Not Enough: Uncertainty Highlighting in AI Code Completions
  
  Helena Vasconcelos, Gagan Bansal, Adam Fourney, Q. Vera Liao, Jennifer Wortman Vaughan
  
  ToCHI | April 2025, Vol 32(1)
  
  Publication
- Navigating Rifts in Human-LLM Grounding: Study and Benchmark
  
  Omar Shaikh, Hussein Mozannar, Gagan Bansal, Adam Fourney, Eric Horvitz
  
  ACL | March 2025
  
  Publication
- Challenges in Human-Agent Communication
  
  Gagan Bansal, Jennifer Wortman Vaughan, Saleema Amershi, Eric Horvitz, Adam Fourney, Hussein Mozannar, Victor Dibia, Daniel S. Weld
  
  MSR-TR-2024-53 | December 2024
  
  Publié par Microsoft
  
  Publication Projet
- Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks
  
  Adam Fourney, Gagan Bansal, Hussein Mozannar, Cheng Tan, Eduardo Salinas, Erkang (Eric) Zhu, Friederike Niedtner, Grace Proebsting, Griffin Bassman, Jack Gerrits, Jacob Alber, Peter Chang, Ricky Loynd, Robert West, Victor Dibia, Ahmed Awadallah, Ece Kamar, Rafah Hosn, Saleema Amershi
  
  MSR-TR-2024-47 | November 2024
  
  Publié par Microsoft
  
  Preprint Vidéo Accès
- AutoGen Studio: A No-Code Developer Tool for Building and Debugging Multi-Agent Systems
  
  Victor Dibia, Jingya Chen, Gagan Bansal, Suff Syed, Adam Fourney, Erkang (Eric) Zhu, Chi Wang, Saleema Amershi
  
  August 2024
  
  Preprint
  
  PDF Publication Vidéo Vidéo Projet
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
  
  Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, Erkang (Eric) Zhu, Li Jiang, Xiaoyun Zhang, Shaokun Zhang, Ahmed Awadallah, Ryen W. White, Doug Burger, Chi Wang
  
  COLM 2024 | August 2024
  
  Best Paper, LLM Agents Workshop ICLR'24
  
  Publication Vidéo Vidéo Vidéo Projet
- Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming
  
  Hussein Mozannar, Gagan Bansal, Adam Fourney, Eric Horvitz
  
  CHI 2024 | May 2024
  
  Honorable Mention, CHI 2024
  
  Publication
- Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanations
  
  Valerie Chen, Q. Vera Liao, Jennifer Wortman Vaughan, Gagan Bansal
  
  Proc. ACM Hum.-Comput. Interact. | October 2023, Vol 7
  
  Article 370
  
  PDF Projet
- Aligning Offline Metrics and Human Judgments of Value for Code Generation Models
  
  Victor Dibia, Adam Fourney, Gagan Bansal, Forough Poursabzi, Han Liu, Saleema Amershi
  
  ACL 2023 | June 2023
  
  Publication
- Generation Probabilities are Not Enough: Improving Error Highlighting for AI Code Suggestions
  
  Helena Vasconcelos, Gagan Bansal, Adam Fourney, Q. Vera Liao, Jennifer Wortman Vaughan
  
  NeurIPS Workshop on Human-Centered AI | October 2022
  
  Publication
- Aligning Offline Metrics and Human Judgments of Value of AI-Pair Programmers
  
  Victor Dibia, Adam Fourney, Gagan Bansal, Forough Poursabzi, Han Liu, Saleema Amershi
  
  ACL 2023 | October 2022
  
  Preprint
- Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance
  
  Gagan Bansal, Tongshuang Wu, Joyce Zhou, Raymond Fok, Besmira Nushi, Ece Kamar, Marco Tulio Ribeiro, Daniel S. Weld
  
  CHI | May 2021
  
  Publication
- Is the Most Accurate AI the Best Teammate? Optimizing AI for Teamwork
  
  Gagan Bansal, Besmira Nushi, Ece Kamar, Eric Horvitz, Dan Weld
  
  AAAI 2021 | February 2021
  
  Publication
- Beyond Accuracy: The Role of Mental Models in Human-AI Team Performance
  
  Gagan Bansal, Besmira Nushi, Ece Kamar, Walter Lasecki, Dan Weld, Eric Horvitz
  
  HCOMP 2019 | October 2019
  
  PDF
- Updates in Human-AI Teams: Understanding and Addressing the Performance/Compatibility Tradeoff
  
