Author

Junhua Zhao

h-index 8 View on Semantic Scholar

We have 3 of 38 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

QART: A Quantum-Classical Hybrid Architecture for Long-Horizon Reasoning -- Exploring a Conditional Path toward Quantum Scaling

Long-horizon reasoning is vulnerable to early errors that compromise later decisions. We present QART, the Quantum-Augmented Reasoning Transformer, a quantum--classical hybrid architecture combining a backbone language model with quantum encoding, CIM-based QUBO optimization, and quantum decoding. Semantic information...

Le-Hao Lin, Yuheng Cheng, Guolong Liu et al. · 0 citations

#artificial intelligence Preprint Aug 2026

RePro: Proof-Verified Benchmark Rewriting for Reliable Evaluation of LLM Mathematical Problem Solving

Proof-Verified Benchmark Rewriting (RePro) is proposed, the first framework to integrate Lean-oriented neural automated theorem provers (ATPs) into benchmark rewriting, which rewrites problems and regenerates answers with correctness ensured by Lean-verified proofs.

Xiyuan Zhou, Zhuo-Qi Li, Xinlei Wang et al. · 0 citations

Review Open access Jul 2026

Exploring Large Language Model‐Based Intelligent Agents: Definitions, Methods, and Prospects

An organizing framework for understanding LLM‐based agents is established, systematically deconstructing both single‐agent and multi‐agent systems into their core components, and the architectural principles and key mechanisms that underpin their intelligence are analyzed.

Yuheng Cheng, Ceyao Zhang, Zhengwen Zhang et al. · WIREs Data Mining and Knowle... · 2 citations