LLM News

Every LLM release, update, and milestone.

Filtered by:problem-synthesis✕ clear
research

Code agents can evolve math problems into harder variants, study finds

A new study demonstrates that code agents can autonomously evolve existing math problems into more complex, solvable variations through systematic exploration. The multi-agent framework addresses a critical bottleneck in training advanced LLMs toward IMO-level mathematical reasoning by providing a scalable mechanism for synthesizing high-difficulty problems.

2 min readvia arxiv.org