About the Program

The keynotes, workshops, posters and demos, and doctoral consortium were joint efforts between the two conferences. Those programs were planned by shared committees, and the accepted content below reflects submissions from both communities.

Titles will link to PDFs as camera-ready versions become available.

Accepted HCOMP Papers

Accepted HCOMP papers are published in the HCOMP 2026 conference proceedings in the ACM Digital Library.

• Adapting Socio-Technical Congruence to Human-Agent Collectives

  Jonas Oppenlaender, Aku Visuri and Simo Hosio

• Adaptive Selection of Effective AI Assistance in AI-assisted Decision Making Using Multi-Armed Bandits

  Zhuoyan Li, Ze Ma, Shishuang He, Zhuoran Lu, Ziang Xiao and Ming Yin

• AgentDynEx: Nudging the Mechanics and Dynamics of Multi-Agent Simulations

  Jenny Ma, Riya Sahni, Karthik Sreedhar and Lydia Chilton

• Beyond Truth Discovery: A Two-Stage Framework to Assess the Severity of False Claim during Disasters

  Ruichen Yao, Tejna Dasari, Gulshat Baispay, Aizhan Zaurbek, Yifan Liu, Yaokun Liu, Zelin Li and Dong Wang

• DoubleAgents: Interactive Simulations for Alignment in Agentic AI

  Tao Long, Xuanming Zhang, Sitong Wang, Zhou Yu and Lydia Chilton

• Easy to Read, Easy to Trust: How Processing Fluency in LLM Explanations Drives Over-Reliance in Hate Speech Moderation

  Bing Tuo, Tim Miller and Gianluca Demartini

• Exploring the Design Space of AI Simulation-Based Communication Training: A Qualitative Study of Online Peer Counselor Preferences

  Jessica Mindel, Sijia Xie, Yee Kit Chan, Holly Swartz, Robert Kraut, Haiyi Zhu, Anna Fang and Tongshuang Wu

• FIBB: Capturing False Information Beliefs and Behaviors Across Physical and Online Environments

  Mung Yao Jia, Niharika Bhattacharjee, Aryan Kapadia and Dong Wang

• From Answers to Audit Opinions: Cost-Aware Expert Verification of Financial Artifacts from Tool-Using LLM Agents

  Jiawei Li

• Guiding Worker Self-Selection in Crowdsourcing Contests: An LLM-Augmented Algorithmic Approach

  Nguyen Thach, Hau Chan, David Parkes and Karim Lakhani

• How AI Assistance Affects Human Skill Development: A Study of Learning with Logic Puzzles

  Shang Wu, Catarina Belem, Shuyuan Fu, Mark Steyvers and Padhraic Smyth

• Information Satisfaction: A Reader-Centered Axis for Summarization Evaluation

  Isabel Cachola, William Walden, Reno Kriz and Mark Dredze

• Looks Can be Deceiving: Annotator and Reviewer Performance Across Imagery Scales In Aerial Damage Assessment

  Thomas Manzini, Priyankari Perali, Raisa Karnik, Stephen Johnson and Robin Murphy

• Measuring Proof Burden in Public Bounty Listings: A RentAHuman Case Study

  Iman YeckehZaare

• One AI Signal, Many Human Judgments: A Bayesian Cascade Analysis of AI-based Credibility Indicators in Online Information Spread

  Zhuoran Lu, Weilong Wang, Yangyang Yu, Xinru Wang, Zhuoyan Li, Zhiwei Liu and Sophia Ananiadou

• Partner-Adaptive Delegation in Ad Hoc Teamwork

  Duy Nhat Phan and Thuy Ngoc Nguyen

• Qualification by Calibration: A Readable Benchmark for Admitting Language Models to Human-Computation Tasks

  Carlos Toxtli and Manuel Delaflor

• Schemex: Discovering Structural Abstractions from Examples

  Sitong Wang, Samia Menon, Dingzeyu Li, Xiaojuan Ma, Richard Zemel and Lydia Chilton

