🛰️ Daily AI Frontier
‹ back to 2026-09-26

Self-Play Pretraining with Zero Data

Research LLMs & Foundation Models

Ranking

Overall 82
Content 95
Popularity N/A

No observed public metrics; popularity remains neutral/archived.

Representative image for Self-Play Pretraining with Zero Data

Merged summary

TL;DR - This paper presents a zero-data pretraining method in which a generator and learner co-evolve from random initialization, creating an adaptive synthetic curriculum without natural training data. It matters because zero-shot performance on natural datasets improves predictably with self-play compute, suggesting a potential route to pretraining limited more by computation than curated data.

  • A generator uses reinforcement learning to propose programs for a universal Turing machine, which produces byte sequences for training.
  • An autoregressive learner predicts those sequences with standard cross-entropy, while the generator targets the frontier of the learner’s capabilities.
  • Zero-shot loss on several natural datasets follows predictable compute scaling despite neither model seeing natural data during training.
  • The learner develops in-context learning behavior, and the system discovers recognizable mathematical sequences.

Sources (1)

Self-Play Pretraining with Zero Data

arXiv cs.AI Aditya Cowsik, Kfir Dolev, Michael Y. Li, G. Bruno De Luca, Nourya Cohen, Noah D. Goodman, Yoav Levine 2026-09-24 arXiv:2609.30063
Public signals N/A
Providers: Hugging Face · N/A OpenAlex · N/A Publisher · N/A Semantic Scholar · N/A X · N/A Fetched 2026-09-26 14:13:33.970300 UTC

TL;DR - This paper presents a zero-data pretraining method in which a generator and learner co-evolve from random initialization, creating an adaptive synthetic curriculum without natural training data. It matters because zero-shot performance on natural datasets improves predictably with self-play compute, suggesting a potential route to pretraining limited more by computation than curated data.

  • A generator uses reinforcement learning to propose programs for a universal Turing machine, which produces byte sequences for training.
  • An autoregressive learner predicts those sequences with standard cross-entropy, while the generator targets the frontier of the learner’s capabilities.
  • Zero-shot loss on several natural datasets follows predictable compute scaling despite neither model seeing natural data during training.
  • The learner develops in-context learning behavior, and the system discovers recognizable mathematical sequences.
item →