# EvoCUA-1.5: Online Reinforcement Learning for Multi-turn Computer-Use Agents

arXiv: https://arxiv.org/abs/2607.09773 · HTML: https://mlsanity.com/paper/2607.09773/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use.
- Builds on 30 of its 37 references that are in the map.
- First posted on arXiv 7 Jul 2026.

## Placed in

- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)
- Deep reinforcement learning methods / [RL training of language and agent models](https://mlsanity.com/deeprl/rl-training-of-language-and-agent-models/)

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

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [UI-TARS: Pioneering Automated GUI Interaction with Native Agents](https://mlsanity.com/paper/2501.12326/) (2025)
- [AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents](https://mlsanity.com/paper/2405.14573/) (2024)
- [OS-ATLAS: A Foundation Action Model for Generalist GUI Agents](https://mlsanity.com/paper/2410.23218/) (2024)
- [Android in the Wild: A Large-Scale Dataset for Android Device Control](https://mlsanity.com/paper/2307.10088/) (2023)
- [WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning](https://mlsanity.com/paper/2411.02337/) (2024)
- [GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents](https://mlsanity.com/paper/2504.10458/) (2025)
- [UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2509.02544/) (2025)
- [DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning](https://mlsanity.com/paper/2406.11896/) (2024)
- [Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents](https://mlsanity.com/paper/2408.07199/) (2024)
- [Mobile-Agent-v3: Fundamental Agents for GUI Automation](https://mlsanity.com/paper/2508.15144/) (2025)
- [UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning](https://mlsanity.com/paper/2503.21620/) (2025)
- [WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2505.16421/) (2025)
- [OpenCUA: Open Foundations for Computer-Use Agents](https://mlsanity.com/paper/2508.09123/) (2025)
- [MMBench-GUI: Hierarchical Multi-Platform Evaluation Framework for GUI Agents](https://mlsanity.com/paper/2507.19478/) (2025)
- [ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data](https://mlsanity.com/paper/2509.15221/) (2025)
- [MobileRL: Online Agentic Reinforcement Learning for Mobile GUI Agents](https://mlsanity.com/paper/2509.18119/) (2025)
- [Step-GUI Technical Report](https://mlsanity.com/paper/2512.15431/) (2025)
- [UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning](https://mlsanity.com/paper/2509.11543/) (2025)
- [InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization](https://mlsanity.com/paper/2508.05731/) (2025)
- [Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation](https://mlsanity.com/paper/2509.23866/) (2025)
- [CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents](https://mlsanity.com/paper/2605.25624/) (2026)
- [Digi-Q: Learning Q-Value Functions for Training Device-Control Agents](https://mlsanity.com/paper/2502.15760/) (2025)
- [WebFactory: Automated Compression of Foundational Language Intelligence into Grounded Web Agents](https://mlsanity.com/paper/2603.05044/) (2026)
- [WebChain: A Large-Scale Human-Annotated Dataset of Real-World Web Interaction Traces](https://mlsanity.com/paper/2603.05295/) (2026)

## Built on by (most cited first, 3 of 3)

- [Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents](https://mlsanity.com/paper/2607.28227/) (2026)
- [Wuying-Browser-Agent: Real-World Centric Fundamental Long-Horizon Browser Agents](https://mlsanity.com/paper/2608.17319/) (2026)
- [Prorsa: Unleashing the Potential of Prefill-Decode Disaggregation in Agentic Reinforcement Learning](https://mlsanity.com/paper/2610.16592/) (2026)

## Abstract (arXiv)

Computer-use agents must solve long-horizon tasks through repeated interaction with partially observable, multimodal desktop environments. Although imitation learning and offline trajectory refinement provide strong priors, static traces cannot cover the causal feedback loop of real computer use: each action changes the screen state, future action space, and recovery options. EvoCUA-1.5 extends self-evolving computer-use agents from offline experience learning to online reinforcement learning, where policies interact with executable sandbox environments and improve from verifiable task outcomes. Online RL in this setting requires more than directly reusing single-turn language-RL recipes. Multi-turn interaction introduces context-managed observations, sparse terminal rewards, variable-length trajectories, and slow environment feedback. EvoCUA-1.5 addresses these challenges with Step-Level Policy Optimization (STEPO), which preserves trajectory-level advantage balance after decomposition into step-level samples; policy-aware filtering and pass-rate calibration over verifiable synthesized tasks; Dynamic Tri-Adaptive Curriculum (DTAC), which combines learnable tasks, difficult positive replay, and controlled infeasible-task exposure; and a fully asynchronous RL infrastructure with staleness control and mini-group batching. Experiments show that these components improve training stability and downstream performance. EvoCUA-1.5 achieves 63.2% success on OSWorld-Verified, outperforming comparable 32B/35B-scale open-weight baselines and even approaching models with significantly larger parameter counts. Overall, EvoCUA-1.5 provides a practical framework for scaling online RL in multi-turn computer-use agents.