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

TL;DR

Cocoa is a system inspired by computational notebooks that enhances human-AI collaboration by allowing flexible planning and execution, enabling users to delegate agency and adjust plans dynamically during complex research tasks.

Contribution

The paper introduces Cocoa, a novel system that supports flexible, interactive collaboration between humans and AI in complex, long-term research activities.

Findings

Cocoa enables steerability without reducing ease-of-use.

Researchers successfully used Cocoa for real-world tasks.

The system supports dynamic plan adjustments during execution.

Abstract

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.