按年被提到
20252025 · 9 次2026
大模型与语言模型›大模型推理与思维链·arXiv:2502.06807 · cs.LG

Competitive Programming with Large Reasoning Models

OpenAI, :, Ahmed El-Kishky, Alexander Wei, Andre Saraiva, Borys Minaiev, Daniel Selsam, David Dohan, Francis Song, Hunter Lightman, Ignasi Clavera, Jakub Pachocki 等 26 人 · 2025
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 9 人首次 2025-02-12 · 最近 2025-08-29
9不同的人
2活跃月份
8讨论串
61被引(OpenAlex)
arXiv 摘要(候选层不写导读)

We show that reinforcement learning applied to large language models (LLMs) significantly boosts performance on complex coding and reasoning tasks. Additionally, we compare two general-purpose reasoning models - OpenAI o1 and an early checkpoint of o3 - with a domain-specific system, o1-ioi, which uses hand-engineered inference strategies designed for competing in the 2024 International Olympiad in Informatics (IOI). We competed live at IOI 2024 with o1-ioi and, using hand-crafted test-time strategies, placed in the 49th percentile. Under relaxed competition constraints, o1-ioi achieved a gold medal. However, when evaluating later models such as o3, we find that o3 achieves gold without hand-crafted domain-specific strategies or relaxed constraints. Our findings show that 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. Notably, o3 achieves a gold medal at the 2024 IOI and obtains a Codeforces rating on par with elite human competitors. 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.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论marojejian · 2025-02

“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-spec…”

评论khafra · 2025-08

“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…”

Claude Sonnet will ship in Xcode原评论 ↗
评论troupo · 2025-08

“> 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/2…”

Claude Sonnet will ship in Xcode原评论 ↗
被提交为 story · 6 次