User profiles for Andrew Zhao

Andrew Zhao

- Verified email at mails.tsinghua.edu.cn - Cited by 2205

Andrew Zhao

- Verified email at sandia.gov - Cited by 538

Andrew Z. Zhao

- Verified email at limelightsteel.com - Cited by 146

Expel: Llm agents are experiential learners

A Zhao, D Huang, Q Xu, M Lin, YJ Liu… - Proceedings of the AAAI …, 2024 - ojs.aaai.org
The recent surge in research interest in applying large language models (LLMs) to decision-making
tasks has flourished by leveraging the extensive world knowledge embedded in …

Measurement reduction in variational quantum algorithms

A Zhao, A Tranter, WM Kirby, SF Ung, A Miyake… - Physical Review A, 2020 - APS
Variational quantum algorithms are promising applications of noisy intermediate-scale
quantum (NISQ) computers. These algorithms consist of a number of separate prepare-and-…

Does reinforcement learning really incentivize reasoning capacity in llms beyond the base model?

Z Chen, R Lu, A Zhao, Z Wang, Y Yue… - Advances in …, 2026 - proceedings.neurips.cc
Reinforcement Learning with Verifiable Rewards (RLVR) has recently demonstrated
notable success in enhancing the reasoning performance of large language models (LLMs), …

Beyond the 80/20 rule: High-entropy minority tokens drive effective reinforcement learning for llm reasoning

…, Z Zhang, Y Liu, A Yang, A Zhao… - Advances in …, 2026 - proceedings.neurips.cc
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful
approach to enhancing the reasoning capabilities of Large Language Models (LLMs), yet its …

Absolute zero: Reinforced self-play reasoning with zero data

A Zhao, Y Wu, T Wu, Q Xu, Y Yue… - Advances in …, 2026 - proceedings.neurips.cc
Reinforcement learning with verifiable rewards (RLVR) has shown promise in enhancing
the reasoning capabilities of large language models by learning directly from rule-based …

Avalon's game of thoughts: Battle against deception through recursive contemplation

…, C Liu, Z Zheng, S Qi, S Chen, Q Yang, A Zhao… - arXiv preprint arXiv …, 2023 - arxiv.org
Recent breakthroughs in large language models (LLMs) have brought remarkable success
in the field of LLM-as-Agent. Nevertheless, a prevalent assumption is that the information …

Fermionic partial tomography via classical shadows

A Zhao, NC Rubin, A Miyake - Physical Review Letters, 2021 - APS
We propose a tomographic protocol for estimating any k -body reduced density matrix ( k -RDM)
of an n -mode fermionic state, a ubiquitous step in near-term quantum algorithms for …

[HTML][HTML] Phonon gas model for thermal conductivity of dense, strongly interacting liquids

AZ Zhao, MC Wingert, R Chen, JE Garay - Journal of Applied Physics, 2021 - pubs.aip.org
Developing predictive thermal property models for liquids based on microscopic principles
has been elusive. The difficulty is that liquids have gas-like and solid-like attributes that are at …

Immune and genomic correlates of response to anti-PD-1 immunotherapy in glioblastoma

J Zhao, AX Chen, RD Gartrell, AM Silverman… - Nature medicine, 2019 - nature.com
Immune checkpoint inhibitors have been successful across several tumor types; however,
their efficacy has been uncommon and unpredictable in glioblastomas (GBM), where <10% of …

Prevalence and genetic diversity of candidate vaccine antigens among invasive Neisseria meningitidis isolates in the United States

X Wang, A Cohn, M Comanducci, L Andrew, X Zhao… - Vaccine, 2011 - Elsevier
Neisseria meningitidis (Nm) serogroups B, C and Y are the major causes of meningococcal
diseases in the United States. NmB accounts for ∼1/3 of the disease but no licensed …