Five small models solve a programming problem together: a planner, two ideators, a solver and a manager, plus a repair worker. Each starts from a fresh context and talks only through files on disk. A script that runs the samples decides success, not a model. It is the method of GVS5H (Lee, 2026), written as a Memdoor workflow: eight YAML files, no code, no model named.

The result

The authors' harness rebuilt on the same model, Qwen3.8-27B, with their prompts, loop and 128K reply cap. The first ten problems of their LiveCodeBench Hard list, five passes each, graded on every hidden test with their corrected grader:

passthis workflowauthors' harnessFable 5, one call
110 / 1097
210 / 10108
310 / 101010
410 / 1098
5*9* / 10107
mean9.89.68.0