  Gagan Bansal, Besmira Nushi, Ece Kamar, Dan Weld, Walter Lasecki, Eric Horvitz
  
  AAAI Conference on Artificial Intelligence | January 2019
  
  Publication Github Projet
- The Challenge of Crafting Intelligible Intelligence
  
  Daniel S. Weld, Gagan Bansal
  
  Communications of ACM | October 2018
  
  Publication
- Magentic Marketplace: An Open-Source Environment for Studying Agentic Markets
  
  Gagan Bansal, Wenyue Hua, Zezhou Huang, Adam Fourney, Amanda Swearngin, Will Epperson, Tyler Payne, Jake Hofman, Brendan Lucier, Chinmay Singh, Markus Mobius, Akshay Nambi, Archana Yadav, Kevin Gao, David Rothschild, Aleksandrs Slivkins, Daniel G. Goldstein, Hussein Mozannar, Nicole Immorlica, Maya Murad, Matthew Vogel, Subbarao Kambhampati, Eric Horvitz, Saleema Amershi
  
  MSR-TR-2025-50 | October 2025
  
  Publié par Microsoft
  
  Publication Vidéo Vidéo Accès
- Navigating Rifts in Human-LLM Grounding: Study and Benchmark
  
  Omar Shaikh, Hussein Mozannar, Gagan Bansal, Adam Fourney, Eric Horvitz
  
  ACL | March 2025
  
  Publication
- Interactive Debugging and Steering of Multi-Agent AI Systems
  
  Will Epperson, Gagan Bansal, Victor Dibia, Adam Fourney (adamfo), Jack Gerrits, Erkang (Eric) Zhu, Saleema Amershi
  
  CHI 2025 | April 2025
  
  Publication
- Generation Probabilities Are Not Enough: Uncertainty Highlighting in AI Code Completions
  
  Helena Vasconcelos, Gagan Bansal, Adam Fourney, Q. Vera Liao, Jennifer Wortman Vaughan
  
  ToCHI | April 2025, Vol 32(1)
  
  Publication
- Navigating Rifts in Human-LLM Grounding: Study and Benchmark
  
  Omar Shaikh, Hussein Mozannar, Gagan Bansal, Adam Fourney, Eric Horvitz
  
  ACL | March 2025
  
  Publication
- Challenges in Human-Agent Communication
  
  Gagan Bansal, Jennifer Wortman Vaughan, Saleema Amershi, Eric Horvitz, Adam Fourney, Hussein Mozannar, Victor Dibia, Daniel S. Weld
  
  MSR-TR-2024-53 | December 2024
  
  Publié par Microsoft
  
  Publication Projet
- AutoGen Studio: A No-Code Developer Tool for Building and Debugging Multi-Agent Systems
  
  Victor Dibia, Jingya Chen, Gagan Bansal, Suff Syed, Adam Fourney, Erkang (Eric) Zhu, Chi Wang, Saleema Amershi
  
  August 2024
  
  Preprint
  
  PDF Publication Vidéo Vidéo Projet
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
  
  Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, Erkang (Eric) Zhu, Li Jiang, Xiaoyun Zhang, Shaokun Zhang, Ahmed Awadallah, Ryen W. White, Doug Burger, Chi Wang
  
  COLM 2024 | August 2024
  
  Best Paper, LLM Agents Workshop ICLR'24
  
  Publication Vidéo Vidéo Vidéo Projet
- When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programming
  
  Hussein Mozannar, Gagan Bansal, Adam Fourney, Eric Horvitz
  
  AAAI 2024 | January 2024
  
  PDF Publication
- Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanations
  
  Valerie Chen, Q. Vera Liao, Jennifer Wortman Vaughan, Gagan Bansal
  
  Proc. ACM Hum.-Comput. Interact. | October 2023, Vol 7
  
  Article 370
  
  PDF Projet
- Aligning Offline Metrics and Human Judgments of Value for Code Generation Models
  
  Victor Dibia, Adam Fourney, Gagan Bansal, Forough Poursabzi, Han Liu, Saleema Amershi
  
  ACL 2023 | June 2023
  
  Publication
- Generation Probabilities are Not Enough: Improving Error Highlighting for AI Code Suggestions
  
  Helena Vasconcelos, Gagan Bansal, Adam Fourney, Q. Vera Liao, Jennifer Wortman Vaughan
  
  NeurIPS Workshop on Human-Centered AI | October 2022
  
  Publication
- Aligning Offline Metrics and Human Judgments of Value of AI-Pair Programmers
  
