後訓練語言模型在程式設計競賽中取得金牌表現

摘要

競賽程式設計已成為檢驗大型語言模型推理能力的關鍵測試，而IOI與ICPC等國際競賽則代表其中最具挑戰性的場景。我們提出了一條端到端的專精化流程，結合大規模題目篩選、合成推理軌跡、監督式微調（SFT）與強化學習（RL）。利用22,000道精心篩選的題目，我們以SFT與RL訓練了Nemotron-3-Nano-CC（30B-A3B），並僅以SFT訓練了Nemotron-3-Ultra-CC（550B-A55B）。我們進一步引入了GenCorrect，這是一種反饋驅動的測試時間計算策略，可反覆生成、評估並改良多樣化解法。在IOI 2025上，Nano-CC經後訓練後從130分提升至291分，搭配GenCorrect後更達到468分，超過438.3分的金牌門檻，而Ultra-CC則達到502分。在這些結果的引導下，我們開發了一套專為競賽設計的Ultra-CC系統，並於IOI 2026期間進行前瞻性評估。在與人類參賽者相同的時間、網路存取與提交限制之下，该系统於600分中獲得535.4分，同時超過361.12分的金牌門檻與498.27分的最高人類得分。據我們所知，這是第一個在IOI題目中得分超越最高分人類選手的AI系統。

English

Competitive programming has become a key test of large language model reasoning, with international competitions such as IOI and ICPC representing its most challenging settings. We present an end-to-end specialization pipeline combining large-scale problem curation, synthetic reasoning traces, supervised fine-tuning (SFT), and reinforcement learning (RL). Using 22,000 curated problems, we train Nemotron-3-Nano-CC (30B-A3B) with SFT and RL and Nemotron-3-Ultra-CC (550B-A55B) with SFT alone. We further introduce GenCorrect, a feedback-driven test-time compute strategy that iteratively generates, evaluates, and refines diverse solutions. On IOI 2025, Nano-CC improves from 130 points to 291 after post-training and to 468 with GenCorrect, exceeding the gold threshold of 438.3 while Ultra-CC reaches 502. Guided by these results, we develop a competition-specific Ultra-CC system and evaluate it prospectively during IOI 2026. Under the same time, internet-access, and submission constraints as human contestants, it scores 535.4 out of 600, exceeding both the gold threshold of 361.12 and the top human score of 498.27. To our knowledge, this is the first AI system to outscore the highest-scoring human contestant on an IOI problem set.