# PRISM-Physics: Causal DAG-Based Process Evaluation for Physics Reasoning

arXiv: https://arxiv.org/abs/2510.03185 · HTML: https://mlsanity.com/paper/2510.03185/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 14 of its 46 references that are in the map.
- First posted on arXiv 3 Oct 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 14 of 14)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems](https://mlsanity.com/paper/2402.14008/) (2024)
- [MiniF2F: a cross-system benchmark for formal Olympiad-level mathematics](https://mlsanity.com/paper/2109.00110/) (2021)
- [Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models](https://mlsanity.com/paper/2410.07985/) (2024)
- [Competitive Programming with Large Reasoning Models](https://mlsanity.com/paper/2502.06807/) (2025)
- [Proof or Bluff? Evaluating LLMs on 2025 USA Math Olympiad](https://mlsanity.com/paper/2503.21934/) (2025)
- [Can Language Models Solve Olympiad Programming?](https://mlsanity.com/paper/2404.10952/) (2024)
- [Are Your LLMs Capable of Stable Reasoning?](https://mlsanity.com/paper/2412.13147/) (2024)
- [PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Models](https://mlsanity.com/paper/2504.16074/) (2025)
- [PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoning](https://mlsanity.com/paper/2502.12054/) (2025)
- [Evaluating Mathematical Reasoning of Large Language Models: A Focus on Error Identification and Correction](https://mlsanity.com/paper/2406.00755/) (2024)
- [SeePhys: Does Seeing Help Thinking? -- Benchmarking Vision-Based Physics Reasoning](https://mlsanity.com/paper/2505.19099/) (2025)
- [Improving Physics Reasoning in Large Language Models Using Mixture of Refinement Agents](https://mlsanity.com/paper/2412.00821/) (2024)
- [OIBench: Benchmarking Strong Reasoning Models with Olympiad in Informatics](https://mlsanity.com/paper/2506.10481/) (2025)

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

- [TSRBench: A Comprehensive Multi-task Multi-modal Time Series Reasoning Benchmark for Generalist Models](https://mlsanity.com/paper/2601.18744/) (2026)
- [Stargazer: A Scalable Model-Fitting Benchmark Environment for AI Agents under Astrophysical Constraints](https://mlsanity.com/paper/2604.15664/) (2026)
- [Scientific Logicality Enriched Methodology for LLM Reasoning: A Practice in Physics](https://mlsanity.com/paper/2605.17104/) (2026)
- [How Good Are Frontier Models at Physics? Expert Re-Grading Reveals Broken Evaluations and Near-Saturation of Leading Benchmarks](https://mlsanity.com/paper/2609.13009/) (2026)

## Abstract (arXiv)

Benchmarks for competition-style reasoning have advanced evaluation in mathematics and programming, yet physics remains comparatively explored. Most existing physics benchmarks evaluate only final answers, which fail to capture reasoning processes, while recent stepwise methods rely on heuristic LLM-as-judge scoring or restrictive linear assumptions, limiting reliability and diagnostic validity. We introduce PRISM-Physics, a process-level evaluation framework and benchmark for complex physics reasoning problems. Solutions are represented as directed acyclic graphs (DAGs) of formulas, explicitly encoding causal dependencies among intermediate steps to enable fine-grained, interpretable, and theoretically grounded scoring. We prove the optimality of the DAG representation and the corresponding scoring policy. Combining with a fully rule-based method for symbolic formula equivalence matching that we developed, we ensure consistent validation across diverse formulations without heuristic judgments. Results show that our evaluation framework is more aligned with human experts' scoring. Experiments on state-of-the-art LLMs reveal persistent reasoning failures in physics, while step-level scoring offers both diagnostic insight and rich signals for later training. By combining structural rigor, theoretical guarantees, and symbolic validation, PRISM-Physics provides a principled foundation for advancing process-level evaluation and guiding the development of models with deeper scientific reasoning capabilities.