Cocoa: Co-Planning and Co-Execution with AI Agents
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917278490034176 |
|---|---|
| author | Feng, K. J. Kevin Pu, Kevin Latzke, Matt August, Tal Siangliulue, Pao Bragg, Jonathan Weld, Daniel S. Zhang, Amy X. Chang, Joseph Chee |
| author_facet | Feng, K. J. Kevin Pu, Kevin Latzke, Matt August, Tal Siangliulue, Pao Bragg, Jonathan Weld, Daniel S. Zhang, Amy X. Chang, Joseph Chee |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_10999 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Cocoa: Co-Planning and Co-Execution with AI Agents Feng, K. J. Kevin Pu, Kevin Latzke, Matt August, Tal Siangliulue, Pao Bragg, Jonathan Weld, Daniel S. Zhang, Amy X. Chang, Joseph Chee Human-Computer Interaction Artificial Intelligence 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. |
| title | Cocoa: Co-Planning and Co-Execution with AI Agents |
| topic | Human-Computer Interaction Artificial Intelligence |
| url | https://arxiv.org/abs/2412.10999 |