IDEAS Research

Science + Innovation for Next-Gen Productivity

Publications

View by:

- Babysitting AI Agents: A User-Centered Taxonomy and Study of Agentic Delegation Failures
  
  Shravika Mittal, Sunnie S. Y. Kim, Scott Counts, Jennifer Neville, Debarati Das, Philippe Laban
  
  October 2026
  
  arXiv | October 2026
  
  Publication
- TeleTune: Evolving Agent Skills From Offline Telemetry
  
  Justin Chih-Yao Chen, Elias Stengel-Eskin, Yan Chen, Pol Llado, Scott Counts, Mohit Bansal, Ben Van Durme, Harsh Jhamtani, Gaurav Verma
  
  October 2026
  
  Preprint Publication
- From Images to Tasks: Characterizing Multimodal LLM Interactions in the Wild
  
  Jinyi Ye, Scott Counts, Gaurav Verma, Kate Lytvynets, Weiwei Yang
  
  September 2026
  
  Preprint
- How Copilot Changed the Pace of Work in Word — And How We Measured It
  
  Gaurav Verma, Siddharth Suri, Scott Counts
  
  MSR-TR-2026-24 | June 2026
  
  Published by Microsoft
  
  Publication
- Abstracting Cross-Domain Action Sequences into Interpretable Workflows
  
  Gaurav Verma, Scott Counts
  
  June 2026
  
  Preprint
- AI in the Enterprise: How People Use M365 Copilot Chat
  
  Scott Counts, Yan Chen, Jing Dong, Himanshu Sharma, Andrey Zaikin, Rui Hu, Alperen Kok, Gorkem Ozer Yilmaz, Siddharth Suri, Kiran Tomlinson, Sonia Jaffe, Will Wang
  
  May 2026
  
  arXiv | May 2026
  
  Preprint
- The FACTS Leaderboard: A Comprehensive Benchmark for Large Language Model Factuality
  
  Aileen Cheng, Alon Jacovi, A. Globerson, Ben Golan, Charles Kwong, C. Alberti, Connie Tao, Eyal Ben-David, Gaurav Singh Tomar, Lukas Haas, Yonatan Bitton, Adam E. Bloniarz, Ai-Jun Bai, Andrew Wang, A. Siddiqui, Arturo Bajuelos Castillo, Aviel Atias, Chang Liu, Corey Fry, Daniel Balle, Deepanway Ghosal, Doron Kukliansky, Dror Marcus, E. Gribovskaya, Eyal Ofek, Honglei Zhuang, Itay Laish, Jan Ackermann, Lily Wang, Meg Risdal, Megan Barnes, Michael Fink, Mohamed Amin, Moran Ambar, Natan Potikha, Nikita Gupta, Nitzan Katz, Noam Velan, Ofir Roval, Ori Ram, Polina Zablotskaia, Prathamesh Bang, Priyanka Agrawal, R. Ghiya, S. Ganapathy, Simon Baumgartner, Sofia Erell, Sushant Prakash, T. Sellam, Vikram Rao, Xuan-Hui Wang, Yaroslav Akulov, Yu-Long Yang, Zhen Yang, Zhixin Lai, Zhongru Wu, Anca D. Dragan, A. Hassidim, Fernando Pereira, Slav Petrov, Srinivasan Venkatachary, Tulsee Doshi, Y. Matias, S. Goldshtein, Debarati Das
  
  NeurIPS 2026 | December 2025
  
  Publication Publication
- A Demo of GeoQA^3: Towards An Accessible AI-based Question-Answering System for Geoanalytics
  
  Chu Li, Rock Yuren Pang, Arnavi Chheda-Kothary, Ather Sharif, Henok Assalif, Jeffrey Heer, Jon E. Froehlich
  
  Proceedings of the 27th International ACM SIGACCESS Conference on Computers and Accessibility | October 2025
  
  International ACM SIGACCESS Conference on Computers and Accessibility
  
  Publication Publication
- AdaptAgent: Adapting Multimodal Web Agents with Few-Shot Learning from Human Demonstrations
  
  Gaurav Verma, Rachneet Kaur, Nishan Srishankar, Zhen Zeng, Tucker Balch, Manuela Veloso
  
  Meeting of the Association for Computational Linguistics | July 2025
  
  Publication Preprint
- Working with AI: Measuring the Applicability of Generative AI to Occupations
  
