Scholar

Zhengliang Shi

Google Scholar ID: 4UlXbpQAAAAJ

Shandong University

Natural Language ProcessingLLM AgentKnowledge Discovery

Homepage↗Google Scholar↗

Citations & Impact

All-time

Citations

388

H-index

10

i10-index

10

Publications

20

Co-authors

12

list available

Contact

Emailshizhl@mail.sdu.edu.cn CVOpen ↗GitHubOpen ↗

Publications

16 items

Self-Compression of Chain-of-Thought via Multi-Agent Reinforcement Learning

2026

Cited

1

Deep Research: A Systematic Survey

2025

Cited

0

OpenReward: Learning to Reward Long-form Agentic Tasks via Reinforcement Learning

2025

Cited

0

Peeking inside the Black-Box: Reinforcement Learning for Explainable and Accurate Relation Extraction

2025

Cited

0

Social Welfare Function Leaderboard: When LLM Agents Allocate Social Welfare

2025

Cited

0

BatonVoice: An Operationalist Framework for Enhancing Controllable Speech Synthesis with Linguistic Intelligence from LLMs

2025

Cited

0

The Hunger Game Debate: On the Emergence of Over-Competition in Multi-Agent Systems

2025

Cited

0

Bridging the Capability Gap: Joint Alignment Tuning for Harmonizing LLM-based Multi-Agent Systems

2025

Cited

0

Resume (English only)

Academic Achievements

First-authored paper accepted to NeurIPS 2025
One first-authored and two second-authored papers accepted to EMNLP 2025
Two papers accepted to ACL 2025
One paper accepted to EMNLP 2024
Proposed Direct Retrieval-augmented Optimization (DRO), collaborating with researchers from CMU, Baidu, UvA, Leiden University, and UoB
Serving as an Area Chair for ACL Rolling Review (ARR)

Co-authors

12 total

Leiden University

Professor of Computer Science, Shandong University

Senior Director, Head of Search Science at Baidu

Leiden Institute of Advanced Computer Science, Leiden University

Maarten de Rijke

University of Amsterdam & ICAI

Assistant Professor at University of Birmingham