SOTA Papers
LatestTrendingDigestSearch
Newsletter
  1. Home
  2. Tao Yu

Tao Yu

1 article on SOTA Papers

Computer Science

Long-Horizon Workflows Expose Agent Reliability Gaps

OSWorld 2.0 packages 108 multi-application workflows into executable tests, where the best tested agent completes only 20.6%.

cs.AI
Jul 28, 20265 min2606.29537

Co-authors

Mengqi YuanZilong ZhouXinzhuang XiongWeiming WuJiayang SunJiamin SongKaiqian CuiBowen WangHaoyuan WuYitong LiDunjie LuHaikong LuQi ZhenXinyuan WangJiaqi DengYuhao YangCheng ChenBoyuan ZhengAlex SuXiao YuHao ZouSaaket AgasheXing Han LuManpreet KaurZhengyang QiVincent Sunn ChenFrederic SalaDayiheng LiuJunyang LinZhou YuYu SuSiva ReddyXin Eric WangPeng QiTianbao Xie
SOTA Papers

Curated editorial synthesis of meaningful arXiv papers. No slop, no overclaiming.

Fields

  • Computer Science
  • Physics
  • Mathematics
  • Economics
  • Electrical Engineering

Navigation

  • Latest
  • Trending
  • Weekly Digest
  • Search
  • Contact

Legal

  • Terms of Service
  • Privacy Policy

© 2026 SOTA Papers. All rights reserved.

Data sourced from arXiv.org