Paper Detail

cotomi Act: Learning to Automate Work by Watching You

Masafumi Oyamada, Kunihiro Takeoka, Kosuke Akimoto, Ryoma Obara, Masafumi Enomoto, Haochen Zhang, Daichi Haraguchi, Takuya Tamura

arxiv Score 19.9

Published 2026-05-04 · First seen 2026-05-09

Research Track B · General AI

Abstract

What if a browser agent could learn your work simply by watching you do it? We present cotomi Act, a browser-based computer-using agent that combines reliable multi-step task execution with persistent organizational knowledge learned from user behavior. For execution, an agent scaffold with adaptive lazy observation, verbal-diff-based history compression, coarse-grained actions, and test-time scaling via best-of-N action selection achieves 80.4% on the 179-task WebArena human-evaluation subset, exceeding the reported 78.2% human baseline. For organizational knowledge, a behavior-to-knowledge pipeline passively observes the user's browsing and progressively abstracts it into artifacts (task boards, wiki) exposed through a shared workspace editable by both user and agent. A controlled proxy evaluation confirms that task success improves as behavior-derived knowledge accumulates. In our live demonstration, attendees interact with the system in a real browser, issuing tasks and observing end-to-end autonomous execution and shared knowledge management.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{oyamada2026cotomi,
  title = {cotomi Act: Learning to Automate Work by Watching You},
  author = {Masafumi Oyamada and Kunihiro Takeoka and Kosuke Akimoto and Ryoma Obara and Masafumi Enomoto and Haochen Zhang and Daichi Haraguchi and Takuya Tamura},
  year = {2026},
  abstract = {What if a browser agent could learn your work simply by watching you do it? We present cotomi Act, a browser-based computer-using agent that combines reliable multi-step task execution with persistent organizational knowledge learned from user behavior. For execution, an agent scaffold with adaptive lazy observation, verbal-diff-based history compression, coarse-grained actions, and test-time scaling via best-of-N action selection achieves 80.4\% on the 179-task WebArena human-evaluation subset, },
  url = {https://arxiv.org/abs/2605.03231},
  keywords = {cs.AI},
  eprint = {2605.03231},
  archiveprefix = {arXiv},
}

Metadata

{}