About the Workshop
The recent emergence of Large Language Model (LLM) agents sheds light on the construction of intelligent systems that become genuine collaborators of humans through mutual partnership. These AI agents can sustain open-ended natural dialogue, exhibit reasoning and planning, and even evoke social or moral responses from humans. Nevertheless, current intelligent systems lack critical characteristics of effective collaboration, such as mutual awareness, mixed-initiative interactions, and shared accountability. Without these qualities, interactions between humans and systems can be brittle, error-prone, and synergistic collaboration remains unrealized.
In this workshop, we propose a novel human-AI interaction design philosophy: to design and study LLM agents as remote collaborators. Grounded in decades of CSCW research on distributed teamwork, remote humans communicate and coordinate through lean channels, lack shared physical context, and must rely on explicit signals to maintain common ground, which is analogous to how humans interact with LLM agents.
Our goal is to create a shared vocabulary and a research agenda that is both grounded in foundational knowledge and visionary about future possibilities.
Call for Participation
Recent advances in Large Language Model (LLM) agents open up possibilities for moving intelligent systems beyond tools toward mutual partnerships with humans. These agents can engage in fluid natural language dialogue, exhibit role-playing behaviors, and demonstrate reasoning and planning capabilities. Still, they lack critical characteristics of effective collaboration, such as mutual awareness, adaptability, and shared accountability, which could introduce risks such as misaligned autonomy, hallucinations, privacy and security vulnerabilities, and over-anthropomorphization.
This workshop calls on the broad HCI, CSCW, AI, and related communities to critically and creatively explore new paradigms of human–agent partnership. We invite contributions that draw on the rich history of technology-mediated remote human collaboration while also envisioning novel forms of mixed-initiative, multi-party, and asynchronous collaboration with AI agents.
Our objectives include:- Establish the "agents as remote collaborators" analogy as a bounded but powerful research heuristic.
- Assess the applicability of the core CSCW theories to emerging human-agent contexts.
- Identify and ideate novel interaction paradigms that extend beyond traditional human-human and human-AI collaboration.
- Integrate considerations of risks (security, privacy, trust miscalibration) into the design space of human-agent collaboration.
- Develop a community-driven research agenda that is suitable for the future of human-agent collaboration studies.
Participation Options
Our workshop offers two ways to participate:- Position paper (traditional submission-based participation); instructions are provided below.
- Participatory form (non-paper participation). Participants may instead submit a participatory form that describes their background, motivation, perspective, and what they hope to contribute or learn. These submissions are also reviewed for discussion value and fit, but acceptance is contingent on available capacity.
Key Dates
All deadlines follow the Anywhere on Earth (AoE) timezone.- Submission Deadline: February 15, 2026, AoE
- Notification Date (Updated): March 3, 2026, AoE
- Workshop Date: Monday, April 13, 2026
Call for Papers
We welcome 2–4 page submissions (ACM single-column format, reference does not count toward page limit), including research articles, survey papers, and position papers that present original ideas, empirical studies, or design visions. Topics of interest include, but are not limited to:
- Applying and extending CSCW/HCI theories (e.g., common ground, workspace awareness, articulation work) to human–agent interaction
- Empirical studies of human–agent collaboration (e.g., trust calibration, coordination, failure recovery)
- Novel design paradigms for human–agent collaboration, including mixed-initiative workflows, coordination strategies, and asynchronous delegation
- Interface and interaction designs that make agents’ goals, actions, and limitations transparent to human partners
- Risks, challenges, and safeguards for human-agent collaboration (e.g., security, privacy, safety, misaligned autonomy)
- Critical perspectives on anthropomorphization, social accountability, and ethics of agentic systems
Submission Site
Submissions will be managed via OpenReview. Submissions will undergo a lightweight review, focusing on the quality of ideas and diversity of perspectives.
Formatting Requirements
Submissions must follow the ACM Master Article Submission Templates (single column).
Accepted Papers
Accepted papers will be published online on the workshop website. A poster session will be hosted, concurrent with the coffee break, that allows authors of accepted papers to share their work. Selected papers will be invited to give a lightning talk during the workshop.
Selected position papers will be compiled into a digital proceedings volume. We are exploring the opportunity to publish the workshop proceedings in the ACM Digital Library (alternatives include established open-access platform such as arXiv.org or CEUR-WS.org).
Schedule
Workshop schedule. All talks include a Q&A session.
Introduction
Keynote Speaker
Valerie ChenPanel Discussion
Hong Shen, Christina Ma, Michael Liu, Kori Inkpen(Coffee Break) Poster Session
This period includes the final 10 minutes of S1.Group Activities
Group Presentations
Synthesis and Closing
Organizers
This workshop is organized by
FAQ
Common questions from participants and accepted-paper authors.
What is the workshop format?
The workshop is organized into two sessions: S1 (2:15-3:45 PM) and S2 (4:30-6:00 PM), with a coffee break and poster session (3:35-4:30 PM) in between.
What should accepted authors prepare for the poster session?
Please prepare a poster summarizing your accepted work. Each poster board is 1.7m wide and 1m tall, accommodating at least two A1 posters (594mm x 841mm). A1 is recommended, but not enforced.
Will there be oral presentations?
The program includes a keynote, panel discussion, and group activities. Due to time constraints, we are not arranging lightning-style paper sharing.
Can I still participate if I did not submit a paper?
Yes. The workshop is open-door. Some seats are reserved for accepted-paper authors until 5 minutes before the workshop starts; after that, all seats are available to walk-ins.
Do accepted-paper authors have a mandatory attendance policy?
There is currently no mandatory attendance policy.
Is remote participation supported?
No. The workshop is in-person only.
Will the workshop be recorded?
No. The workshop will not be recorded by organizers in order to promote transparent discussion.
Who should I contact for workshop questions?
Please contact Bingsheng Yao (b.yao@northeastern.edu) and Chaoran Chen (cchen25@nd.edu).
Accepted Papers
Browse accepted papers and abstracts.
Loading accepted papers...