  Kiran Tomlinson, Sonia Jaffe, Will Wang, Scott Counts, Siddharth Suri
  
  July 2025
  
  Preprint
- Prototypical Human-AI Collaboration Behaviors from LLM-Assisted Writing in the Wild
  
  Sheshera Mysore, Debarati Das, Hancheng Cao, Bahar Sarrafzadeh
  
  May 2025
  
  arXiv | May 2025
  
  Publication Author's Version Publication
- A Framework for Situating Innovations, Opportunities, and Challenges in Advancing Vertical Systems with Large AI Models
  
  Gaurav Verma, Jiawei Zhou, Mohit Chandra, Srijan Kumar, Munmun De Choudhury
  
  AAAI/ACM Conference on AI, Ethics, and Society | April 2025
  
  Publication Preprint Author's Version
- Interpretable User Satisfaction Estimation for Conversational Systems with Large Language Models
  
  Ying-Chun Lin, Jennifer Neville, Jack W. Stokes, Longqi Yang, Tara Safavi, Mengting Wan, Scott Counts, Siddharth Suri, Reid Andersen, Xiaofeng Xu, Deepak Gupta, Sujay Kumar Jauhar, Xia Song, Georg Buscher, Saurabh Tiwary, Brent Hecht, Jaime Teevan
  
  ACL | August 2024
  
  Publication Project
- The Use of Generative Search Engines for Knowledge Work and Complex Tasks
  
  Siddharth Suri, Scott Counts, Leijie Wang, Chacha Chen, Mengting Wan, Tara Safavi, Jennifer Neville, Chirag Shah, Ryen W. White, Reid Andersen, Georg Buscher, Sathish Manivannan, Nagu Rangan, Longqi Yang
  
  March 2024
  
  Publication Preprint Project
- TnT-LLM: Text Mining at Scale with Large Language Models
  
  Mengting Wan, Tara Safavi, Sujay Kumar Jauhar, Yujin Kim, Scott Counts, Jennifer Neville, Siddharth Suri, Chirag Shah, Ryen W. White, Longqi Yang, Reid Andersen, Georg Buscher, Dhruv Joshi, Nagu Rangan
  
  KDD | March 2024
  
  Publication Project

- Babysitting AI Agents: A User-Centered Taxonomy and Study of Agentic Delegation Failures
  
  Shravika Mittal, Sunnie S. Y. Kim, Scott Counts, Jennifer Neville, Debarati Das, Philippe Laban
  
  October 2026
  
  arXiv | October 2026
  
  Publication
- TeleTune: Evolving Agent Skills From Offline Telemetry
  
  Justin Chih-Yao Chen, Elias Stengel-Eskin, Yan Chen, Pol Llado, Scott Counts, Mohit Bansal, Ben Van Durme, Harsh Jhamtani, Gaurav Verma
  
  October 2026
  
  Preprint Publication
- From Images to Tasks: Characterizing Multimodal LLM Interactions in the Wild
  
  Jinyi Ye, Scott Counts, Gaurav Verma, Kate Lytvynets, Weiwei Yang
  
  September 2026
  
  Preprint
- How Copilot Changed the Pace of Work in Word — And How We Measured It
  
  Gaurav Verma, Siddharth Suri, Scott Counts
  
  MSR-TR-2026-24 | June 2026
  
  Published by Microsoft
  
  Publication
- Abstracting Cross-Domain Action Sequences into Interpretable Workflows
  
  Gaurav Verma, Scott Counts
  
  June 2026
  
  Preprint
- AI in the Enterprise: How People Use M365 Copilot Chat
  
  Scott Counts, Yan Chen, Jing Dong, Himanshu Sharma, Andrey Zaikin, Rui Hu, Alperen Kok, Gorkem Ozer Yilmaz, Siddharth Suri, Kiran Tomlinson, Sonia Jaffe, Will Wang
  
  May 2026
  
  arXiv | May 2026
  
  Preprint
- The FACTS Leaderboard: A Comprehensive Benchmark for Large Language Model Factuality
  