  Victor Dibia, Adam Fourney, Gagan Bansal, Forough Poursabzi, Han Liu, Saleema Amershi
  
  ACL 2023 | October 2022
  
  Preprint
- Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance
  
  Gagan Bansal, Tongshuang Wu, Joyce Zhou, Raymond Fok, Besmira Nushi, Ece Kamar, Marco Tulio Ribeiro, Daniel S. Weld
  
  CHI | May 2021
  
  Publication
- Beyond Accuracy: The Role of Mental Models in Human-AI Team Performance
  
  Gagan Bansal, Besmira Nushi, Ece Kamar, Walter Lasecki, Dan Weld, Eric Horvitz
  
  HCOMP 2019 | October 2019
  
  PDF
- Updates in Human-AI Teams: Understanding and Addressing the Performance/Compatibility Tradeoff
  
  Gagan Bansal, Besmira Nushi, Ece Kamar, Dan Weld, Walter Lasecki, Eric Horvitz
  
  AAAI Conference on Artificial Intelligence | January 2019
  
  Publication Github Projet
- The Challenge of Crafting Intelligible Intelligence
  
  Daniel S. Weld, Gagan Bansal
  
  Communications of ACM | October 2018
  
  Publication
- Aligning Offline Metrics and Human Judgments of Value for Code Generation Models
  
  Victor Dibia, Adam Fourney, Gagan Bansal, Forough Poursabzi, Han Liu, Saleema Amershi
  
  ACL 2023 | June 2023
  
  Publication
- Aligning Offline Metrics and Human Judgments of Value of AI-Pair Programmers
  
  Victor Dibia, Adam Fourney, Gagan Bansal, Forough Poursabzi, Han Liu, Saleema Amershi
  
  ACL 2023 | October 2022
  
  Preprint

- SentinelBench: A Benchmark for Long-Running Monitoring Agents
  
  Matheus Kunzler Maldaner, Adam Fourney, Amanda Swearngin, Hussein Mozannar, Gagan Bansal, Maya Murad, Rafah Hosn, Saleema Amershi
  
  June 2026
  
  arXiv | June 2026
  
  Publication
- Magentic Marketplace: An Open-Source Environment for Studying Agentic Markets
  
  Gagan Bansal, Wenyue Hua, Zezhou Huang, Adam Fourney, Amanda Swearngin, Will Epperson, Tyler Payne, Jake Hofman, Brendan Lucier, Chinmay Singh, Markus Mobius, Akshay Nambi, Archana Yadav, Kevin Gao, David Rothschild, Aleksandrs Slivkins, Daniel G. Goldstein, Hussein Mozannar, Nicole Immorlica, Maya Murad, Matthew Vogel, Subbarao Kambhampati, Eric Horvitz, Saleema Amershi
  
  MSR-TR-2025-50 | October 2025
  
  Publié par Microsoft
  
  Publication Vidéo Vidéo Accès
- Magentic-UI: Towards Human-in-the-loop Agentic Systems
  
  Hussein Mozannar, Gagan Bansal, Cheng Tan, Adam Fourney, Victor Dibia, Jingya Chen, Jack Gerrits, Tyler Payne, Matheus Kunzler Maldaner, Madeleine Grunde-McLaughlin, Eric Zhu, Griffin Bassman, Jacob Alber, Peter Chang, Ricky Loynd, Friederike Niedtner, Ece Kamar, Maya Murad, Rafah Hosn, Saleema Amershi
  
  MSR-TR-2025-40 | July 2025
  
  Publié par Microsoft
  
  Publication Projet
- Challenges in Human-Agent Communication
  
  Gagan Bansal, Jennifer Wortman Vaughan, Saleema Amershi, Eric Horvitz, Adam Fourney, Hussein Mozannar, Victor Dibia, Daniel S. Weld
  
  MSR-TR-2024-53 | December 2024
  
  Publié par Microsoft
  
  Publication Projet
- Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks
  
  Adam Fourney, Gagan Bansal, Hussein Mozannar, Cheng Tan, Eduardo Salinas, Erkang (Eric) Zhu, Friederike Niedtner, Grace Proebsting, Griffin Bassman, Jack Gerrits, Jacob Alber, Peter Chang, Ricky Loynd, Robert West, Victor Dibia, Ahmed Awadallah, Ece Kamar, Rafah Hosn, Saleema Amershi
  
