Eight universities propose unified framework for work agents
Zishan Xu · hf · 2026-10-27
A paper from researchers at SJTU, HKU, HKUST-GZ, Tsinghua, Zhejiang and other universities proposes a unified framework for "work agents": systems combining foundation models with runtime harnesses to reliably execute complex digital tasks.
Key points:
- Introduces persistence and openness as new dimensions for characterizing agent systems
- Proposes capability families and a set of evaluation metrics
- Ships with an Awesome Work Agents list and project homepage
More from coding & agent
- Polylane builds its agent memory system on Git, with nightly self-correction — dinasaur_404 · 2026-10-27
- Manus on rebuilding itself as an AI-native org: expose interfaces, demand evidence, go async — dotey · 2026-10-27
- RL doesn't just reward thinking longer—it incentives parallel agent swarms — rosstaylor90 · 2026-10-27
- A peek at a personal multi-agent setup: Codex, Muse and Grokbot with role-based memory — op7418 · 2026-10-27
- Context Layer V2 evals: ~40% accuracy gain, ~30% latency cut vs MCP alone — shensi · 2026-10-27
- Agent made 133 calls in 41 seconds: engineer argues physics, not protocols, is the bottleneck — shensi · 2026-10-27