  Aileen Cheng, Alon Jacovi, A. Globerson, Ben Golan, Charles Kwong, C. Alberti, Connie Tao, Eyal Ben-David, Gaurav Singh Tomar, Lukas Haas, Yonatan Bitton, Adam E. Bloniarz, Ai-Jun Bai, Andrew Wang, A. Siddiqui, Arturo Bajuelos Castillo, Aviel Atias, Chang Liu, Corey Fry, Daniel Balle, Deepanway Ghosal, Doron Kukliansky, Dror Marcus, E. Gribovskaya, Eyal Ofek, Honglei Zhuang, Itay Laish, Jan Ackermann, Lily Wang, Meg Risdal, Megan Barnes, Michael Fink, Mohamed Amin, Moran Ambar, Natan Potikha, Nikita Gupta, Nitzan Katz, Noam Velan, Ofir Roval, Ori Ram, Polina Zablotskaia, Prathamesh Bang, Priyanka Agrawal, R. Ghiya, S. Ganapathy, Simon Baumgartner, Sofia Erell, Sushant Prakash, T. Sellam, Vikram Rao, Xuan-Hui Wang, Yaroslav Akulov, Yu-Long Yang, Zhen Yang, Zhixin Lai, Zhongru Wu, Anca D. Dragan, A. Hassidim, Fernando Pereira, Slav Petrov, Srinivasan Venkatachary, Tulsee Doshi, Y. Matias, S. Goldshtein, Debarati Das
  
  NeurIPS 2026 | December 2025
  
  Publication Publication
- A Demo of GeoQA^3: Towards An Accessible AI-based Question-Answering System for Geoanalytics
  
  Chu Li, Rock Yuren Pang, Arnavi Chheda-Kothary, Ather Sharif, Henok Assalif, Jeffrey Heer, Jon E. Froehlich
  
  Proceedings of the 27th International ACM SIGACCESS Conference on Computers and Accessibility | October 2025
  
  International ACM SIGACCESS Conference on Computers and Accessibility
  
  Publication Publication
- AdaptAgent: Adapting Multimodal Web Agents with Few-Shot Learning from Human Demonstrations
  
  Gaurav Verma, Rachneet Kaur, Nishan Srishankar, Zhen Zeng, Tucker Balch, Manuela Veloso
  
  Meeting of the Association for Computational Linguistics | July 2025
  
  Publication Preprint
- Working with AI: Measuring the Applicability of Generative AI to Occupations
  
  Kiran Tomlinson, Sonia Jaffe, Will Wang, Scott Counts, Siddharth Suri
  
  July 2025
  
  Preprint
- Prototypical Human-AI Collaboration Behaviors from LLM-Assisted Writing in the Wild
  
  Sheshera Mysore, Debarati Das, Hancheng Cao, Bahar Sarrafzadeh
  
  May 2025
  
  arXiv | May 2025
  
  Publication Author's Version Publication
- A Framework for Situating Innovations, Opportunities, and Challenges in Advancing Vertical Systems with Large AI Models
  
  Gaurav Verma, Jiawei Zhou, Mohit Chandra, Srijan Kumar, Munmun De Choudhury
  
  AAAI/ACM Conference on AI, Ethics, and Society | April 2025
  
  Publication Preprint Author's Version
- Interpretable User Satisfaction Estimation for Conversational Systems with Large Language Models
  
  Ying-Chun Lin, Jennifer Neville, Jack W. Stokes, Longqi Yang, Tara Safavi, Mengting Wan, Scott Counts, Siddharth Suri, Reid Andersen, Xiaofeng Xu, Deepak Gupta, Sujay Kumar Jauhar, Xia Song, Georg Buscher, Saurabh Tiwary, Brent Hecht, Jaime Teevan
  
  ACL | August 2024
  
  Publication Project
- The Use of Generative Search Engines for Knowledge Work and Complex Tasks
  
  Siddharth Suri, Scott Counts, Leijie Wang, Chacha Chen, Mengting Wan, Tara Safavi, Jennifer Neville, Chirag Shah, Ryen W. White, Reid Andersen, Georg Buscher, Sathish Manivannan, Nagu Rangan, Longqi Yang
  
  March 2024
  
  Publication Preprint Project
- TnT-LLM: Text Mining at Scale with Large Language Models
  
  Mengting Wan, Tara Safavi, Sujay Kumar Jauhar, Yujin Kim, Scott Counts, Jennifer Neville, Siddharth Suri, Chirag Shah, Ryen W. White, Longqi Yang, Reid Andersen, Georg Buscher, Dhruv Joshi, Nagu Rangan
  
