When AI output gets too good for human experts to grade, how does self-improvement keep going? A new method breaks right through that wall. Title: Recursive Self-Improvement through Multi-Agent Self-Supervision URL: A single model grading its own output hits a ceiling fast. MASS (Multi-Agent Self-Supervision) coordinates multiple copies of the same model to evolve better workflows, then retrains itself on the resulting traces, breaking the homogeneous self-critique loop. 🧬 Evolving workflows For each task, an evolutionary search improves the orchestrator-subagent setup, meaning roles, instructions, output contracts, and execution order, guided only by self-evaluation, gradually discovering better coordination patterns. 📈 Efficiency and performance together Across two improvement cycles on Qwen3.6-27B, MASS delivers 1.2-1.6x higher performance per output token on four open-ended benchmarks. Students trained on multi-agent traces even outperformed single-agent students trained on 1.4x more tokens. 🔁 Internalization drives the bootstrap Without any workflow prompt at inference time, coordination behaviors like code handoffs start appearing on their own, jumping from 1 in 110 trajectories to 83 in 110. The improved model then becomes a better optimizer and evaluator for the next cycle, keeping the recursive loop spinning. As AI output increasingly outpaces human grading, having models supervise each other through coordination looks like a path worth watching closely. #AIAgents# #SelfImprovement#