# CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning arXiv: https://arxiv.org/abs/2508.20096 ยท HTML: https://mlsanity.com/paper/2508.20096/ ## Key facts - Cited by 6 papers in the map (data through 14 Oct 2026). - Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. - Builds on 44 of its 66 references that are in the map. - First posted on arXiv 27 Aug 2025. ## Placed in - LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/) - LLM agents and tool use / [GUI and mobile agents](https://mlsanity.com/agents/gui-and-mobile-agents/) ## Builds on (most cited first, 30 of 44) - [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023) - [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024) - [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023) - [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024) - [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025) - [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025) - [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024) - [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023) - [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019) - [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015) - [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023) - [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025) - [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021) - [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023) - [CogAgent: A Visual Language Model for GUI Agents](https://mlsanity.com/paper/2312.08914/) (2023) - [UI-TARS: Pioneering Automated GUI Interaction with Native Agents](https://mlsanity.com/paper/2501.12326/) (2025) - [SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents](https://mlsanity.com/paper/2401.10935/) (2024) - [WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models](https://mlsanity.com/paper/2401.13919/) (2024) - [Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents](https://mlsanity.com/paper/2410.05243/) (2024) - [OS-ATLAS: A Foundation Action Model for Generalist GUI Agents](https://mlsanity.com/paper/2410.23218/) (2024) - [WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning](https://mlsanity.com/paper/2411.02337/) (2024) - [ShowUI: One Vision-Language-Action Model for GUI Visual Agent](https://mlsanity.com/paper/2411.17465/) (2024) - [ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL](https://mlsanity.com/paper/2402.19446/) (2024) - [Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents](https://mlsanity.com/paper/2408.07199/) (2024) - [OS-Copilot: Towards Generalist Computer Agents with Self-Improvement](https://mlsanity.com/paper/2402.07456/) (2024) - [Agent S: An Open Agentic Framework that Uses Computers Like a Human](https://mlsanity.com/paper/2410.08164/) (2024) - [OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis](https://mlsanity.com/paper/2412.19723/) (2024) - [Android in the Zoo: Chain-of-Action-Thought for GUI Agents](https://mlsanity.com/paper/2403.02713/) (2024) - [Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents](https://mlsanity.com/paper/2504.00906/) (2025) - [Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis](https://mlsanity.com/paper/2505.13227/) (2025) ## Built on by (most cited first, 6 of 6) - [ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning](https://mlsanity.com/paper/2512.05111/) (2025) - [SPARK: Synergistic Policy And Reward Co-Evolving Framework](https://mlsanity.com/paper/2509.22624/) (2025) - [Using GUI Agent for Electronic Design Automation](https://mlsanity.com/paper/2512.11611/) (2025) - [Visual Self-Refine: A Pixel-Guided Paradigm for Accurate Chart Parsing](https://mlsanity.com/paper/2602.16455/) (2026) - [OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models](https://mlsanity.com/paper/2607.28609/) (2026) - [Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents](https://mlsanity.com/paper/2605.28775/) (2026) ## Abstract (arXiv) Autonomous agents for Graphical User Interfaces (GUIs) face significant challenges in specialized domains such as scientific computing, where both long-horizon planning and precise execution are required. Existing approaches suffer from a trade-off: generalist agents excel at planning but perform poorly in execution, while specialized agents demonstrate the opposite weakness. Recent compositional frameworks attempt to bridge this gap by combining a planner and an actor, but they are typically static and non-trainable, which prevents adaptation from experience. This is a critical limitation given the scarcity of high-quality data in scientific domains. To address these limitations, we introduce CODA, a novel and trainable compositional framework that integrates a generalist planner (Cerebrum) with a specialist executor (Cerebellum), trained via a dedicated two-stage pipeline. In the first stage, Specialization, we apply a decoupled GRPO approach to train an expert planner for each scientific application individually, bootstrapping from a small set of task trajectories. In the second stage, Generalization, we aggregate all successful trajectories from the specialized experts to build a consolidated dataset, which is then used for supervised fine-tuning of the final planner. This equips CODA with both robust execution and cross-domain generalization. Evaluated on four challenging applications from the ScienceBoard benchmark, CODA significantly outperforms baselines and establishes a new state of the art among open-source models.