1/n I’m thrilled to share that our @OpenAI reasoning system scored high enough to achieve gold 🥇🥇 in one of the world’s top programming competitions - the 2025 International Olympiad in Informatics (IOI) - placing first among AI participants! 👨‍💻👨‍💻 2/n We officially competed in the online AI track of the IOI, where we scored higher than all but 5 (of 330) human participants and placed first among AI participants. We had the same 5 hour time limit and 50 submission limit as human participants. Like the human contestants, our system competed *without* internet or RAG, and just access to a basic terminal tool.

Watching the model solve these IMO problems and achieve gold-level performance was magical. A few thoughts 🧵

https://twitter.com/alexwei_/status/1946477742855532918

The model solves these problems without tools like lean or coding, it just uses natural language, and also only has 4.5 hours. We see the model reason at a very high level - trying out different strategies, making observations from examples, and testing hypothesis.

Feeling spooked👻🎃? Get grounded...introducing "Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrieval."

Meet LeReT (Learning to Retrieve by Trying), a RL-based framework that improves LLM’s ability to use retrieval tools by up to 29%.

sherylhsu.com/LeReT/ [2/5] Why is this important?
Like seeing a ghost 👻👻, LLMs often hallucinate (glue in pizza) and grounding LLM answers in retrieved facts improves factuality and transparency. Improving LLM’s ability to retrieve correct information thus improves overall performance.