PulseAugur
LIVE 08:28:45
tool · [1 source] ·
0
tool

cotomi Act agent learns to automate tasks by watching user behavior

Researchers have developed cotomi Act, a browser agent designed to automate work by learning from user actions. The system achieves high task execution accuracy on the WebArena benchmark, surpassing a human baseline. It also incorporates a knowledge pipeline that abstracts user browsing behavior into editable artifacts like task boards and wikis, improving task success as knowledge accumulates. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT This agent could significantly streamline workflows by learning and automating repetitive tasks directly within a browser environment.

RANK_REASON This is a research paper detailing a new AI agent and its performance on a benchmark. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

COVERAGE [1]

  1. arXiv cs.AI TIER_1 · Masafumi Oyamada, Kunihiro Takeoka, Kosuke Akimoto, Ryoma Obara, Masafumi Enomoto, Haochen Zhang, Daichi Haraguchi, Takuya Tamura ·

    cotomi Act: Learning to Automate Work by Watching You

    arXiv:2605.03231v1 Announce Type: new 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 learne…