frontier models
Two Cooks Expose a Coordination Ceiling
In a twenty-map visual benchmark, one model controls both players through high-level actions; the strongest tested system completes only 26.2 percent of orders on average.
Summary
In a twenty-map visual benchmark, one model controls both players through high-level actions; the strongest tested system completes only 26.2 percent of orders on average.
DuoCook uses top-down Unreal Engine scenes to test whether a vision-language model can track changing state, sequence recipe steps and allocate shared equipment between two players. The benchmark spans twenty maps with contention, terrain changes and handoff dependencies; the engine handles navigation after the model selects high-level actions. The strongest evaluated model completed 26.2 percent of orders on average. A shared self-authored notebook helped some model families and hurt others. The result measures this benchmark’s centralized controller, not human collaboration or all embodied planning.
Why it matters
In a twenty-map visual benchmark, one model controls both players through high-level actions; the strongest tested system completes only 26.2 percent of orders on average.
Limits and context
- The result measures this benchmark’s centralized controller, not human collaboration or all embodied planning.
Key claims
In a twenty-map visual benchmark, one model controls both players through high-level actions; the strongest tested system completes only 26.2 percent of orders on average.
Qualification: The result measures this benchmark’s centralized controller, not human collaboration or all embodied planning.
Evidence: source-2026-10-24-009
Sources
- arXiv preprint 2610.31511, original v1arXiv · primary research
Corrections
No corrections have been recorded for this story.