  KDD | March 2024
  
  Publication Project
- Babysitting AI Agents: A User-Centered Taxonomy and Study of Agentic Delegation Failures
  
  Shravika Mittal, Sunnie S. Y. Kim, Scott Counts, Jennifer Neville, Debarati Das, Philippe Laban
  
  October 2026
  
  arXiv | October 2026
  
  Publication
- A Demo of GeoQA^3: Towards An Accessible AI-based Question-Answering System for Geoanalytics
  
  Chu Li, Rock Yuren Pang, Arnavi Chheda-Kothary, Ather Sharif, Henok Assalif, Jeffrey Heer, Jon E. Froehlich
  
  Proceedings of the 27th International ACM SIGACCESS Conference on Computers and Accessibility | October 2025
  
  International ACM SIGACCESS Conference on Computers and Accessibility
  
  Publication Publication
- The FACTS Leaderboard: A Comprehensive Benchmark for Large Language Model Factuality
  
  Aileen Cheng, Alon Jacovi, A. Globerson, Ben Golan, Charles Kwong, C. Alberti, Connie Tao, Eyal Ben-David, Gaurav Singh Tomar, Lukas Haas, Yonatan Bitton, Adam E. Bloniarz, Ai-Jun Bai, Andrew Wang, A. Siddiqui, Arturo Bajuelos Castillo, Aviel Atias, Chang Liu, Corey Fry, Daniel Balle, Deepanway Ghosal, Doron Kukliansky, Dror Marcus, E. Gribovskaya, Eyal Ofek, Honglei Zhuang, Itay Laish, Jan Ackermann, Lily Wang, Meg Risdal, Megan Barnes, Michael Fink, Mohamed Amin, Moran Ambar, Natan Potikha, Nikita Gupta, Nitzan Katz, Noam Velan, Ofir Roval, Ori Ram, Polina Zablotskaia, Prathamesh Bang, Priyanka Agrawal, R. Ghiya, S. Ganapathy, Simon Baumgartner, Sofia Erell, Sushant Prakash, T. Sellam, Vikram Rao, Xuan-Hui Wang, Yaroslav Akulov, Yu-Long Yang, Zhen Yang, Zhixin Lai, Zhongru Wu, Anca D. Dragan, A. Hassidim, Fernando Pereira, Slav Petrov, Srinivasan Venkatachary, Tulsee Doshi, Y. Matias, S. Goldshtein, Debarati Das
  
  NeurIPS 2026 | December 2025
  
  Publication Publication
- AdaptAgent: Adapting Multimodal Web Agents with Few-Shot Learning from Human Demonstrations
  
  Gaurav Verma, Rachneet Kaur, Nishan Srishankar, Zhen Zeng, Tucker Balch, Manuela Veloso
  
  Meeting of the Association for Computational Linguistics | July 2025
  
  Publication Preprint
- Prototypical Human-AI Collaboration Behaviors from LLM-Assisted Writing in the Wild
  
  Sheshera Mysore, Debarati Das, Hancheng Cao, Bahar Sarrafzadeh
  
  May 2025
  
  arXiv | May 2025
  
  Publication Author's Version Publication
- A Framework for Situating Innovations, Opportunities, and Challenges in Advancing Vertical Systems with Large AI Models
  
  Gaurav Verma, Jiawei Zhou, Mohit Chandra, Srijan Kumar, Munmun De Choudhury
  
  AAAI/ACM Conference on AI, Ethics, and Society | April 2025
  
  Publication Preprint Author's Version
- The FACTS Leaderboard: A Comprehensive Benchmark for Large Language Model Factuality
  
