Metraipolis › archive › dc_c7a7cf94fc74

Recursive Self-Improvement through Multi-Agent Self-Supervision — arXiv:2610.12176

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.12176
License (as archived)
CC0-1.0
Archived
2026-10-09T05:50:38.113Z
SHA-256 of the archived text
070f32177b57347dfef370eafea9040736090c1c19323ffb9c2f9f67ac70b953
Stable URL of this page
https://metraipolis.com/documento/dc_c7a7cf94fc74

How to cite

Recursive Self-Improvement through Multi-Agent Self-Supervision — arXiv:2610.12176 — arXiv (en), https://arxiv.org/abs/2610.12176 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c7a7cf94fc74 (Metraipolis archive dc_c7a7cf94fc74, sha256 070f32177b57347dfef370eafea9040736090c1c19323ffb9c2f9f67ac70b953)
BibTeX
@misc{dcc7a7cf94fc74,
  title = {Recursive Self-Improvement through Multi-Agent Self-Supervision — arXiv:2610.12176},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.12176},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c7a7cf94fc74; sha256 070f32177b57347dfef370eafea9040736090c1c19323ffb9c2f9f67ac70b953},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.12176. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recursive self-improvement (RSI) of a model on non-verifiable tasks, such as open-ended research, faces a supervision bottleneck when its outputs exceed what even human experts can reliably assess, leaving the model itself (optimizee) as the best available optimizer and evaluator. However, a single model instance struggles to critique and improve its own complex reasoning under this homogeneous loop. To address this, we propose Multi-Agent Self-Supervision (MASS), an RSI method that alternates between evolutionary workflow optimization and supervised fine-tuning on self-generated trajectories. Guided by early findings that multi-agent topologies excel at complex reasoning, MASS prompts a single base model to iteratively propose, execute, and self-evaluate multi-agent workflows. Through an evolutionary search constrained by structural guardrails, the model optimizes these computational-graph-like orchestrations, discovering the most effective distinct roles and information routing for a given task. Over two MASS cycles with Qwen3.6-27B, the model achieves 1.2-1.6x higher performance per output tokens on four open-ended public benchmarks. Because the improved model subsequently acts as a better optimizer and evaluator, this alternating framework enables a continuous, recursive bootstrapping of the model's capabilities. Moreover, multi-agent traces are also more training-efficient: a student trained on them outperforms a single-agent student trained on 1.4x more training tokens. These findings suggest that jointly learning orchestration and bounded subagent execution from multi-agent trajectories can provide an effective signal for RSI.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.12176 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T05:47:01.090Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).