  MSR-TR-2024-47 | November 2024
  
  Publié par Microsoft
  
  Preprint Vidéo Accès
- Interactive Debugging and Steering of Multi-Agent AI Systems
  
  Will Epperson, Gagan Bansal, Victor Dibia, Adam Fourney (adamfo), Jack Gerrits, Erkang (Eric) Zhu, Saleema Amershi
  
  CHI 2025 | April 2025
  
  Publication
- Navigating Rifts in Human-LLM Grounding: Study and Benchmark
  
  Omar Shaikh, Hussein Mozannar, Gagan Bansal, Adam Fourney, Eric Horvitz
  
  ACL | March 2025
  
  Publication
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
  
  Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, Erkang (Eric) Zhu, Li Jiang, Xiaoyun Zhang, Shaokun Zhang, Ahmed Awadallah, Ryen W. White, Doug Burger, Chi Wang
  
  COLM 2024 | August 2024
  
  Best Paper, LLM Agents Workshop ICLR'24
  
  Publication Vidéo Vidéo Vidéo Projet
- Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming
  
  Hussein Mozannar, Gagan Bansal, Adam Fourney, Eric Horvitz
  
  CHI 2024 | May 2024
  
  Honorable Mention, CHI 2024
  
  Publication
- When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programming
  
  Hussein Mozannar, Gagan Bansal, Adam Fourney, Eric Horvitz
  
  AAAI 2024 | January 2024
  
  PDF Publication
- Aligning Offline Metrics and Human Judgments of Value for Code Generation Models
  
  Victor Dibia, Adam Fourney, Gagan Bansal, Forough Poursabzi, Han Liu, Saleema Amershi
  
  ACL 2023 | June 2023
  
  Publication
- Generation Probabilities are Not Enough: Improving Error Highlighting for AI Code Suggestions
  
  Helena Vasconcelos, Gagan Bansal, Adam Fourney, Q. Vera Liao, Jennifer Wortman Vaughan
  
  NeurIPS Workshop on Human-Centered AI | October 2022
  
  Publication
- Aligning Offline Metrics and Human Judgments of Value of AI-Pair Programmers
  
  Victor Dibia, Adam Fourney, Gagan Bansal, Forough Poursabzi, Han Liu, Saleema Amershi
  
  ACL 2023 | October 2022
  
  Preprint
- Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance
  
  Gagan Bansal, Tongshuang Wu, Joyce Zhou, Raymond Fok, Besmira Nushi, Ece Kamar, Marco Tulio Ribeiro, Daniel S. Weld
  
  CHI | May 2021
  
  Publication
- Is the Most Accurate AI the Best Teammate? Optimizing AI for Teamwork
  
  Gagan Bansal, Besmira Nushi, Ece Kamar, Eric Horvitz, Dan Weld
  
  AAAI 2021 | February 2021
  
  Publication
- Beyond Accuracy: The Role of Mental Models in Human-AI Team Performance
  
  Gagan Bansal, Besmira Nushi, Ece Kamar, Walter Lasecki, Dan Weld, Eric Horvitz
  
  HCOMP 2019 | October 2019
  
  PDF
- Updates in Human-AI Teams: Understanding and Addressing the Performance/Compatibility Tradeoff
  
  Gagan Bansal, Besmira Nushi, Ece Kamar, Dan Weld, Walter Lasecki, Eric Horvitz
  
  AAAI Conference on Artificial Intelligence | January 2019
  
  Publication Github Projet
- AutoGen Studio: A No-Code Developer Tool for Building and Debugging Multi-Agent Systems
  
  Victor Dibia, Jingya Chen, Gagan Bansal, Suff Syed, Adam Fourney, Erkang (Eric) Zhu, Chi Wang, Saleema Amershi
  
  August 2024
  
  Preprint
  
  PDF Publication Vidéo Vidéo Projet
- Generation Probabilities Are Not Enough: Uncertainty Highlighting in AI Code Completions
  
  Helena Vasconcelos, Gagan Bansal, Adam Fourney, Q. Vera Liao, Jennifer Wortman Vaughan
  
  ToCHI | April 2025, Vol 32(1)
  
