Towards Verifiable and Self-Correcting AI Physicists for Quantum Many-Body Simulations
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909029103566848 |
|---|---|
| author | Deng, Ken Wang, Xiangfei Duan, Guijing Mo, Chen Huang, Junkun Zhang, Runqing Qian, Ling Huang, Zhiguo Han, Jize Luo, Di |
| author_facet | Deng, Ken Wang, Xiangfei Duan, Guijing Mo, Chen Huang, Junkun Zhang, Runqing Qian, Ling Huang, Zhiguo Han, Jize Luo, Di |
| contents | While large language models (LLMs) promise to revolutionize automated scientific discovery, their application in rigorous real-world physical research is stalled by two critical barriers: a lack of realistic evaluation benchmarks and systemic LLM hallucinations. Here, we address both problems. We introduce QMP-Bench, a pioneering end-to-end research-level benchmark in quantum many-body simulation consisting of $100$ tasks extracted from $21$ high-impact prestigious journals, presenting a challenge even for current frontier LLMs. To establish a paradigm for reliable and transparent AI physicists, we present PhysVEC, a multi-agent framework that enforces self-verifiable and error correction in AI research. PhysVEC seamlessly integrates programming and scientific verifiers to guarantee coding correctness and principle-based physical validity, yielding interpretable evidence and error correction at each step. PhysVEC significantly outperforms existing LLM baselines on various scenarios in QMP-Bench and presents a favorable inference-time scaling, successfully transforming unreliable AI generations into accurate physical reproductions, paving a robust and trustworthy path towards future automated scientific discovery. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_00149 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Towards Verifiable and Self-Correcting AI Physicists for Quantum Many-Body Simulations Deng, Ken Wang, Xiangfei Duan, Guijing Mo, Chen Huang, Junkun Zhang, Runqing Qian, Ling Huang, Zhiguo Han, Jize Luo, Di Computational Physics While large language models (LLMs) promise to revolutionize automated scientific discovery, their application in rigorous real-world physical research is stalled by two critical barriers: a lack of realistic evaluation benchmarks and systemic LLM hallucinations. Here, we address both problems. We introduce QMP-Bench, a pioneering end-to-end research-level benchmark in quantum many-body simulation consisting of $100$ tasks extracted from $21$ high-impact prestigious journals, presenting a challenge even for current frontier LLMs. To establish a paradigm for reliable and transparent AI physicists, we present PhysVEC, a multi-agent framework that enforces self-verifiable and error correction in AI research. PhysVEC seamlessly integrates programming and scientific verifiers to guarantee coding correctness and principle-based physical validity, yielding interpretable evidence and error correction at each step. PhysVEC significantly outperforms existing LLM baselines on various scenarios in QMP-Bench and presents a favorable inference-time scaling, successfully transforming unreliable AI generations into accurate physical reproductions, paving a robust and trustworthy path towards future automated scientific discovery. |
| title | Towards Verifiable and Self-Correcting AI Physicists for Quantum Many-Body Simulations |
| topic | Computational Physics |
| url | https://arxiv.org/abs/2604.00149 |