AI Paper Atlas

Research map / Large language models / Agents, code and math

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

Wanjia Zhao, Qinwei Ma, Jingzhe Shi, Shirley Wu, Jiaqi Han, Yijia Xiao, Si-Yuan Chen, Xiao Luo, Ludwig Schmidt, James Zou

ICLR 2026 · Large language models › Agents, code and math · approach: Inductive and abstract reasoning evaluation · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use PRISM-DAG causal DAG scoring instead of LLM-as-Judgeevaluation framework · Human alignment (70 problems)Kendall tau_b: 0.294 -> 0.346Improved
use PRISM-DAG instead of PSAS-S step-independent scoringevaluation framework · Human alignment (70 problems)Kendall tau_b: 0.213 -> 0.346Improved
raise GPT-5 reasoning effort from low to highGPT-5 · PRISM-Physics text-only (avg)step-level accuracy: 46.17 -> 54.13Improved
raise GPT-5 reasoning effort from low to mediumGPT-5 · PRISM-Physics text-only (avg)step-level accuracy: 46.17 -> 37.55Hurt
raise GPT-5-mini reasoning effort from low to highGPT-5-mini · PRISM-Physics text-only (avg)step-level accuracy: 37.02 -> 48.78Improved
raise GPT-5-mini reasoning effort from low to highGPT-5-mini · PRISM-Physics text-only (avg)final-answer accuracy: 18.71 -> 26.01Improved
raise GPT-5-mini reasoning effort from low to medium (latency)GPT-5-mini · PRISM-Physicslatency: 129.0% higherHurt
add diagrams (multimodal input)Gemini-2.5-Pro · PRISM-Physics (avg)step-level accuracy: 41.19 -> 50.49Improved
add diagrams (multimodal input)GPT-5 (medium) · PRISM-Physics (avg)step-level accuracy: 37.55 -> 54.43Improved
add diagrams (multimodal input)Claude-sonnet-4 · PRISM-Physics (avg)final-answer accuracy: 16.54 -> 19.19Improved
add diagrams (multimodal input)smaller or weaker models · PRISM-PhysicsaccuracyMixed
use reasoning models instead of chat modelsLLMs · PRISM-Physicsaccuracy: 41.36 -> 43.39Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy