12 papers
ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research
Wanghan Xu, Shuo Li, Tianlin Ye +48
AI coding agents are increasingly used for scientific work, but their end-to-end autonomous research capability remains difficult to verify. We present ResearchClawBench, a benchma…
SCI-PRM: A Tool Aware Process Reward Model for Scientific Reasoning Verification
Xiangyu Zhao, Henry Hengyuan Zhao, Yiheng Wang +7
While Process Reward Models (PRMs) have achieved remarkable success in mathematical reasoning, their application in complex scientific domains-such as biology, chemistry, and physi…
Exponentially improved quantum simulation of scalar QFT
Qing-Hong Cao, Ying-Ying Li, Xiaohui Liu +2
Quantum simulations of scalar quantum field theories (QFT) provide important benchmarks for demonstrating quantum advantage. We revisit digitization in the occupation basis, which…
PRBench: End-to-end Paper Reproduction in Physics Research
Shi Qiu, Junyi Deng, Yiwei Deng +48
AI agents powered by large language models exhibit strong reasoning and problem-solving capabilities, enabling them to assist scientific research tasks such as formula derivation a…
An End-to-end Architecture for Collider Physics and Beyond
Shi Qiu, Zeyu Cai, Jiashen Wei +7
We present, to our knowledge, the first language-driven agent system capable of executing end-to-end collider phenomenology tasks, instantiated within a decoupled, domain-agnostic…
Detailed balance in large language model-driven agents
Zhuo-Yang Song, Qing-Hong Cao, Ming-xing Luo +1
Large language model (LLM)-driven agents are emerging as a powerful new paradigm for solving complex problems. Despite the empirical success of these practices, a theoretical frame…
Omni-Weather: A Unified Multimodal Model for Weather Radar Understanding and Generation
Zhiwang Zhou, Yuandong Pu, Xuming He +10
Weather modeling requires both accurate prediction and mechanistic interpretation, yet existing methods treat these goals in isolation, separating generation from understanding. To…
Iterated Agent for Symbolic Regression
Zhuo-Yang Song, Zeyu Cai, Shutao Zhang +8
Symbolic regression (SR), the automated discovery of mathematical expressions from data, is a cornerstone of scientific inquiry. However, it is often hindered by the combinatorial…
PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Models
Shi Qiu, Shaoyang Guo, Zhuo-Yang Song +51
Current benchmarks for evaluating the reasoning capabilities of Large Language Models (LLMs) face significant limitations: task oversimplification, data contamination, and flawed e…
Scalable Quantum State Preparation via Large-Language-Model-Driven Discovery
Qing-Hong Cao, Zong-Yue Hou, Ying-Ying Li +5
Efficient quantum state preparation remains a central challenge in first-principles quantum simulations of dynamics in quantum field theories, where the Hilbert space is intrinsica…
Bridging the Dimensional Chasm: Uncover Layer-wise Dimensional Reduction in Transformers through Token Correlation
Zhuo-Yang Song, Zeyu Li, Qing-Hong Cao +2
The geometric evolution of token representations in large language models (LLMs) presents a fundamental paradox: while human language inherently organizes semantic information in l…
Explainable AI-assisted Optimization for Feynman Integral Reduction
Zhuo-Yang Song, Tong-Zhi Yang, Qing-Hong Cao +2
We present a novel approach to optimizing the reduction of Feynman integrals using integration-by-parts identities. By developing a priority function through the FunSearch algorith…