Achieving Olympia-Level Geometry Large Language Model Agent via Complexity Boosting Reinforcement Learning
Abstract
Large language model (LLM) agents exhibit strong mathematical problem-solving abilities and can even solve International Mathematical Olympiad (IMO) level problems with the assistance of formal proof systems. However, due to weak heuristics for auxiliary constructions, AI for geometry problem solving remains dominated by expert models such as AlphaGeometry 2, which rely heavily on large-scale data synthesis and search for both training and evaluation. In this work, we make the first attempt to build a medalist-level LLM agent for geometry and present InternGeometry. InternGeometry overcomes the heuristic limitations in geometry by iteratively proposing propositions and auxiliary constructions, verifying them with a symbolic engine, and reflecting on the engine's feedback to guide subsequent proposals. A dynamic memory mechanism enables InternGeometry to conduct more than two hundred interactions with the symbolic engine per problem. To further accelerate learning, we introduce Complexity-Boosting Reinforcement Learning (CBRL), which gradually increases the complexity of synthesized problems across training stages. Built on InternThinker-32B, InternGeometry solves 44 of 50 IMO geometry problems (2000-2024), exceeding the average gold medalist score (40.9), using only 13K training examples, just 0.004% of the data used by AlphaGeometry 2, demonstrating the potential of LLM agents on expert-level geometry tasks. InternGeometry can also propose novel auxiliary constructions for IMO problems that do not appear in human solutions.
Cite
Text
Zhao et al. "Achieving Olympia-Level Geometry Large Language Model Agent via Complexity Boosting Reinforcement Learning." International Conference on Learning Representations, 2026.Markdown
[Zhao et al. "Achieving Olympia-Level Geometry Large Language Model Agent via Complexity Boosting Reinforcement Learning." International Conference on Learning Representations, 2026.](https://mlanthology.org/iclr/2026/zhao2026iclr-achieving/)BibTeX
@inproceedings{zhao2026iclr-achieving,
title = {{Achieving Olympia-Level Geometry Large Language Model Agent via Complexity Boosting Reinforcement Learning}},
author = {Zhao, Haiteng and Shen, Junhao and Zhang, Yiming and Gao, Songyang and Liu, Kuikun and Ma, Tianyou and Zheng, Fan and Lin, Dahua and Zhang, Wenwei and Chen, Kai},
booktitle = {International Conference on Learning Representations},
year = {2026},
url = {https://mlanthology.org/iclr/2026/zhao2026iclr-achieving/}
}