mlsanityData to 14 Oct 2026

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

arXiv 2509.01659 ↗First posted 1 Sep 2025cs.AIcited by 14

Not on the map. Why?

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.

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

13 of 42 references.

References · 13

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,986
  3. 2023GAIA: a benchmark for General AI Assistantscited by 1,128
  4. 2025Kimina-Prover Preview: Towards Large Formal Reasoning Models with Reinforcement Learningcited by 180
  5. 2025A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligencecited by 170
  6. 2025Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolutioncited by 116
  7. 2024Lean Copilot: Large Language Models as Copilots for Theorem Proving in Leancited by 58
  8. 2025Prover Agent: An Agent-Based Framework for Formal Mathematical Proofscited by 31
  9. 2023A Survey of the Evolution of Language Model-Based Dialogue Systems: Data, Task and Modelscited by 23
  10. 2025Position: Agent Should Invoke External Tools ONLY When Epistemically Necessarycited by 22
  11. 2022Formalizing Chemical Physics using the Lean Theorem Provercited by 9
  12. 2024Lean4Lean: Verifying a Typechecker for Lean, in Leancited by 8
1 more
  1. 2025On Path to Multimodal Historical Reasoning: HistBench and HistAgentcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 8; 2026: 6.

14 papers.

Sort:

By area:

  1. 2026Why LLMs Aren't Scientists Yet: Lessons from Four Autonomous Research Attemptscited by 13
  2. 2025P1: Mastering Physics Olympiads with Reinforcement Learningcited by 8
  3. 2025SciAgent: A Unified Multi-Agent System for Generalistic Scientific Reasoningcited by 7
  4. 2026P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiadscited by 7
  5. 2025CapGeo-Bench: Decoupling Visual Perception from Reasoning and Evaluating Geometric Understandingcited by 5
  6. 2025Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AIcited by 3
  7. 2025Large Language Models Achieve Gold Medal Performance at the International Olympiad on Astronomy & Astrophysics (IOAA)cited by 3
  8. 2025ChemLabs on ChemO: A Multi-Agent System for Multimodal Reasoning on IChO 2025cited by 3
  9. 2026Research on World Models Is Not Merely Injecting World Knowledge into Specific Taskscited by 3
  10. 2025MorphoBench: A Benchmark with Difficulty Adaptive to Model Reasoningcited by 2
  11. 2026Agentic AI for Scalable and Robust Optical Systems Controlcited by 2
  12. 2025Mastering Olympiad-Level Physics with Artificial Intelligencecited by 1
2 more
  1. 2026ReasFlow: Assisting Reasoning-Centric Scientific Discovery in Applied Mathematics via a Knowledge-Based Multi-Agent Systemcited by 1
  2. 2026Can AI Evaluate AI Scientists? A Benchmarking Study of Autonomous Research Generation Systems Using Automated Multi-Model Reviewcited by 1