arXiv AI September 3, 2026 By Aleksander Ficek, Sean Narenthiran, Mehrzad Samadi, Somshubra Majumdar, Boris Ginsburg

Post-Training Language Models for Gold-Medal Performance in Coding Competitions

The paper reports a specialized training pipeline for large language models to excel in competitive programming, combining problem curation, synthetic reasoning traces, supervised fine‑tuning, and reinforcement learning. Using 22,000 curated problems, the authors train two models—Nemotron‑3‑Nano‑CC (30B) and Nemotron‑3‑Ultra‑CC (550B)—and introduce GenCorrect, a test‑time refinement strategy. On the IOI 2025 benchmark, Nano‑CC scores 468 points with GenCorrect, surpassing the gold‑medal threshold, while Ultra‑CC reaches 502; in IOI 2026, a competition‑specific Ultra‑CC system scores 535.4, exceeding both the gold threshold and the top human score of 498.27, marking the first AI system to outscore the highest‑scoring human contestant on an IOI problem set.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Sep 12

An Open Recipe for IMO Gold: Training Nemotron for Olympiad Mathematics

The paper presents a method for training Nemotron 3 Ultra to generate proofs for difficult Olympiad mathematics. By fine‑tuning two specialist checkpoints with supervised learning and reinforcement learning, the authors evaluate how checkpoint selection, verification, and refinement affect performance. The resulting open‑model pipeline, which operates entirely in natural language without external tools, achieved 30 out of 42 points at IMO 2026, meeting the gold‑medal threshold, and the authors release the checkpoints, training data, code, solutions, and a new benchmark of 200 problems.

By Ivan Moshkov, Stephen Ge, George Armstrong, Wei Du, Sadegh Mahdavi, Igor Gitman

reinforcement-learning fine-tuning benchmarks

arXiv AI

Jul 9

LiveOIBench: Can Large Language Models Outperform Human Contestants in Informatics Olympiads?

arXiv:2510. 09595v3 Announce Type: replace Abstract: Competitive programming problems are increasingly used to evaluate the coding capabilities of large language models (LLMs) due to their complexity and ease of verification.

By Kaijian Zou, Aaron Xiong, Yunxiang Zhang, Frederick Zhang, Yueqi Ren, Jirong Yang, Ayoung Lee, Shitanshu Bhushan, Lu Wang

llms benchmarks

arXiv AI

Jun 26

NebulaExp-8B: An Empirical Post-Training Pipeline via Full-Scale Ablation Research

arXiv:2606. 26671v1 Announce Type: new Abstract: Post-training alignment determines the reasoning and human preference following capabilities of large language models, yet most existing works withhold detailed data construction, filtering rules and training recipes, which hinders community reproducibility and lightweight model optimization.

By Qiaobo Hao, Yangqian Wu, Shunyi Wang, Zhongjian Zhang, Ziqun Li, Yayin He, Muqing Li, Chen Zhong

llms reinforcement-learning fine-tuning efficiency benchmarks safety

arXiv AI

Jul 14

GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning

arXiv:2604. 02721v2 Announce Type: replace Abstract: Competitive programming remains one of the last few human strongholds in coding against AI.

By DeepReinforce Team, Xiaoya Li, Guoyin Wang, Songqiao Su, Chris Shum, Jiwei Li

llms agents nlp reinforcement-learning

arXiv AI

Jun 9

Reasoning Arena: Trace Tournaments When Verifiable Rewards Fall Short

arXiv:2606. 09380v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a leading paradigm for improving the reasoning ability of large language models through outcome-based supervision.

By Han Zhou, Adam X. Yang, Laurence Aitchison, Anna Korhonen, Albert Q. Jiang

llms reinforcement-learning benchmarks

arXiv AI

Jul 20

Understanding Reasoning from Pretraining to Post-Training

arXiv:2607. 16097v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become central to improving large language models (LLMs) on complex reasoning tasks, yet RL post-training is largely studied in isolation from the pretraining that precedes it.

By Jingyan Shen, Ang Li, Salman Rahman, Yifan Sun, Micah Goldblum, Matus Telgarsky, Pavel Izmailov

llms reinforcement-learning fine-tuning

One email a morning, machine-written

Related stories

An Open Recipe for IMO Gold: Training Nemotron for Olympiad Mathematics

LiveOIBench: Can Large Language Models Outperform Human Contestants in Informatics Olympiads?

NebulaExp-8B: An Empirical Post-Training Pipeline via Full-Scale Ablation Research

GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning

Reasoning Arena: Trace Tournaments When Verifiable Rewards Fall Short

Understanding Reasoning from Pretraining to Post-Training