Alphabell.
Paper · Self-reward and self-play

SWE-growth

SWE-growth: Teacher-Guided Adaptive Self-Play for Software Engineering AgentsA teacher-guided self-play framework that uses verified outcomes to generate training data for a student coding model, improving its performance on SWE-bench.

SWE-growth
Figure 1 of the paper, arXiv. Source
The loop

A student coding model attempts repository-level repair tasks, and a teacher model identifies learning opportunities from the failures. These verified outcomes are used as training data for supervised fine-tuning and reinforcement learning, making the student model better at software engineering.

The loop
SWE-growth
Paper · arXiv
  1. Student model attempts repair tasks
  2. Teacher model identifies learning opportunities
  3. Verified outcomes fine-tune the student
  4. Student improves at software engineering
  1. Student model attempts repair tasks
  2. Teacher model identifies learning opportunities
  3. Verified outcomes fine-tune the student
  4. Student improves at software engineering
↻ The improved system does the next round, and the loop turns again.

Why it is a road to recursion

It demonstrates a scalable self-play framework where a teacher model guides a student model through its own failures to generate high-quality training data for software engineering.

Evidence

Improves Qwen3-Coder-30B-A3B-Instruct from 27.7% to 31.7% on SWE-bench Pro.

self-playcoding-agentsrlhf