A model coaches and judges itself: two rounds of multi-agent self-supervision lift score per output token to 1.2–1.6x baseline
One shared model plays a team of virtual subagents, searches for better multi-agent workflows, picks the best by its own judgment, and trains on that team's executions; this is Multi-Agent Self-Supervision (MASS). With a 27B open-weights model over two cycles, score per output token reached 1.2–1.6x the base model's level on four open-ended research benchmarks. The work also warns that when a model is its own evaluator, shared blind spots could let mistakes be accepted as progress and reinforced through training.