• The Belief Update Gate: Separating Inertia from Learning in Human–AI Interaction

  Shreyan Biswas, Alexander Erlei and Ujwal Gadiraju

• Towards Actionable Surgical Team Dynamics: from Teamwork to Counterfactual Annotations

  Vincenzo Marco De Luca, Antonio Longa and Andrea Passerini

• When AI Says "I have been in similar situations": Synthetic Lived Experience in Peer-like Caregiver Support

  Drishti Goel, Agam Goyal, Veda Duddu, Olivia Pal, Violeta Rodriguez, Daniel Brown, Ravi Karkar, Dong Whi Yoo and Koustuv Saha

• When the Interviewer Is a Bot: Behavior, Breakdowns, and Trust in MLLM-Led Interviews

  He Zhang, Kambinachi Chukwuma, Chanmin Kim and John Carroll

Accepted HCOMP Talks

• Behavioral Drivers of the Jagged Frontier in Human-AI Collaboration

  Harang Ju and Sinan Aral

• Cognitive Security for Human-AI Systems

  Utsav Gupta, Eric Heng, Andreas Haupt and Brett Frischmann

• Enhancing LLM-Based Data Annotation through Error Decomposition: A Human-in-the-Loop Evaluation Paradigm

  Zhen Xu, Vedant Khatri, Yijun Dai, Xiner Liu, Siyan Li, Xuanming Zhang and Renzhe Yu

• Escaping the Nash Trap: Structural Estimation and Alignment of Strategic Reasoning in Large Language Models

  Jiannan Xu, Yongkang Duan, Jane Yi Jiang and Jiding Zhang

• Interactive Human-AI Alignment: Interaction Mechanisms as Building Blocks for Alignment Design

  Tao Long and Lydia Chilton

• The Polymath Plus Project: AI-mediated human collaboration to advance mathematical discovery

  Pietro Michelucci, Sam Shaaban, Jason Dyer, Michael Stillman, Marc Salo, Bruno Gianni, Caroline Nickerson, Margaret Lane, Marina Weis-Haggerty and Joaquín Peréz

Keynotes

Three keynote speakers span industry, academia, and government, with one talk on each day of the conference. Click any speaker to view their talk title, abstract, and biography.

• Industry • Joint Keynote
  

  Eric Horvitz

  Chief Scientific Officer

  Microsoft

  Monday, September 28, 2026

  9:15 AM – 10:30 AM EDT

  View Talk & Bio
• Academia • HCOMP Keynote
  

  Diyi Yang

  Assistant Professor of Computer Science

  Stanford University

  Tuesday, September 29, 2026

  11:00 AM – 12:15 PM EDT

  View Talk & Bio
• Government • CI Keynote
  

  Laurie Allen

  Creative Engagement Officer

  Library of Congress

  Wednesday, September 30, 2026

  9:15 AM – 10:30 AM EDT

  View Talk & Bio

All 3 Keynotes ×

Eric Horvitz Diyi Yang Laurie Allen

Industry • Joint Keynote

Eric Horvitz

Chief Scientific Officer

Microsoft

Monday, Sep 28, 2026

9:15 AM – 10:30 AM EDT

Talk & Abstract About Speaker

Talk title and abstract coming soon.

Biography coming soon.

Academia • HCOMP Keynote

Diyi Yang

Assistant Professor of Computer Science

Stanford University

Tuesday, Sep 29, 2026

11:00 AM – 12:15 PM EDT

Talk & Abstract About Speaker

Human-AI Collaboration: Building Agents That Augment Work

AI agents are transforming how people work; however, building agents that augment workers requires knowing what they want from AI, how they collaborate with it, and whether that collaboration helps them. In this talk, we first audit the U.S. workforce to map where workers want automation, where they want augmentation, and where AI capabilities fall short, complemented by an analysis of nearly 250,000 real-world conversations.

