# Physics Supernova: AI Agent Matches Elite Gold Medalists at IPhO 2025

arXiv: https://arxiv.org/abs/2509.01659 · HTML: https://mlsanity.com/paper/2509.01659/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 42 references that are in the map.
- First posted on arXiv 1 Sep 2025.

## Builds on (most cited first, 13 of 13)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [Kimina-Prover Preview: Towards Large Formal Reasoning Models with Reinforcement Learning](https://mlsanity.com/paper/2504.11354/) (2025)
- [A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence](https://mlsanity.com/paper/2507.21046/) (2025)
- [Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution](https://mlsanity.com/paper/2505.20286/) (2025)
- [Lean Copilot: Large Language Models as Copilots for Theorem Proving in Lean](https://mlsanity.com/paper/2404.12534/) (2024)
- [Prover Agent: An Agent-Based Framework for Formal Mathematical Proofs](https://mlsanity.com/paper/2506.19923/) (2025)
- [A Survey of the Evolution of Language Model-Based Dialogue Systems: Data, Task and Models](https://mlsanity.com/paper/2311.16789/) (2023)
- [Position: Agent Should Invoke External Tools ONLY When Epistemically Necessary](https://mlsanity.com/paper/2506.00886/) (2025)
- [Formalizing Chemical Physics using the Lean Theorem Prover](https://mlsanity.com/paper/2210.12150/) (2022)
- [Lean4Lean: Verifying a Typechecker for Lean, in Lean](https://mlsanity.com/paper/2403.14064/) (2024)
- [On Path to Multimodal Historical Reasoning: HistBench and HistAgent](https://mlsanity.com/paper/2505.20246/) (2025)

## Built on by (most cited first, 14 of 14)

- [Why LLMs Aren't Scientists Yet: Lessons from Four Autonomous Research Attempts](https://mlsanity.com/paper/2601.03315/) (2026)
- [P1: Mastering Physics Olympiads with Reinforcement Learning](https://mlsanity.com/paper/2511.13612/) (2025)
- [SciAgent: A Unified Multi-Agent System for Generalistic Scientific Reasoning](https://mlsanity.com/paper/2511.08151/) (2025)
- [P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads](https://mlsanity.com/paper/2602.09443/) (2026)
- [CapGeo-Bench: Decoupling Visual Perception from Reasoning and Evaluating Geometric Understanding](https://mlsanity.com/paper/2510.09302/) (2025)
- [Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI](https://mlsanity.com/paper/2510.04978/) (2025)
- [Large Language Models Achieve Gold Medal Performance at the International Olympiad on Astronomy & Astrophysics (IOAA)](https://mlsanity.com/paper/2510.05016/) (2025)
- [ChemLabs on ChemO: A Multi-Agent System for Multimodal Reasoning on IChO 2025](https://mlsanity.com/paper/2511.16205/) (2025)
- [Research on World Models Is Not Merely Injecting World Knowledge into Specific Tasks](https://mlsanity.com/paper/2602.01630/) (2026)
- [MorphoBench: A Benchmark with Difficulty Adaptive to Model Reasoning](https://mlsanity.com/paper/2510.14265/) (2025)
- [Agentic AI for Scalable and Robust Optical Systems Control](https://mlsanity.com/paper/2602.20144/) (2026)
- [Mastering Olympiad-Level Physics with Artificial Intelligence](https://mlsanity.com/paper/2511.10515/) (2025)
- [ReasFlow: Assisting Reasoning-Centric Scientific Discovery in Applied Mathematics via a Knowledge-Based Multi-Agent System](https://mlsanity.com/paper/2607.14178/) (2026)
- [Can AI Evaluate AI Scientists? A Benchmarking Study of Autonomous Research Generation Systems Using Automated Multi-Model Review](https://mlsanity.com/paper/2607.28631/) (2026)

## Abstract (arXiv)

Physics provides fundamental laws that describe and predict the natural world. AI systems aspiring toward more general, real-world intelligence must therefore demonstrate strong physics problem-solving abilities: to formulate and apply physical laws for explaining and predicting physical processes. The International Physics Olympiad (IPhO)--the world's most prestigious physics competition--offers a rigorous benchmark for this purpose. We introduce Physics Supernova, an AI agent system with superior physics problem-solving abilities that match elite IPhO gold medalists. In IPhO 2025 theory problems, Physics Supernova attains 23.5/30 points, ranking 14th of 406 contestants and surpassing the median performance of human gold medalists. We extensively analyzed Physics Supernova's capabilities and flexibility across diverse physics tasks. These results show that principled tool integration within agent systems can deliver competitive improvements in solving challenging science problems. The codes are available at https://github.com/CharlesQ9/Physics-Supernova.