Reinforcement Learning

Survival is the Only Reward: Sustainable Self-Training Through Environment-Mediated Selection

The original publication this post is based on can be found here: https://arxiv.org/abs/2601.12310. Self-training systems often degenerate due to the lack of an external criterion for judging data quality, leading to …

Generalising from Self-Produced Data: Model Training Beyond Human Constraints

The original publication this post is based on can be found here: https://arxiv.org/abs/2504.04711. Current large language models (LLMs) are constrained by human-derived training data and limited by a single level of …