We then introduce frameworks to measure collaboration directly by pairing workers with agents on real-world tasks to separate human and agent skill contributions, and by quantifying how much cognitive effort users offload through reconstructing how they would have worked without AI. Overall, this talk highlights how to understand and evaluate human-AI collaboration and how to design agents that augment human work.

Diyi Yang is an assistant professor in the Computer Science Department at Stanford University, also affiliated with the Stanford NLP Group, Stanford HCI Group and Stanford Human Centered AI Institute. Her research focuses on human-centered natural language processing and human-AI interaction.

She is a recipient of Microsoft Research Faculty Fellowship (2021), NSF CAREER Award (2022), an ONR Young Investigator Award (2023), and a Sloan Research Fellowship (2024). Her work has received multiple paper awards or nominations at top NLP and HCI conferences.

Government • CI Keynote

Laurie Allen

Creative Engagement Officer

Library of Congress

Wednesday, Sep 30, 2026

9:15 AM – 10:30 AM EDT

Talk & Abstract About Speaker

Talk title and abstract coming soon.

Laurie Allen is the Creative Engagement Officer in Researcher & Collections Services at the Library of Congress. She moved into this new position in 2026 after serving as the Chief of the Digital Innovation Division (LC Labs) in the Digital Strategy Directorate.

Before joining the Library of Congress in 2019, she spent nearly 20 years in academic libraries, leading efforts in scholarly communication, crowdsourcing, public data curation, and a variety of other projects where history, memory, art, and cultural heritage intersect with new technologies and new approaches to public engagement. Laurie lives in Philadelphia and holds a Bachelor's degree in Philosophy from Bard College, and a Master's of Library and Information Science from Simmons College.

Accepted Workshops

Workshops are a joint HCOMP and CI program. Titles, descriptions, organizers, and participation details are on the Accepted Workshops section of the Attend page.

Posters and Demos

• A Mobile Tool for Naturalistically Logging Human Information-Seeking Across Search Engines and Conversational AI Poster

  Andy Luu and Vassilis Kostakos

• A taxonomy of rater disagreements: Surveying challenges & opportunities from the perspective of annotating online toxicity Poster

  Wenbo Zhang, Saptarshi Roy, Saatvik Pradhan, Vinodkumar Prabhakaran, Ian D. Kivlichan, Davis Yadav, Hangzhi Guo and Amulya Yadav

• Adoption Depth and Organizational-Labor Transformation in the AI Era Poster

  Anuoluwapo Joshua

• AI in Information Cascades Poster

  Yiqun Wang

• An Empirical Study on Human Evaluation of Legal Generative AI Applications Poster

  Robert Kingan, Leslie Barrett, Tina Tseng and Micah Rappazzo

• Anchored Sequential Deliberation: Slower Convergence, More Stable Outcomes Poster

  Sijing Tu and Ashish Goel

• BenchMarkerUI: An Interactive System for Auditing and Repairing Multiple-Choice Benchmarks Demo

  Hyunjin Oh, Nishant Balepur and Jordan Boyd-Graber

• Beyond AI Uncertainty: Predicting When Human Review Will Actually Improve an AI Decision Poster

  Akbar Mohammed, Sambasiva Rao Akkisetti, Naveen Anand Mishra and Satya Karteek Gudipati

• Beyond Consensus: Designing AI Summaries That Preserve Dissent in Group Decision-Making Poster

  Naveen Anand Mishra, Satya Karteek Gudipati, Akbar Mohammed and Gopikanth Ankam

• Beyond the Traceback: Crowdsourced Calibration of Skill-Targeted LLM Explanations for Programming Errors Poster

  Alexandru-Radu Moraru, Shreyan Biswas and Ujwal Gadiraju

• BirdsongChat: Cross-Modal Generation and Interactive Control for Bird Motion and Soundscape Demo

