Brief
Occamy-1.0 aims at the low-cost knee of the co-work cost-performance curve
A 35B co-work model, trained from a post-trained Qwen3.6-35B-A3B checkpoint, is presented as cost-efficient for long-horizon agent workflows. The paper reports it as competitive with larger frontier systems on several tasks, and releases the weights plus a subset of training data.
The pitch is about episode economics rather than peak capability. Co-work agents chain information gathering, tool use, coding and file manipulation across many model invocations, so cost and latency pile up over the whole run. The authors argue many everyday steps are about state tracking, coordination, recovery and follow-through, not frontier-scale reasoning.
The one useful detail for operators: the paper says its aggregate score across four representative benchmarks puts it at the low-cost knee of the observed cost-performance Pareto frontier, under its own stated evaluation and pricing protocol. Supporting evaluations in tool calling, coding and instruction following are reported to preserve broad agentic capability.
Evidence is thin on the operational specifics. The abstract does not give per-benchmark numbers, latency figures, harness configurations or deployment requirements, so treat the frontier claim as the authors' framing rather than a measured result you can plan against.
Our reading
Our reading is that the release is most useful as a candidate to test in cost-sensitive multi-step workflows, not as a settled answer on which model to run.
Source details and supporting facts
Each line is stated by the page named above it.
Stated by arXiv
- Occamy-1.0 is a cost-efficient co-work model obtained by further training the post-trained Qwen3.6-35B-A3B checkpoint.
- The authors construct execution-grounded data and environments, capture replayable long-horizon trajectories across multiple harnesses, and use staged post-training.
- The model weights and a subset of the training data are released to support research on practical co-work agents and agentic post-training.
Sources
- arXivText stored 14 September 2026
How this story was checked. Written from the 1 page listed above, stored 14 September 2026; claims checked against that stored text on 14 September 2026.
What that means
- 3 of 3 reported statements were confirmed against the page that carries them; the rest were removed rather than published.
- Figures in the text were required to appear in the stored source text: yes. Identifiers: yes.
- The check reads stored text only: no claim rests on a fresh look that did not happen.
- Where the reporting was silent, the text says so instead of filling the gap.