# Recursive Self-Improvement through Multi-Agent Self-Supervision

arXiv: https://arxiv.org/abs/2610.12176 · HTML: https://mlsanity.com/paper/2610.12176/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 45 references that are in the map.
- First posted on arXiv 8 Oct 2026.

## Builds on (most cited first, 15 of 15)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [Self-Rewarding Language Models](https://mlsanity.com/paper/2401.10020/) (2024)
- [Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision](https://mlsanity.com/paper/2312.09390/) (2023)
- [Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models](https://mlsanity.com/paper/2312.06585/) (2023)
- [Language Agents as Optimizable Graphs](https://mlsanity.com/paper/2402.16823/) (2024)
- [Multi-Agent Evolve: LLM Self-Improve through Co-evolution](https://mlsanity.com/paper/2510.23595/) (2025)
- [Recursive Harness Self-Improvement](https://mlsanity.com/paper/2607.15524/) (2026)
- [SIA: Self Improving AI with Harness & Weight Updates](https://mlsanity.com/paper/2605.27276/) (2026)
- [TTHE: Test-Time Harness Evolution](https://mlsanity.com/paper/2607.08124/) (2026)
- [Harness-Aware Self-Evolving: Co-Evolving Model Weights, Harness, and Task Solutions](https://mlsanity.com/paper/2607.03935/) (2026)
- [Squeeze Evolve: Unified Multi-Model Orchestration for Verifier-Free Evolution](https://mlsanity.com/paper/2604.07725/) (2026)
- [HELIX: Model-Harness Co-evolution for Recursive Self-Improvement](https://mlsanity.com/paper/2608.13951/) (2026)
- [Scaling Discovery through Test-Time Communication](https://mlsanity.com/paper/2609.21032/) (2026)
- [Sakana Fugu Technical Report](https://mlsanity.com/paper/2606.21228/) (2026)

## Built on by (most cited first, 1 of 1)

- [SwarmRSI: Recursive Self-Improvement through Evolving Scientific Agent Swarm](https://mlsanity.com/paper/2610.20431/) (2026)

## Abstract (arXiv)

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.