# Multi-Agent Self-Supervision for AI Self-Improvement

> AI system learns to improve itself using team coordination.
- Title: Multi-Agent Self-Supervision for AI Self-Improvement
- Summary: AI system learns to improve itself using team coordination. AI model enhances research capabilities through self-supervised multi-agent teamwork.
- Keywords: mass, self-improvement, multi-agent, recursive self-improvement, ai research, workflow optimization, ai training, technology, startups, Self-Supervision, Sakana AI
- Source: Sakana AI — https://pub.sakana.ai/mass
- Read time: 1 min
- Topics: mass, ai, self-improvement, multi-agent, recursive self-improvement, ai research, workflow optimization, ai training, technology, startups
## MASS: Recursive Self-Improvement
AI system improves itself using multi-agent teamwork to create better research outputs.
## Why Self-Supervision Matters
Frontier AI models need self-supervision to advance beyond human knowledge without external evaluators.
## Homogeneous Recursive Self-Improvement
The model acts as both optimizer and evaluator to improve itself through self-supervision.
## Teamwork for AI Learning
MASS uses multi-agent teams to create self-supervision signals for recursive self-improvement.
## How MASS Works
Inner loop optimizes team workflow while outer loop updates model weights with selected executions.
## Workflow Optimization
Team workflow search finds optimal sequences for data preparation, feature construction, and backtesting.
## Training Process
MASS trains on selected team executions to improve model performance across research tasks.
## Performance Results
Two rounds of MASS improve task performance from 53.9% to 69.9% against base model on test tasks.
## Benchmark Improvements
MASS achieves 1.2, 1.6× better performance on public benchmarks after two rounds of self-improvement.
## Role Generalization
MASS improves workflow optimizer and evaluator capabilities through self-supervision.
## Coordination Without Workflow
Model learns to delegate tasks without explicit workflow instructions through self-improvement.
## Information Flow Analysis
Optimal workflows encode more task information in contracts and call order than roles and instructions.
## Trajectory Effectiveness
Multi-agent trajectories provide denser learning signals than single-agent trajectories for self-improvement.
## Optimizer Bottleneck
The model's optimizer is the main bottleneck for self-improvement, not the evaluator.
## Safety Concerns
Shared blind spots in self-evaluation could lead to unsafe improvements if not corrected.
## The Odyssean Moment
AI could achieve continuous self-learning without external supervisors.
## Key takeaway

AI model enhances research capabilities through self-supervised multi-agent teamwork.