  Aileen Cheng, Alon Jacovi, A. Globerson, Ben Golan, Charles Kwong, C. Alberti, Connie Tao, Eyal Ben-David, Gaurav Singh Tomar, Lukas Haas, Yonatan Bitton, Adam E. Bloniarz, Ai-Jun Bai, Andrew Wang, A. Siddiqui, Arturo Bajuelos Castillo, Aviel Atias, Chang Liu, Corey Fry, Daniel Balle, Deepanway Ghosal, Doron Kukliansky, Dror Marcus, E. Gribovskaya, Eyal Ofek, Honglei Zhuang, Itay Laish, Jan Ackermann, Lily Wang, Meg Risdal, Megan Barnes, Michael Fink, Mohamed Amin, Moran Ambar, Natan Potikha, Nikita Gupta, Nitzan Katz, Noam Velan, Ofir Roval, Ori Ram, Polina Zablotskaia, Prathamesh Bang, Priyanka Agrawal, R. Ghiya, S. Ganapathy, Simon Baumgartner, Sofia Erell, Sushant Prakash, T. Sellam, Vikram Rao, Xuan-Hui Wang, Yaroslav Akulov, Yu-Long Yang, Zhen Yang, Zhixin Lai, Zhongru Wu, Anca D. Dragan, A. Hassidim, Fernando Pereira, Slav Petrov, Srinivasan Venkatachary, Tulsee Doshi, Y. Matias, S. Goldshtein, Debarati Das
  
  NeurIPS 2026 | December 2025
  
  Publication Publication
- Interpretable User Satisfaction Estimation for Conversational Systems with Large Language Models
  
  Ying-Chun Lin, Jennifer Neville, Jack W. Stokes, Longqi Yang, Tara Safavi, Mengting Wan, Scott Counts, Siddharth Suri, Reid Andersen, Xiaofeng Xu, Deepak Gupta, Sujay Kumar Jauhar, Xia Song, Georg Buscher, Saurabh Tiwary, Brent Hecht, Jaime Teevan
  
  ACL | August 2024
  
  Publication Project
- The Use of Generative Search Engines for Knowledge Work and Complex Tasks
  
  Siddharth Suri, Scott Counts, Leijie Wang, Chacha Chen, Mengting Wan, Tara Safavi, Jennifer Neville, Chirag Shah, Ryen W. White, Reid Andersen, Georg Buscher, Sathish Manivannan, Nagu Rangan, Longqi Yang
  
  March 2024
  
  Publication Preprint Project
- TnT-LLM: Text Mining at Scale with Large Language Models
  
  Mengting Wan, Tara Safavi, Sujay Kumar Jauhar, Yujin Kim, Scott Counts, Jennifer Neville, Siddharth Suri, Chirag Shah, Ryen W. White, Longqi Yang, Reid Andersen, Georg Buscher, Dhruv Joshi, Nagu Rangan
  
  KDD | March 2024
  
  Publication Project
- A Demo of GeoQA^3: Towards An Accessible AI-based Question-Answering System for Geoanalytics
  
  Chu Li, Rock Yuren Pang, Arnavi Chheda-Kothary, Ather Sharif, Henok Assalif, Jeffrey Heer, Jon E. Froehlich
  
  Proceedings of the 27th International ACM SIGACCESS Conference on Computers and Accessibility | October 2025
  
  International ACM SIGACCESS Conference on Computers and Accessibility
  
  Publication Publication
- How Copilot Changed the Pace of Work in Word — And How We Measured It
  
  Gaurav Verma, Siddharth Suri, Scott Counts
  
  MSR-TR-2026-24 | June 2026
  
  Published by Microsoft
  
  Publication
- AI in the Enterprise: How People Use M365 Copilot Chat
  
  Scott Counts, Yan Chen, Jing Dong, Himanshu Sharma, Andrey Zaikin, Rui Hu, Alperen Kok, Gorkem Ozer Yilmaz, Siddharth Suri, Kiran Tomlinson, Sonia Jaffe, Will Wang
  
  May 2026
  
  arXiv | May 2026
  
  Preprint
- The Use of Generative Search Engines for Knowledge Work and Complex Tasks
  
  Siddharth Suri, Scott Counts, Leijie Wang, Chacha Chen, Mengting Wan, Tara Safavi, Jennifer Neville, Chirag Shah, Ryen W. White, Reid Andersen, Georg Buscher, Sathish Manivannan, Nagu Rangan, Longqi Yang
  
  March 2024
  
  Publication Preprint Project
- AI in the Enterprise: How People Use M365 Copilot Chat
  
  Scott Counts, Yan Chen, Jing Dong, Himanshu Sharma, Andrey Zaikin, Rui Hu, Alperen Kok, Gorkem Ozer Yilmaz, Siddharth Suri, Kiran Tomlinson, Sonia Jaffe, Will Wang
  
  May 2026
  
  arXiv | May 2026
  
  Preprint
- Working with AI: Measuring the Applicability of Generative AI to Occupations
  
