# Intern-S1-MO: Long-horizon Reasoning Agent for Olympiad?Level Mathematical Problem Solving

arXiv: https://arxiv.org/abs/2512.10739 · HTML: https://mlsanity.com/paper/2512.10739/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Mathematical reasoning, one of 17 directions in LLM reasoning.
- Builds on 19 of its 56 references that are in the map.
- First posted on arXiv 11 Dec 2025.

## Placed in

- LLM reasoning / [Mathematical reasoning](https://mlsanity.com/lr/mathematical-reasoning/)

## Builds on (most cited first, 19 of 19)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [ProcessBench: Identifying Process Errors in Mathematical Reasoning](https://mlsanity.com/paper/2412.06559/) (2024)
- [TTRL: Test-Time Reinforcement Learning](https://mlsanity.com/paper/2504.16084/) (2025)
- [ToRL: Scaling Tool-Integrated RL](https://mlsanity.com/paper/2503.23383/) (2025)
- [Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving](https://mlsanity.com/paper/2507.23726/) (2025)
- [Prover-Verifier Games improve legibility of LLM outputs](https://mlsanity.com/paper/2407.13692/) (2024)
- [Winning Gold at IMO 2025 with a Model-Agnostic Verification-and-Refinement Pipeline](https://mlsanity.com/paper/2507.15855/) (2025)
- [Agent RL Scaling Law: Agent RL with Spontaneous Code Execution for Mathematical Problem Solving](https://mlsanity.com/paper/2505.07773/) (2025)
- [rStar2-Agent: Agentic Reasoning Technical Report](https://mlsanity.com/paper/2508.20722/) (2025)
- [Intern-S1: A Scientific Multimodal Foundation Model](https://mlsanity.com/paper/2508.15763/) (2025)
- [Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning](https://mlsanity.com/paper/2502.06781/) (2025)
- [Mask-DPO: Generalizable Fine-grained Factuality Alignment of LLMs](https://mlsanity.com/paper/2503.02846/) (2025)
- [SATORI-R1: Incentivizing Multimodal Reasoning through Explicit Visual Anchoring](https://mlsanity.com/paper/2505.19094/) (2025)
- [ARTIST: Improving the Generation of Text-rich Images with Disentangled Diffusion Models and Large Language Models](https://mlsanity.com/paper/2406.12044/) (2024)
- [The Imitation Game: Turing Machine Imitator is Length Generalizable Reasoner](https://mlsanity.com/paper/2507.13332/) (2025)

## Built on by (most cited first, 4 of 4)

- [Seed-Prover 1.5: Mastering Undergraduate-Level Theorem Proving via Learning from Experience](https://mlsanity.com/paper/2512.17260/) (2025)
- [Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models](https://mlsanity.com/paper/2512.24618/) (2025)
- [Intern-S2-Preview: Scientific Agentic Foundation Model](https://mlsanity.com/paper/2608.13505/) (2026)
- [ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning](https://mlsanity.com/paper/2606.03503/) (2026)

## Abstract (arXiv)

Large Reasoning Models (LRMs) have expanded the mathematical reasoning frontier through Chain-of-Thought (CoT) techniques and Reinforcement Learning with Verifiable Rewards (RLVR), capable of solving AIME-level problems. However, the performance of LRMs is heavily dependent on the extended reasoning context length. For solving ultra-hard problems like those in the International Mathematical Olympiad (IMO), the required reasoning complexity surpasses the space that an LRM can explore in a single round. Previous works attempt to extend the reasoning context of LRMs but remain prompt-based and built upon proprietary models, lacking systematic structures and training pipelines. Therefore, this paper introduces Intern-S1-MO, a long-horizon math agent that conducts multi-round hierarchical reasoning, composed of an LRM-based multi-agent system including reasoning, summary, and verification. By maintaining a compact memory in the form of lemmas, Intern-S1-MO can more freely explore the lemma-rich reasoning spaces in multiple reasoning stages, thereby breaking through the context constraints for IMO-level math problems. Furthermore, we propose OREAL-H, an RL framework for training the LRM using the online explored trajectories to simultaneously bootstrap the reasoning ability of LRM and elevate the overall performance of Intern-S1-MO. Experiments show that Intern-S1-MO can obtain 26 out of 35 points on the non-geometry problems of IMO2025, matching the performance of silver medalists. It also surpasses the current advanced LRMs on inference benchmarks such as HMMT2025, AIME2025, and CNMO2025. In addition, our agent officially participates in CMO2025 and achieves a score of 102/126 under the judgment of human experts, reaching the gold medal level.