logoalt Hacker News

Xx_crazy420_xX • today at 4:55 AM • 1 reply • view on HN

Autoresearch is nothing new, big players are already in the game with more sophisticated solutions:

  - https://arxiv.org/abs/2602.02660 (MARS)
  - https://arxiv.org/abs/2601.14525 (Execution-grounded automated AI research)
  - https://arxiv.org/abs/2601.10402 (ML-Master 2.0)
The mostly used benchmark for automated AI engineering/ research is: https://github.com/openai/mle-bench

Replies

bluequbit • today at 9:20 AM

The thing is, autoresearch feels more accessible that the listed solutions. I can use it trivially on virtually any problem that has verifiable rewards and a feedback loop.

➕ show 2 replies