Agora | Research Hub

Citations & Impact

All-time

Citations

1,757

H-index

24

i10-index

37

Publications

20

Co-authors

34

list available

Contact

Emaildaizhongxiang@cuhk.edu.cn TwitterOpen ↗GitHubOpen ↗

Publications

22 items

MASPOB: Bandit-Based Prompt Optimization for Multi-Agent Systems with Graph Neural Networks

2026

Cited

0

Words & Weights: Streamlining Multi-Turn Interactions via Co-Adaptation

2026

Cited

0

CASTLE: A Comprehensive Benchmark for Evaluating Student-Tailored Personalized Safety in Large Language Models

2026

Cited

0

Workflow-R1: Group Sub-sequence Policy Optimization for Multi-turn Workflow Construction

2026

Cited

0

Real-Time Aligned Reward Model beyond Semantics

2026

Cited

2

Dual-Robust Cross-Domain Offline Reinforcement Learning Against Dynamics Shifts

2025

Cited

0

UCO: A Multi-Turn Interactive Reinforcement Learning Method for Adaptive Teaching with Large Language Models

2025

Cited

0

EduAgentQG: A Multi-Agent Workflow Framework for Personalized Question Generation

2025

Cited

0

Resume (English only)

Academic Achievements

September 2025: Two papers accepted to NeurIPS 2025.
August 2025: Invited as Area Chair for ICLR 2026.
May 2025: Paper on LLM source attribution & watermarking accepted to ACL 2025 Findings.
May 2025: Two papers accepted to ICML 2025.
April 2025: Invited as Area Chair for NeurIPS 2025.
April 2025: Paper on Bayesian optimization accepted to Journal of Machine Learning Research (JMLR).
Multiple preprints and workshop papers published at ICLR, ICML, etc., covering prompt optimization, federated learning, active preference optimization, and integration of MAB with LLMs.

Co-authors

34 total