# FrontierPhysics: Evaluating Agents for End-to-End Physics Research

**Authors:** Bingran You, Wenjun Ke, Ria Rosenauer, Bo Liu, Wenbo Chen, Min Chen, Shuqi Xu, Yue Ma, Jiechao Feng, Bo Chen, Xiangkai Sun, Jiarui Liu, Jinen Guo, Zeyu Zhou, Xu Huang, Zhuohan Li, Haoyu Li, Heguang Lin, Lijie Ding, Yadong Zeng, Kangqi Zhang, Xinge Liu, Hanwen Liu, Zhenghong Li, Alexander von Recum, Yuchen Zhu, Felix Schwarzfischer, Yizhou Zhao, Jicheng Wang, Binxu Li, Qian Yu, Chan Li, Cheng Dai, Di Wang, Haoyu Zhang, Jiankai Sun, Kaituo Feng, Mian Qin, Ruihong Yin, Yiqun Luo, Weiwei Wu, Shihong Pan, Tsung Yeh Hsieh, Xiao Huang, Yan Zhang, Sihan Li, Zirui Ren, Zengji Tu, Kyoung Whan Choe, Ke Sun, Vincenzo Galia, Vaisakhi Mishra, Jiashu He, Hongyang Wang, Zhiheng Yang, Shubham Gaur, Yifan Gu, Shuyi Wang, Zihao Zuo, Steven Dillmann, Yiyou Sun, Xinyang Han, Hanchung Lee, Molei Tao, Yue Zhao, Shilong Liu, Yuchen Wu, Xuandong Zhao, Xiangyi Li, Florian Brand, Gerbrand Ceder, Hartmut Haeffner  
**Lab:** BenchFlow · **Published:** 4 Nov 2026 · **Upvotes:** 47 · **Level:** Advanced  
**Links:** [arXiv](https://arxiv.org/abs/2611.06910) · [PDF](https://arxiv.org/pdf/2611.06910) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2611.06910.html)

## Curator's notes

**TL;DR:** FrontierPhysics benchmarks AI agents on full-cycle physics research tasks, revealing current models struggle to produce correct, publishable work.

- **What's new:** Introduces an end-to-end benchmark covering literature review, planning, experimentation, and manuscript writing across nine physics domains, unlike prior fixed-question tests.
- **Key result:** Across 22 models in 26 configurations, no configuration passes more than 46 of its 168 rollouts.
- **Why it matters:** Builders need realistic evaluation of AI's ability to conduct genuine scientific research, not just answer isolated questions.

## Key numbers

- **56**: an end-to-end benchmark with 56 tasks made by 42 physicists based on their own research
- **22**: Across 22 models in 26 configurations

## Abstract

AI agents are playing an increasingly important role in physics research. However, existing physics benchmarks only evaluate fixed questions, isolated sub-tasks, or paper reproduction with given solutions, and rarely check research quality alongside correctness. We introduce FrontierPhysics, an end-to-end benchmark with 56 tasks made by 42 physicists based on their own research, covering nine domains across theoretical, computational, and experimental physics. Each task requires agents to review the literature, develop a research plan, conduct research and experiments, and produce structured outputs and scientific manuscripts. Combining deterministic verifiers with expert-authored rubrics, FrontierPhysics evaluates whether agents' research is correct and publishable. Across 22 models in 26 configurations, no configuration passes more than 46 of its 168 rollouts. Manual review of agent trajectories shows that frontier agents' main weaknesses are insufficiently rigorous reasoning and limited expert intuition, rather than gaps in physics knowledge or execution errors.

## What you could build

1. Create a tool that uses the benchmark to fine‑tune language models for research planning.
2. Develop a visual dashboard that tracks agent performance on each benchmark sub‑task.
3. Implement a curriculum that gradually increases task complexity using FrontierPhysics tasks.

## Quiz yourself

What is the maximum number of rollouts any model configuration passes in the FrontierPhysics benchmark?

**Answer:** No configuration passes more than 46 of its 168 rollouts, as reported in the abstract.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.