  Ellie Zhang, Callie Liao and Duoduo Liao

• Collective Intelligence Simulator: An Interactive Testbed for Studying Team Decisions Across Agile Sprints Demo

  Arslan Sultan and Juan Garbajosa

• Decoding the Mind of the Machine: A Cognitive Evaluation Framework of Perception and Adaptation in Language Models Poster

  Siyu Wu, Aritra Bandyopadhyay, Jonathan Francis, Alessandro Oltramari and Frank Ritter

• Diamond In The Sky: Towards Human–AI Complementary Story-Driven Learning Environment for Children's STEM Education Poster

  Tisha Khandokar

• Dynamic Complementarity in Human–LLM Collaboration: Modeling Competence Evolution Over Repeated Decision Tasks Poster

  Negin Yazdani Motlagh, Negar Yazdani Motlagh and Lewis Tseng

• Dynamic Opinion-policy Feedback Model Explains Long-Term Patterns of Public Opinion Change Poster

  Rachael Kha

• Evaluating Beyond the Screen: Collective Assessment of AI-Generated Business Plans with Resource-Constrained Entrepreneurs Poster

  Qi Zhao, Marjory Pineda, Ketul Chhaya, Aakash Gautam and Yasmine Kotturi

• Evaluation and Best Practices of AI-Assisted Thematic Analysis Poster

  Teddy Wright, Nastaran Jadidi, Sara Yeo and Vineet Pandey

• Exploration vs. Fixation: Scaffolding Divergent and Convergent Thinking for Human-AI Co-Creation with Generative Models Poster

  Chao Wen, Tung Phung, Pronita Mehrotra, Sumit Gulwani, Roger Beaty, Tomohiro Nagashima and Adish Singla

• From Caregivers to Child-Facing AI: Understanding, Engaging, and Protecting Young Users Poster

  Ran An, Klaus Libertus and Rachel Chung

• GeoVision: Designing a Complementary Human-AI Workflow for Cue-Based Geolocation Poster

  Kirk Knutsen and Kurt Luther

• Human vs AI Instruction in Multilingual Conversational Crowdsourcing: Effects on Crowdworker Performance, Efficiency and Interaction Poster

  Jose Libreros, Tasneem Hussain, Florian Schlechte and Matthias Hirth

• Human-AI Co-Construction of Verifiable Narrative Identity: A Pilot Study on Family Stories Poster

  Cheng-En Tsai, Fanfan Chen and Jane Yung-Jen Hsu

• Human-AI Collaboration for Detecting AI-Generated Media: Just-in-Time Advice from Experts and LLMs Poster

  Negar Kamali, Aakriti Kumar, Angelos Chatzimparmpas, Candice Gerstner, Jessica Hullman and Matthew Groh

• Human-AI Collaborative Ontology Editing: An LLM-Assisted Dashboard for Improving an Ontology of Work Activities Poster

  Yilin Yang, Sophia Min, Alice Cai, Xinru Wang, Aadya Nishtha, Shuo Sun, Iman YeckehZaare and Thomas Malone

• Human-AI Complementarity in Poverty Governance: An Interpretable XGBoost Scorecard for Calibrating Human Decision-Making Poster

  Md Foysal Ahmed, Md Main Uddin Rony and Mohaimen Mansur

• Knowing When Humans Need More Help: Confidence-Aware Enterprise AI Decision Support Poster

  Satheeshkumar Ponugoti and Gopikanth Ankam

• Mapping AI Exposure Across the U.S. Workforce: Evidence from Millions of AI Conversations Poster

  Teddy Wright, Alice Schwarze and Zach Boyd

• Mental Models and Personalization of Model Selection Poster

  Zezhen He, Xinlan Emily Hu, Dean Eckles and Renee Gosline

• Merging the Interaction Gap: A RAG-Driven Contextual Knowledge Graph for Human-AI Communication in Interactive Data Products Poster