  Kiran Tomlinson, Sonia Jaffe, Will Wang, Scott Counts, Siddharth Suri
  
  July 2025
  
  Preprint

- Babysitting AI Agents: A User-Centered Taxonomy and Study of Agentic Delegation Failures
  
  Shravika Mittal, Sunnie S. Y. Kim, Scott Counts, Jennifer Neville, Debarati Das, Philippe Laban
  
  October 2026
  
  arXiv | October 2026
  
  Publication
- AI in the Enterprise: How People Use M365 Copilot Chat
  
  Scott Counts, Yan Chen, Jing Dong, Himanshu Sharma, Andrey Zaikin, Rui Hu, Alperen Kok, Gorkem Ozer Yilmaz, Siddharth Suri, Kiran Tomlinson, Sonia Jaffe, Will Wang
  
  May 2026
  
  arXiv | May 2026
  
  Preprint
- Prototypical Human-AI Collaboration Behaviors from LLM-Assisted Writing in the Wild
  
  Sheshera Mysore, Debarati Das, Hancheng Cao, Bahar Sarrafzadeh
  
  May 2025
  
  arXiv | May 2025
  
  Publication Author's Version Publication
- The FACTS Leaderboard: A Comprehensive Benchmark for Large Language Model Factuality
  
  Aileen Cheng, Alon Jacovi, A. Globerson, Ben Golan, Charles Kwong, C. Alberti, Connie Tao, Eyal Ben-David, Gaurav Singh Tomar, Lukas Haas, Yonatan Bitton, Adam E. Bloniarz, Ai-Jun Bai, Andrew Wang, A. Siddiqui, Arturo Bajuelos Castillo, Aviel Atias, Chang Liu, Corey Fry, Daniel Balle, Deepanway Ghosal, Doron Kukliansky, Dror Marcus, E. Gribovskaya, Eyal Ofek, Honglei Zhuang, Itay Laish, Jan Ackermann, Lily Wang, Meg Risdal, Megan Barnes, Michael Fink, Mohamed Amin, Moran Ambar, Natan Potikha, Nikita Gupta, Nitzan Katz, Noam Velan, Ofir Roval, Ori Ram, Polina Zablotskaia, Prathamesh Bang, Priyanka Agrawal, R. Ghiya, S. Ganapathy, Simon Baumgartner, Sofia Erell, Sushant Prakash, T. Sellam, Vikram Rao, Xuan-Hui Wang, Yaroslav Akulov, Yu-Long Yang, Zhen Yang, Zhixin Lai, Zhongru Wu, Anca D. Dragan, A. Hassidim, Fernando Pereira, Slav Petrov, Srinivasan Venkatachary, Tulsee Doshi, Y. Matias, S. Goldshtein, Debarati Das
  
  NeurIPS 2026 | December 2025
  
  Publication Publication
- A Demo of GeoQA^3: Towards An Accessible AI-based Question-Answering System for Geoanalytics
  
  Chu Li, Rock Yuren Pang, Arnavi Chheda-Kothary, Ather Sharif, Henok Assalif, Jeffrey Heer, Jon E. Froehlich
  
  Proceedings of the 27th International ACM SIGACCESS Conference on Computers and Accessibility | October 2025
  
  International ACM SIGACCESS Conference on Computers and Accessibility
  
  Publication Publication
- AdaptAgent: Adapting Multimodal Web Agents with Few-Shot Learning from Human Demonstrations
  
  Gaurav Verma, Rachneet Kaur, Nishan Srishankar, Zhen Zeng, Tucker Balch, Manuela Veloso
  
  Meeting of the Association for Computational Linguistics | July 2025
  
  Publication Preprint
- A Framework for Situating Innovations, Opportunities, and Challenges in Advancing Vertical Systems with Large AI Models
  
  Gaurav Verma, Jiawei Zhou, Mohit Chandra, Srijan Kumar, Munmun De Choudhury
  
  AAAI/ACM Conference on AI, Ethics, and Society | April 2025
  
  Publication Preprint Author's Version
- Interpretable User Satisfaction Estimation for Conversational Systems with Large Language Models
  