  Publication
- Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanations
  
  Valerie Chen, Q. Vera Liao, Jennifer Wortman Vaughan, Gagan Bansal
  
  Proc. ACM Hum.-Comput. Interact. | October 2023, Vol 7
  
  Article 370
  
  PDF Projet
- The Challenge of Crafting Intelligible Intelligence
  
  Daniel S. Weld, Gagan Bansal
  
  Communications of ACM | October 2018
  
  Publication

Gagan Bansal

Publications

SentinelBench: A Benchmark for Long-Running Monitoring Agents

Magentic Marketplace: An Open-Source Environment for Studying Agentic Markets

Magentic-UI: Towards Human-in-the-loop Agentic Systems

Interactive Debugging and Steering of Multi-Agent AI Systems

Generation Probabilities Are Not Enough: Uncertainty Highlighting in AI Code Completions

Navigating Rifts in Human-LLM Grounding: Study and Benchmark

Challenges in Human-Agent Communication

Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks

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

AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation

Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming

When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programming

Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanations

Aligning Offline Metrics and Human Judgments of Value for Code Generation Models

Generation Probabilities are Not Enough: Improving Error Highlighting for AI Code Suggestions

Aligning Offline Metrics and Human Judgments of Value of AI-Pair Programmers

Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance

Is the Most Accurate AI the Best Teammate? Optimizing AI for Teamwork

Beyond Accuracy: The Role of Mental Models in Human-AI Team Performance

Updates in Human-AI Teams: Understanding and Addressing the Performance/Compatibility Tradeoff

The Challenge of Crafting Intelligible Intelligence

SentinelBench: A Benchmark for Long-Running Monitoring Agents

Magentic Marketplace: An Open-Source Environment for Studying Agentic Markets

Magentic-UI: Towards Human-in-the-loop Agentic Systems

Interactive Debugging and Steering of Multi-Agent AI Systems

Generation Probabilities Are Not Enough: Uncertainty Highlighting in AI Code Completions

Navigating Rifts in Human-LLM Grounding: Study and Benchmark

Challenges in Human-Agent Communication

Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks

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

AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation

Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming

Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanations

Aligning Offline Metrics and Human Judgments of Value for Code Generation Models

Generation Probabilities are Not Enough: Improving Error Highlighting for AI Code Suggestions

Aligning Offline Metrics and Human Judgments of Value of AI-Pair Programmers

Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance

Is the Most Accurate AI the Best Teammate? Optimizing AI for Teamwork

Beyond Accuracy: The Role of Mental Models in Human-AI Team Performance

Updates in Human-AI Teams: Understanding and Addressing the Performance/Compatibility Tradeoff

The Challenge of Crafting Intelligible Intelligence

Magentic Marketplace: An Open-Source Environment for Studying Agentic Markets

Navigating Rifts in Human-LLM Grounding: Study and Benchmark

Interactive Debugging and Steering of Multi-Agent AI Systems

Generation Probabilities Are Not Enough: Uncertainty Highlighting in AI Code Completions

Navigating Rifts in Human-LLM Grounding: Study and Benchmark

Challenges in Human-Agent Communication

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

AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation

When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programming

Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanations

Aligning Offline Metrics and Human Judgments of Value for Code Generation Models

Generation Probabilities are Not Enough: Improving Error Highlighting for AI Code Suggestions

Aligning Offline Metrics and Human Judgments of Value of AI-Pair Programmers

Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance

Beyond Accuracy: The Role of Mental Models in Human-AI Team Performance

Updates in Human-AI Teams: Understanding and Addressing the Performance/Compatibility Tradeoff

The Challenge of Crafting Intelligible Intelligence

Aligning Offline Metrics and Human Judgments of Value for Code Generation Models

Aligning Offline Metrics and Human Judgments of Value of AI-Pair Programmers

SentinelBench: A Benchmark for Long-Running Monitoring Agents

Magentic Marketplace: An Open-Source Environment for Studying Agentic Markets

Magentic-UI: Towards Human-in-the-loop Agentic Systems

Challenges in Human-Agent Communication

Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks

Interactive Debugging and Steering of Multi-Agent AI Systems

Navigating Rifts in Human-LLM Grounding: Study and Benchmark

AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation

Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming

When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programming

Aligning Offline Metrics and Human Judgments of Value for Code Generation Models

Generation Probabilities are Not Enough: Improving Error Highlighting for AI Code Suggestions

Aligning Offline Metrics and Human Judgments of Value of AI-Pair Programmers

Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance

Is the Most Accurate AI the Best Teammate? Optimizing AI for Teamwork

Beyond Accuracy: The Role of Mental Models in Human-AI Team Performance

Updates in Human-AI Teams: Understanding and Addressing the Performance/Compatibility Tradeoff

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