At COLM: iOSWorld Phone-Agent Benchmark, Odysseys' 200 Web Tasks, Multi-Agent Computer Use
kohjingyu · x · 2026-10-05
Google researcher Koh Jingyu shares his three COLM presentations:
- iOSWorld (Oct 8, poster #81): a realistic iOS environment for benchmarking phone agents.
- Odysseys (poster #46): 200 long-horizon web tasks derived from real browsing sessions, evaluated on the live Internet.
- Multi-Agent Computer Use (MACU) (Oct 9 workshops): a framework where a manager model decomposes computer-use tasks into parallel subtasks, improving both success rate and speed.
He says his current focus is CUAs for complex tasks (including science applications) and new architectures supporting multi-agent coordination.
More from coding & agent
- Teknium catalogs 305 open, hackable devices your AI agent can control and live in — Teknium · 2026-10-06
- Crawler + GPT agent scanned 5,137 jobs for $6.53, found 3 low-competition niches — Arindam_1729 · 2026-10-06
- xAI Cookbook adds 4 Grok SDK examples: screenshot-to-React, X sentiment tracker, AI ad generator — tetsuoai · 2026-10-06
- Power user runs a swarm of personal agents — poke, instinct, muse, dot, Grok bot, pickle and more — sebkrier · 2026-10-06
- omni-macos: A Fully Local Semantic Finder for Apple Silicon, Now Daily-Driver Good — JinaAI_ · 2026-10-06
- User: Team Grok Bots let you spin up org-wide custom tools and workflows in minutes — aryamankhawow · 2026-10-06