AutoMaster
AutoMaster: Autonomous Post-Training by Making the Same Model a Better TeacherAn autonomous post-training system uses an LLM agent to develop interventions that improve a teacher model's rollouts, yielding better fine-tuning data for target models.

An LLM agent analyzes teacher trajectories to design skills that suppress undesirable habits and elicit effective behaviors. This improves the teacher model, which then generates higher quality data to fine-tune a better successor.
- Agent analyzes teacher trajectories
- Agent designs skills to suppress bad habits
- Teacher model generates improved rollouts
- Target model fine-tunes on better data
- Agent analyzes teacher trajectories
- Agent designs skills to suppress bad habits
- Teacher model generates improved rollouts
- Target model fine-tunes on better data
Why it is a road to recursion
Automating the design of post-training interventions allows models to continuously refine their own teaching behaviors without human-engineered skill definitions.
Evidence
Improves mean performance over Vanilla SFT on successful unguided teacher trajectories by 1.42 to 8.99 percentage points across 4B and 9B target models.
Related loops
More training data →
- Aligned model generates training data
- Reward model judges and filters it
- Data trains next intermediate instruct model
- Next model generates better alignment data
- repeat

- Proposer agent builds environments
- Solver generates rollouts
- Rollouts guide next environments
- Solver trains on new environments
- repeat

- Simulator co-evolves tasks and adversaries
- Generates challenging web agent scenarios
- Agent trains on resulting curriculum
- Agent handles harder tasks and attacks
- repeat