  Jawwad Shadman Siddique

• Multi-Agent Debate for Human-AI Decision-Making Poster

  Harry Tian and Ming Yin

• MusiChat: Vibe Composing for Music Creation Demo

  Callie Liao, Duoduo Liao and Ellie Zhang

• Performance, Suggestion Adoption, and Trust in Iterative AI-Assisted Ideation Poster

  Jiacheng Sun and Ting Liao

• Preserving the Record of a Cultural Computing Community: A Human-AI Collaborative Knowledge Graph Workflow Poster

  Lindsey Hartman

• Principled Uncertainty Quantification in Large Language Models: A Survey of Probabilistic Foundations and Frontiers Poster

  Jatin Chopra

• Right Advice, Wrong Reasons: Effect of Reasoning Alignment on Trust and Reliance in AI Advisors Poster

  Eunkyu Park, Vasudha Varadarajan, Wesley Hanwen Deng, Anisha Reddy, Gunhee Kim, Motahhare Eslami, Jana Schaich Borg and Maarten Sap

• Should an Expert Specialize, Synthesize, or Speculate? Discovering Latent Clusters and Ensemble Probabilities through Bandit-Arm Bid Search and Arbitrage Poster

  Theodore Ledford

• Supporting Personal Investigative Sensemaking with an Emotion-Adaptive AI Assistant Poster

  Fei Shan and Kurt Luther

• Temporal Alignment Impacts Human–AI collaboration in a Cooperative Task Poster

  Grace Roessling, Chase McDonald and Cleotilde Gonzalez

• Trusted but Untouched: How Opacity and Audience Distance Stall Synthetic Interview Outputs Before Collective Sensemaking Poster

  Inyeop Kim, Eunsol Lee, Miyoung Seo, Younghyun Choi and Kyung Sakong

• Trustworthy Autonomy at Hyperscale: Granular Authorization, Human Oversight, and Progressive Crystallization for Production AI Agents Poster

  Arun Malik

• VibeJam: A User Study Platform for Web Development with Agents Demo

  Nishant Balepur, Connor Baumler, Valerie Chen, Eunsol Choi, Rachel Rudinger and Jordan Boyd-Graber

• What Should Humans Refuse to Delegate to AI? A Turing Test for Civilization Poster

  Utsav Gupta

• Where AI Helps a Design Workflow—and Where It Does Not: Stage-Level Human–AI Complementarity in Multi-Agent Design Thinking Poster

  Younghyun Choi, Inyeop Kim, Jiyeon Lee, Janghyun Park, Nahye Kim and Kyung Sakong

• Which Piece Should I Play Next? Human–AI Collaboration for Personalized Music-Difficulty Assessment Poster

  Arman Bahraini and Eli Tilevich

• Who Decides Which AI to Use? Expert Weighting Diverges from Leaderboards Across Three Deployment Contexts Poster

  Buse Esirik and Ebru Gökalp

Doctoral Consortium Students

• Adaptive Communication in AI-Mediated Systems

  Ruyuan Wan

• AI Agents for Supporting Group Collaboration in Education

  Prerna Ravi

• AI and Collective Information Aggregation

  Yiqun Wang

• AI as a Collaborative Agent for Neurodivergent Adults: Design for Work, Productivity, and Communication

  Zinat Ara

• AI Disengagement

  Shreya Chappidi

• Balancing Learning and Sourcing: Human-AI Complementarity in Learnersourcing

  Yuzhe Zhou

• Evaluation in the Age of Automated Expertise: Supporting Human Judgment in Human-AI Red-Teaming Teams

  Alice Qian

• TBD

  Nouhayla Majdoubi

• The Universalization Problem in Content Moderation: Towards Culturally Adaptive Evaluation and Governance of Harmful Speech

  Farida Eleshin

• Tools and Methods for Worker-Centered AI

  Kashif Imteyaz