  Ying-Chun Lin, Jennifer Neville, Jack W. Stokes, Longqi Yang, Tara Safavi, Mengting Wan, Scott Counts, Siddharth Suri, Reid Andersen, Xiaofeng Xu, Deepak Gupta, Sujay Kumar Jauhar, Xia Song, Georg Buscher, Saurabh Tiwary, Brent Hecht, Jaime Teevan
  
  ACL | August 2024
  
  Publication Project
- TnT-LLM: Text Mining at Scale with Large Language Models
  
  Mengting Wan, Tara Safavi, Sujay Kumar Jauhar, Yujin Kim, Scott Counts, Jennifer Neville, Siddharth Suri, Chirag Shah, Ryen W. White, Longqi Yang, Reid Andersen, Georg Buscher, Dhruv Joshi, Nagu Rangan
  
  KDD | March 2024
  
  Publication Project
- A Demo of GeoQA^3: Towards An Accessible AI-based Question-Answering System for Geoanalytics
  
  Chu Li, Rock Yuren Pang, Arnavi Chheda-Kothary, Ather Sharif, Henok Assalif, Jeffrey Heer, Jon E. Froehlich
  
  Proceedings of the 27th International ACM SIGACCESS Conference on Computers and Accessibility | October 2025
  
  International ACM SIGACCESS Conference on Computers and Accessibility
  
  Publication Publication
- A Demo of GeoQA^3: Towards An Accessible AI-based Question-Answering System for Geoanalytics
  
  Chu Li, Rock Yuren Pang, Arnavi Chheda-Kothary, Ather Sharif, Henok Assalif, Jeffrey Heer, Jon E. Froehlich
  
  Proceedings of the 27th International ACM SIGACCESS Conference on Computers and Accessibility | October 2025
  
  International ACM SIGACCESS Conference on Computers and Accessibility
  
  Publication Publication
- TeleTune: Evolving Agent Skills From Offline Telemetry
  
  Justin Chih-Yao Chen, Elias Stengel-Eskin, Yan Chen, Pol Llado, Scott Counts, Mohit Bansal, Ben Van Durme, Harsh Jhamtani, Gaurav Verma
  
  October 2026
  
  Preprint Publication
- From Images to Tasks: Characterizing Multimodal LLM Interactions in the Wild
  
  Jinyi Ye, Scott Counts, Gaurav Verma, Kate Lytvynets, Weiwei Yang
  
  September 2026
  
  Preprint
- Abstracting Cross-Domain Action Sequences into Interpretable Workflows
  
  Gaurav Verma, Scott Counts
  
  June 2026
  
  Preprint
- Working with AI: Measuring the Applicability of Generative AI to Occupations
  
  Kiran Tomlinson, Sonia Jaffe, Will Wang, Scott Counts, Siddharth Suri
  
  July 2025
  
  Preprint
- The Use of Generative Search Engines for Knowledge Work and Complex Tasks
  
  Siddharth Suri, Scott Counts, Leijie Wang, Chacha Chen, Mengting Wan, Tara Safavi, Jennifer Neville, Chirag Shah, Ryen W. White, Reid Andersen, Georg Buscher, Sathish Manivannan, Nagu Rangan, Longqi Yang
  
  March 2024
  
  Publication Preprint Project
- How Copilot Changed the Pace of Work in Word — And How We Measured It
  
  Gaurav Verma, Siddharth Suri, Scott Counts
  
  MSR-TR-2026-24 | June 2026
  
  Published by Microsoft
  
  Publication

IDEAS Research

Publications

Babysitting AI Agents: A User-Centered Taxonomy and Study of Agentic Delegation Failures

TeleTune: Evolving Agent Skills From Offline Telemetry

From Images to Tasks: Characterizing Multimodal LLM Interactions in the Wild

How Copilot Changed the Pace of Work in Word — And How We Measured It

Abstracting Cross-Domain Action Sequences into Interpretable Workflows

AI in the Enterprise: How People Use M365 Copilot Chat

The FACTS Leaderboard: A Comprehensive Benchmark for Large Language Model Factuality

A Demo of GeoQA^3: Towards An Accessible AI-based Question-Answering System for Geoanalytics

AdaptAgent: Adapting Multimodal Web Agents with Few-Shot Learning from Human Demonstrations

Working with AI: Measuring the Applicability of Generative AI to Occupations

Prototypical Human-AI Collaboration Behaviors from LLM-Assisted Writing in the Wild

