RUC & Fudan release CoworkOS: agent runtime for long-horizon work with human edits, boosting benchmarks from 33.19 to 42.95
jiqizhixin · x · 2026-11-20
Renmin University of China and Fudan University released the official technical report for CoworkOS, targeting the bottleneck where complex artifact tasks outlast a single conversation and humans make edits along the way.
Mechanism: the model decides actions and acceptance while a runtime maintains execution state; a coordinator manages delegated work, shared application objects let humans and agents revise the same artifacts, and persistent memory plus job logs enable resumption.
Results: in a sustained-work experiment, a GLM-5.3 agent ran five rounds of automated post-training on Qwen3.6-35B-A3B, raising its 8-benchmark average from 33.19 to 42.95 (AutomationBench +33.15pp, SkillsBench +14.91pp, etc.). CoworkOS also leads OpenHands, Codex, and DSH across SkillsBench, Tool Use, JobBench and other benchmarks.
More from coding & agent
- TrustedSec: AI agents make attacker attention cheap, rewriting offensive security economics — cyb3rops · 2026-11-20
- Apple job listing reveals an AI agent that browses, runs terminal commands and debugs code — mark_k · 2026-11-20
- Agno builds sandboxing for Claude Code/Codex agents with S3 checkpoint restore — pritisinghhhh · 2026-11-20
- AI CRM agent in n8n: AI plans, plain-code rules gate approvals — ZtasnimS75 · 2026-11-20
- Solid Bits launches: 200+ free animated components for SolidJS 2.0 with shadcn registry — shadcn · 2026-11-20
- ForgeSystem paper proposes AI agents forging demand-specific software — Div_pradeep · 2026-11-20