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

arXiv: https://arxiv.org/abs/2412.10999 · HTML: https://mlsanity.com/paper/2412.10999/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- Builds on 58 of its 160 references that are in the map.
- First posted on arXiv 14 Dec 2024.

## Builds on (most cited first, 30 of 58)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models](https://mlsanity.com/paper/2310.04406/) (2023)
- [SPECTER: Document-level Representation Learning using Citation-informed Transformers](https://mlsanity.com/paper/2004.07180/) (2020)
- [Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance](https://mlsanity.com/paper/2006.14779/) (2020)
- [On the Planning Abilities of Large Language Models : A Critical Investigation](https://mlsanity.com/paper/2305.15771/) (2023)
- [Consistent Estimators for Learning to Defer to an Expert](https://mlsanity.com/paper/2006.01862/) (2020)
- [AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts](https://mlsanity.com/paper/2110.01691/) (2021)
- [AI Agents That Matter](https://mlsanity.com/paper/2407.01502/) (2024)
- [Harms from Increasingly Agentic Algorithmic Systems](https://mlsanity.com/paper/2302.10329/) (2023)
- [ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search](https://mlsanity.com/paper/2310.13227/) (2023)
- [DISCOVERYWORLD: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents](https://mlsanity.com/paper/2406.06769/) (2024)
- [ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testing](https://mlsanity.com/paper/2309.09128/) (2023)
- [Visibility into AI Agents](https://mlsanity.com/paper/2401.13138/) (2024)
- [Put Your Money Where Your Mouth Is: Evaluating Strategic Planning and Execution of LLM Agents in an Auction Arena](https://mlsanity.com/paper/2310.05746/) (2023)
- [A Design Space for Intelligent and Interactive Writing Assistants](https://mlsanity.com/paper/2403.14117/) (2024)
- [Building Machines that Learn and Think with People](https://mlsanity.com/paper/2408.03943/) (2024)
- [(A)I Am Not a Lawyer, But...: Engaging Legal Experts towards Responsible LLM Policies for Legal Advice](https://mlsanity.com/paper/2402.01864/) (2024)
- [LLMs as Research Tools: A Large Scale Survey of Researchers' Usage and Perceptions](https://mlsanity.com/paper/2411.05025/) (2024)
- [VISAR: A Human-AI Argumentative Writing Assistant with Visual Programming and Rapid Draft Prototyping](https://mlsanity.com/paper/2304.07810/) (2023)
- [IdeaSynth: Iterative Research Idea Development Through Evolving and Composing Idea Facets with Literature-Grounded Feedback](https://mlsanity.com/paper/2410.04025/) (2024)
- [CoQuest: Exploring Research Question Co-Creation with an LLM-based Agent](https://mlsanity.com/paper/2310.06155/) (2023)
- [Data-driven Discovery with Large Generative Models](https://mlsanity.com/paper/2402.13610/) (2024)

## Built on by (most cited first, 30 of 39)

- [Levels of Autonomy for AI Agents](https://mlsanity.com/paper/2506.12469/) (2025)
- [Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human Oversight](https://mlsanity.com/paper/2509.10723/) (2025)
- [Thinking beyond the anthropomorphic paradigm benefits LLM research](https://mlsanity.com/paper/2502.09192/) (2025)
- [Measuring and mitigating overreliance to build human-compatible AI](https://mlsanity.com/paper/2509.08010/) (2025)
- [Mapping the Design Space of User Experience for Computer Use Agents](https://mlsanity.com/paper/2602.07283/) (2026)
- [Measuring LLM Novelty As The Frontier Of Original And High-Quality Output](https://mlsanity.com/paper/2504.09389/) (2025)
- [A Good Plan is Hard to Find: Aligning Models with Preferences is Misaligned with What Helps Users](https://mlsanity.com/paper/2509.18632/) (2025)
- [When Should Users Check? Modeling Confirmation Frequency in Multi-Step Agentic AI Tasks](https://mlsanity.com/paper/2510.05307/) (2025)
- [Comparing Human Oversight Strategies for Computer-Use Agents](https://mlsanity.com/paper/2604.04918/) (2026)
- [TableTalk: Scaffolding Spreadsheet Development with a Language Agent](https://mlsanity.com/paper/2502.09787/) (2025)
- [Modeling Distinct Human Interaction in Web Agents](https://mlsanity.com/paper/2602.17588/) (2026)
- [ClearFairy: Capturing Creative Workflows through Decision Structuring, In-Situ Questioning, and Rationale Inference](https://mlsanity.com/paper/2509.14537/) (2025)
- [Semantic Commit: Helping Users Update Intent Specifications for AI Memory at Scale](https://mlsanity.com/paper/2504.09283/) (2025)
- [Attribution Gradients: Incrementally Unfolding Citations for Critical Examination of Attributed AI Answers](https://mlsanity.com/paper/2510.00361/) (2025)
- [On the Regulatory Potential of User Interfaces for AI Agent Governance](https://mlsanity.com/paper/2512.00742/) (2025)
- [Overseeing Agents Without Constant Oversight: Challenges and Opportunities](https://mlsanity.com/paper/2602.16844/) (2026)
- [Hedwig: Dynamic Autonomy for Coding Agents Under Local Oversight](https://mlsanity.com/paper/2605.11495/) (2026)
- [Plover: Steering GUI Agents through Plan-Centric Interaction](https://mlsanity.com/paper/2607.15193/) (2026)
- [Understanding User Experiences of Computer Use Agents: Design Space and Opportunities for Building Agent UX Prototypes](https://mlsanity.com/paper/2510.04452/) (2025)
- [How to Steer Your Multi-Agent System: Human-LLM Collaborative Planning](https://mlsanity.com/paper/2605.23023/) (2026)
- [HiLSVA: Design and Evaluation of a Human-in-the-Loop Agentic System for Scientific Visualization](https://mlsanity.com/paper/2606.26614/) (2026)
- ["When to Hand Off, When to Work Together": Understanding Concurrent Human-Agent Interaction in Shared Co-Creative Workspaces](https://mlsanity.com/paper/2603.02050/) (2026)
- [LitPivot: Developing Well-Situated Research Ideas Through Dynamic Contextualization and Critique within the Literature Landscape](https://mlsanity.com/paper/2604.02600/) (2026)
- [Effects of Generative AI Errors on User Reliance Across Task Difficulty](https://mlsanity.com/paper/2604.04319/) (2026)
- [Auditing and Controlling AI Agent Actions in Spreadsheets](https://mlsanity.com/paper/2604.20070/) (2026)
- [Intentmaking and Sensemaking: Human Interaction with AI-Guided Mathematical Discovery](https://mlsanity.com/paper/2605.05921/) (2026)
- [CollabSkill: Evaluating Human-Agent Collaboration On Real-World Tasks](https://mlsanity.com/paper/2606.09833/) (2026)
- [HANSEL: Extracting Breadcrumbs from Web Agent Trajectories for Interactive Verification](https://mlsanity.com/paper/2606.18671/) (2026)
- [Agent-Integrated Software: Interaction Contracts and Continuous Assurance](https://mlsanity.com/paper/2609.11381/) (2026)
- [OrchVis: Hierarchical Multi-Agent Orchestration for Human Oversight](https://mlsanity.com/paper/2510.24937/) (2025)

## Abstract (arXiv)

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.