OS-Marathon: Benchmarking Computer-Use Agents on Vast-Horizon, Repetitive Tasks

[2601.20650] OS-Marathon: Benchmarking Computer-Use Agents on Vast-Horizon, Repetitive Tasks Skip to main content Search Submit Donate Log in Computer Science > Computer Vision and Pattern Recognition arXiv:2601.20650 (cs) [Submitted on 28 Jan 2026 ( v1 ), last revised 26 Aug 2026 (this version, v3)] Title: OS-Marathon: Benchmarking Computer-Use Agents on Vast-Horizon, Repetitive Tasks Authors: Jing Wu , Wenjie Ai , Daphne Barretto , Yiye Chen , Qingyu Chen , Yuhang He , Pranit Chawla , Nicholas Gydé , Yanan Jian , Vibhav Vineet View PDF HTML (experimental) Abstract: Vast-horizon, repetitive workflows are common in daily routines, e.g., processing expense reports from a stack of receipts, organising a collection of PDF annotations into structured notes, and are tedious for humans, with execution length scaling with the volume of data to process. They are, however, well-suited to autonomous agents, since their structured, recurring sub-workflows follow a logic that can be systematically learned. Yet no existing benchmark evaluates agents specifically on vast-horizon, repetitive capabilities, leaving the problem largely underexplored. To bridge this gap, we establish OS-Marathon, comprising 100 vast-horizon, repetitive tasks across 5 scenarios and 10 domains, on which our evaluation reveals that leading state-of-the-art (SOTA) CUAs struggle substantially. We further find that introducing a task orchestrator to decompose the workflow into per-instance subtasks fails to mitigate the challenge: errors accumulate and propagate across solver agents, indicating that naive decomposition is insufficient for these tasks. We then explore a cost-friendly personalisation strategy, i.e. GraphDemo, that adapts general agents to such tasks from a single human demonstration of the recurring sub-workflow logic. Extensive experiments show both the real-world challenge of vast-horizon, repetitive tasks and the improvement provided by human demonstration in this setting. Project website: this https URL . Comments: EMNLP 2026 Main Conference, Project Page: this https URL Subjects: Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2601.20650 [cs.CV] (or arXiv:2601.20650v3 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2601.20650 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Jing Wu [ view email ] [v1] Wed, 28 Jan 2026 14:35:23 UTC (6,353 KB) [v2] Mon, 2 Feb 2026 12:28:52 UTC (6,353 KB) [v3] Wed, 26 Aug 2026 22:31:44 UTC (21,794 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Current browse context: cs.CV < prev | next > new | recent | 2026-01 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• OS-Marathon: Benchmarking Computer-Use Agents on Vast-Horizon, Repetitive Tasks#674288
• StartupBench: Benchmarking General-Purpose Agents on Market-Validated End-to-End Workflows#463268
• SWE-Touch: Benchmarking Coding Agents When Users Touch the Code#424006
• WindowsWorld: A Process-Centric Benchmark of Autonomous GUI Agents in Professional Cross-Application Environments#157331
• CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents#228184