Cocoa: Co-Planning and Co-Execution with AI Agents

要旨

As AI agents take on increasingly long-running tasks involving sophisticated planning and execution, there is a corresponding need for novel interaction designs that enable deeper human-agent collaboration. However, most prior works leverage human interaction to fix "autonomous" workflows that have yet to become fully autonomous or rigidly treat planning and execution as separate stages. Based on a formative study with 9 researchers using AI to support their work, we propose a design that affords greater flexibility in collaboration, so that users can 1) delegate agency to the user or agent via a collaborative plan where individual steps can be assigned; and 2) interleave planning and execution so that plans can adjust after partial execution. We introduce Cocoa, a system that takes design inspiration from computational notebooks to support complex research tasks. A lab study (n=16) found that Cocoa enabled steerability without sacrificing ease-of-use, and a week-long field deployment (n=7) showed how researchers collaborated with Cocoa to accomplish real-world tasks.

受賞
Best Paper
著者
K. J. Kevin Feng
University of Washington, Seattle, Washington, United States
Kevin Pu
University of Toronto, Toronto, Ontario, Canada
Matt Latzke
Allen Institute for AI, Seattle, Washington, United States
Tal August
University of Illinois Urbana-Champaign , Urbana, Illinois, United States
Pao Siangliulue
Allen Institute for AI, Seattle, Washington, United States
Jonathan Bragg
Allen Institute for Artificial Intelligence, Seattle, Washington, United States
Daniel S. Weld
Allen Institute for Artificial Intelligence, Seattle, Washington, United States
Amy X.. Zhang
University of Washington, Seattle, Washington, United States
Joseph Chee Chang
Allen Institute for AI, Seattle, Washington, United States

会議: CHI 2026

ACM CHI Conference on Human Factors in Computing Systems

セッション: AI Collaboration in Practice

P1 - Room 128
7 件の発表
2026-04-14 18:00:00
2026-04-14 19:30:00