Paper Detail
Tingjia Miao, Wenkai Jin, Muhua Zhang, Jinxin Tan, Yuelin Hu, Tu Guo, Jiejun Zhang, Yuhan Wang, Wenbo Li, Yinuo Gao, Shuo Chen, Weiqi Jiang, Yayun Hu, Zixing Lei, Xianghe Pang, Zexi Liu, Yuzhi Zhang, Linfeng Zhang, Kun Chen, Wei Wang, Weinan E, Siheng Chen
The paradigm of agentic science requires AI systems to conduct robust reasoning and engage in long-horizon, autonomous exploration. However, current scientific benchmarks remain confined to domain knowledge comprehension and complex reasoning, failing to evaluate the exploratory nature and procedural complexity of real-world research. In this work, we present research-oriented evaluations in theoretical and computational physics, a natural testbed with comprehensive domain knowledge, complex reasoning, and verifiable end-to-end workflows without reliance on experiments. Here we introduce PRL-Bench (Physics Research by LLMs), a benchmark designed to systematically map the capability boundaries of LLMs in executing end-to-end physics research. Constructed from 100 curated papers from the latest issues of Physical Review Letters since August 2025 and validated by domain experts, PRL-Bench covers five major theory- and computation-intensive subfields of modern physics: astrophysics, condensed matter physics, high-energy physics, quantum information, and statistical physics. Each task in the benchmark is designed to replicate the core properties of authentic scientific research, including exploration-oriented formulation, long-horizon workflows, and objective verifiability, thereby reconstructing the essential reasoning processes and research workflows of real physics research. Evaluation across frontier models shows that performance remains limited, with the best overall score below 50, revealing a pronounced gap between current LLM capabilities and the demands of real scientific research. PRL-Bench serves a reliable testbed for accessing next generation AI scientists advancing AI systems toward autonomous scientific discovery.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@misc{miao2026prl,
title = {PRL-Bench: A Comprehensive Benchmark Evaluating LLMs' Capabilities in Frontier Physics Research},
author = {Tingjia Miao and Wenkai Jin and Muhua Zhang and Jinxin Tan and Yuelin Hu and Tu Guo and Jiejun Zhang and Yuhan Wang and Wenbo Li and Yinuo Gao and Shuo Chen and Weiqi Jiang and Yayun Hu and Zixing Lei and Xianghe Pang and Zexi Liu and Yuzhi Zhang and Linfeng Zhang and Kun Chen and Wei Wang and Weinan E and Siheng Chen},
year = {2026},
abstract = {The paradigm of agentic science requires AI systems to conduct robust reasoning and engage in long-horizon, autonomous exploration. However, current scientific benchmarks remain confined to domain knowledge comprehension and complex reasoning, failing to evaluate the exploratory nature and procedural complexity of real-world research. In this work, we present research-oriented evaluations in theoretical and computational physics, a natural testbed with comprehensive domain knowledge, complex rea},
url = {https://huggingface.co/papers/2604.15411},
keywords = {agentic science, scientific benchmarks, theoretical physics, computational physics, LLMs, PRL-Bench, end-to-end workflows, scientific research, autonomous exploration, domain knowledge, huggingface daily},
eprint = {2604.15411},
archiveprefix = {arXiv},
}
{}