A Framework for Situating Innovations, Opportunities, and Challenges in Advancing Vertical Systems with Large AI Models

Interpretable User Satisfaction Estimation for Conversational Systems with Large Language Models

The Use of Generative Search Engines for Knowledge Work and Complex Tasks

TnT-LLM: Text Mining at Scale with Large Language Models

Babysitting AI Agents: A User-Centered Taxonomy and Study of Agentic Delegation Failures

TeleTune: Evolving Agent Skills From Offline Telemetry

From Images to Tasks: Characterizing Multimodal LLM Interactions in the Wild

How Copilot Changed the Pace of Work in Word — And How We Measured It

Abstracting Cross-Domain Action Sequences into Interpretable Workflows

AI in the Enterprise: How People Use M365 Copilot Chat

The FACTS Leaderboard: A Comprehensive Benchmark for Large Language Model Factuality

A Demo of GeoQA^3: Towards An Accessible AI-based Question-Answering System for Geoanalytics

AdaptAgent: Adapting Multimodal Web Agents with Few-Shot Learning from Human Demonstrations

Working with AI: Measuring the Applicability of Generative AI to Occupations

Prototypical Human-AI Collaboration Behaviors from LLM-Assisted Writing in the Wild

A Framework for Situating Innovations, Opportunities, and Challenges in Advancing Vertical Systems with Large AI Models

Interpretable User Satisfaction Estimation for Conversational Systems with Large Language Models

The Use of Generative Search Engines for Knowledge Work and Complex Tasks

TnT-LLM: Text Mining at Scale with Large Language Models

Babysitting AI Agents: A User-Centered Taxonomy and Study of Agentic Delegation Failures

A Demo of GeoQA^3: Towards An Accessible AI-based Question-Answering System for Geoanalytics

The FACTS Leaderboard: A Comprehensive Benchmark for Large Language Model Factuality

AdaptAgent: Adapting Multimodal Web Agents with Few-Shot Learning from Human Demonstrations

Prototypical Human-AI Collaboration Behaviors from LLM-Assisted Writing in the Wild

A Framework for Situating Innovations, Opportunities, and Challenges in Advancing Vertical Systems with Large AI Models

The FACTS Leaderboard: A Comprehensive Benchmark for Large Language Model Factuality

Interpretable User Satisfaction Estimation for Conversational Systems with Large Language Models

The Use of Generative Search Engines for Knowledge Work and Complex Tasks

TnT-LLM: Text Mining at Scale with Large Language Models

A Demo of GeoQA^3: Towards An Accessible AI-based Question-Answering System for Geoanalytics

How Copilot Changed the Pace of Work in Word — And How We Measured It

AI in the Enterprise: How People Use M365 Copilot Chat

The Use of Generative Search Engines for Knowledge Work and Complex Tasks

AI in the Enterprise: How People Use M365 Copilot Chat

Working with AI: Measuring the Applicability of Generative AI to Occupations

Babysitting AI Agents: A User-Centered Taxonomy and Study of Agentic Delegation Failures

AI in the Enterprise: How People Use M365 Copilot Chat

Prototypical Human-AI Collaboration Behaviors from LLM-Assisted Writing in the Wild

The FACTS Leaderboard: A Comprehensive Benchmark for Large Language Model Factuality

A Demo of GeoQA^3: Towards An Accessible AI-based Question-Answering System for Geoanalytics

AdaptAgent: Adapting Multimodal Web Agents with Few-Shot Learning from Human Demonstrations

A Framework for Situating Innovations, Opportunities, and Challenges in Advancing Vertical Systems with Large AI Models

Interpretable User Satisfaction Estimation for Conversational Systems with Large Language Models

TnT-LLM: Text Mining at Scale with Large Language Models

A Demo of GeoQA^3: Towards An Accessible AI-based Question-Answering System for Geoanalytics

A Demo of GeoQA^3: Towards An Accessible AI-based Question-Answering System for Geoanalytics

TeleTune: Evolving Agent Skills From Offline Telemetry

From Images to Tasks: Characterizing Multimodal LLM Interactions in the Wild

Abstracting Cross-Domain Action Sequences into Interpretable Workflows

Working with AI: Measuring the Applicability of Generative AI to Occupations

The Use of Generative Search Engines for Knowledge Work and Complex Tasks

How Copilot Changed the Pace of Work in Word — And How We Measured It