CoworkOS Paper Proposes a Runtime Layer for Long-Horizon Agent Work
The authors of CoworkOS describe a general-purpose harness for long-horizon productivity work that splits task strategy from execution management. The model chooses actions, delegation and acceptance, while the runtime holds state and feedback. A three-layer design lets work run directly or be handed to Subagents, synchronously or asynchronously, and a shared application layer lets people and agents inspect and revise the same documents, presentations, CAD models and Blender scenes. Hierarchical workspaces and persistent semantic memory keep files, decisions and job logs resumable after an interruption.
Why it matters
The paper's split between model decisions and runtime state targets the part of agent work that usually breaks down: keeping long jobs coherent and resumable. Its shared editing layer also gives people a way to step into agent work by changing the artifact directly, not only through chat.
Sources
- PrimaryHugging Face Papers
Written by AIToolMaps from the source above and checked against it sentence by sentence.