Competitive Programming with Large Reasoning Models · HackerPapers discussions

Competitive Programming with Large Reasoning Models — mentioned by troupo

Fri, 29 Aug 2025 12:29:59 GMT

> the extrapolation should have been straightforward, Indeed."By late next month you'll have over four dozen husbands" https://xkcd.com/605/ > So, here's some support for my second claim: I don't think any of these links support the claim that "No SOTA model was trained without verified reward training for math and programming" https://arxiv.org/abs/2507.06920: "We hope this work contributes to building a scalable foundation for reliable LLM code evaluation" https://arxiv.org/abs/2506.11425: A custom agent with a custom environment and a custom training dataset on ~800 predetermined problems.…

Paper and discussion history. A mention is not an endorsement.

Competitive Programming with Large Reasoning Models — mentioned by khafra

Fri, 29 Aug 2025 07:42:31 GMT

My two claims: 1. OpenAI has been doing verifier-guided training since last year. 2. No SOTA model was trained without verified reward training for math and programming. I supported the first claim with a document describing what OpenAI was doing last year; the extrapolation should have been straightforward, but it's easy for people who aren't tracking AI progress to underestimate the rate at which it occurs. So, here's some support for my second claim: https://arxiv.org/abs/2507.06920 https://arxiv.org/abs/2506.11425 https://arxiv.org/abs/2502.06807

Paper and discussion history. A mention is not an endorsement.

Competitive Programming with Large Reasoning Models — HN submission

Sun, 16 Feb 2025 23:32:10 GMT

OpenAI: Competitive Programming with Large Reasoning Models

2 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

Competitive Programming with Large Reasoning Models — HN submission

Sat, 15 Feb 2025 04:05:09 GMT

Competitive Programming with Large Reasoning Models

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Competitive Programming with Large Reasoning Models — mentioned by marojejian

Fri, 14 Feb 2025 18:08:22 GMT

Paper: https://arxiv.org/html/2502.06807v1 "although specialized pipelines such as o1-ioi yield solid improvements, the scaled-up, general-purpose o3 model surpasses those results without relying on hand-crafted inference heuristics." "Overall, these results indicate that scaling general-purpose reinforcement learning, rather than relying on domain-specific techniques, offers a robust path toward state-of-the-art AI in reasoning domains, such as competitive programming."

Paper and discussion history. A mention is not an endorsement.

Competitive Programming with Large Reasoning Models — HN submission

Wed, 12 Feb 2025 22:37:05 GMT

Competitive programming with large language models

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Competitive Programming with Large Reasoning Models — HN submission

Wed, 12 Feb 2025 13:59:52 GMT

Competitive Programming with Large Reasoning Models

6 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Competitive Programming with Large Reasoning Models — HN submission

Wed, 12 Feb 2025 05:35:29 GMT

OpenAI o3 just scored 99.8% on CodeForces using brute-force

2 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

Competitive Programming with Large Reasoning Models — HN submission

Wed, 12 Feb 2025 04:22:01 GMT

Competitive Programming with Large Reasoning Models

16 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.