6 papers
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…
Collins-type fragmentation energy correlator in semi-inclusive deep inelastic lepton-hadron scattering
Qing-Hong Cao, Zhite Yu, C. -P. Yuan +2
We initiate a systematic study of fragmentation energy correlators (FECs), which generalize traditional fragmentation functions and encode non-perturbative information about transv…
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…
Dihadron Angular Correlations in the Collision
Wan-Li Ju, Zhe-Yan Shu, Tong-Zhi Yang +2
The precision of fixed-order calculations on the dihadron production in electron-positron annihilation is paramount for probing QCD factorization and constraining non-perturbative…
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…