# Scaling Agents for Computer Use

arXiv: https://arxiv.org/abs/2510.02250 · HTML: https://mlsanity.com/paper/2510.02250/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in GUI and mobile agents, one of 16 directions in LLM agents and tool use.
- Builds on 16 of its 61 references that are in the map.
- First posted on arXiv 2 Oct 2025.

## Placed in

- LLM agents and tool use / [GUI and mobile agents](https://mlsanity.com/agents/gui-and-mobile-agents/)

## Builds on (most cited first, 16 of 16)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (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)
- [AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents](https://mlsanity.com/paper/2405.14573/) (2024)
- [Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction](https://mlsanity.com/paper/2412.04454/) (2024)
- [Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale](https://mlsanity.com/paper/2409.08264/) (2024)
- [Agent S: An Open Agentic Framework that Uses Computers Like a Human](https://mlsanity.com/paper/2410.08164/) (2024)
- [An Illusion of Progress? Assessing the Current State of Web Agents](https://mlsanity.com/paper/2504.01382/) (2025)
- [Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents](https://mlsanity.com/paper/2504.00906/) (2025)
- [UI-Venus Technical Report: Building High-performance UI Agents with RFT](https://mlsanity.com/paper/2508.10833/) (2025)
- [Scaling Test-time Compute for LLM Agents](https://mlsanity.com/paper/2506.12928/) (2025)
- [Multi-Turn Code Generation Through Single-Step Rewards](https://mlsanity.com/paper/2502.20380/) (2025)
- [GUI-Robust: A Comprehensive Dataset for Testing GUI Agent Robustness in Real-World Anomalies](https://mlsanity.com/paper/2506.14477/) (2025)
- [Agentic Lybic: Multi-Agent Execution System with Tiered Reasoning and Orchestration](https://mlsanity.com/paper/2509.11067/) (2025)

## Built on by (most cited first, 14 of 14)

- [CUA-Skill: Develop Skills for Computer Using Agent](https://mlsanity.com/paper/2601.21123/) (2026)
- [When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents](https://mlsanity.com/paper/2602.08235/) (2026)
- [OmegaUse: Building a General-Purpose GUI Agent for Autonomous Task Execution](https://mlsanity.com/paper/2601.20380/) (2026)
- [Agent Alpha: Tree Search Unifying Generation, Exploration and Evaluation for Computer-Use Agents](https://mlsanity.com/paper/2602.02995/) (2026)
- [Watch and Learn: Learning to Use Computers from Online Videos](https://mlsanity.com/paper/2510.04673/) (2025)
- [StructAgent: Harness Long-horizon Digital Agents with Unified Causal Structure](https://mlsanity.com/paper/2607.11388/) (2026)
- [Surfer 2: The Next Generation of Cross-Platform Computer Use Agents](https://mlsanity.com/paper/2510.19949/) (2025)
- [VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation](https://mlsanity.com/paper/2604.21375/) (2026)
- [GUIDE: Resolving Domain Bias in GUI Agents through Real-Time Web Video Retrieval and Plug-and-Play Annotation](https://mlsanity.com/paper/2603.26266/) (2026)
- [Rethinking Inference-Time Scaling in Local Computer-Use Agents: Failure Modes and Compute Tradeoffs](https://mlsanity.com/paper/2607.28573/) (2026)
- [When Is an Agent Evaluation Over? Outcome Finality and Cross-Unit Separation](https://mlsanity.com/paper/2608.14940/) (2026)
- [LocalLSTC: A Long Short-Term Control Architecture for Locally Deployed GUI Agents](https://mlsanity.com/paper/2608.25777/) (2026)
- [ReLiveGym: Evaluating Long-Lived Agents over Weeks of Replayed Reality](https://mlsanity.com/paper/2610.00710/) (2026)
- [GUI-HARVEST: Self-Improving GUI Agents through Evidence-Driven Harness Evolution](https://mlsanity.com/paper/2610.00948/) (2026)

## Abstract (arXiv)

Computer-use agents (CUAs) hold promise for automating everyday digital tasks, but their performance on long-horizon, complex problems remains unreliable. Single-rollout execution is brittle, with small errors compounding over time and leading to high variance in outcomes. While prior work has attempted to scale within a single rollout, such approaches have yielded limited gains. Scaling over multiple rollouts offers a more promising alternative but doing so effectively is challenging due to the difficulty of evaluating and selecting among long-horizon agent behaviors. We introduce Behavior Judge (BJudge), which addresses this challenge by representing agent executions as behavior narratives and comparing candidate behaviors at this level, substantially improving robustness and success rates. Using multiple rollouts, BJudge establishes a new state of the art (SoTA) in OSWorld at 72.6%, significantly outperforming prior methods and surpassing human-level performance at 72.36%, with comprehensive ablations validating key design choices. We further demonstrate strong generalization results to different operating systems on WindowsAgentArena and AndroidWorld. Crucially, our results highlight the strong effectiveness of scaling CUAs, when you do it right: effective scaling requires structured trajectory understanding and selection, and BJudge provides a practical framework to achieve this.