Huanghai Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Huanghai Liu has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Weixing Shen
Tsinghua University, Beijing, China
2 shared publications - Yiran Hu
University of Waterloo, Waterloo, Canada
2 shared publications - Yun Liu
Tsinghua University, Beijing, China
2 shared publications - Ben Kao
University of Hong Kong
1 shared publication - Charles L. A. Clarke
University of Waterloo, Waterloo, Ontario, Canada
1 shared publication - Chong Wang
Tsinghua University, Beijing, China
1 shared publication
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 9036-9040
LexSkill: A Systematic Chinese Legal Skill Framework with High-Quality Annotations and an Execution Harness
Agents in knowledge-intensive domains require not only knowledge retrieval, but also the skills to effectively use retrieved knowledge. Since domain knowledge is often highly complex, agents must possess strong reasoning capabilities in order to perform tasks effectively. In the legal domain, different legal systems exhibit substantial differences, and the reasoning logic for applying legal knowledge varies significantly across systems. Meanwhile, existing skill collections lack a systematic skill framework grounded in domain knowledge, limiting their scalability and extensibility. To address these challenges, we present LexSkill, a reasoning-oriented legal skill library for the Chinese legal system. Within this framework, legal experts construct 36 atomic skills, further organized into 180 sub-atomic skills and 2 compound skills. Since legal problem solving also requires grounded access to legal resources and coordinated reasoning across multiple steps, we further introduce Chinese-Law-Harness, which augments the skill library with MCP modules built over a case repository and a statutory repository, and incorporates a multi-agent system for skill orchestration and execution. Evaluations on existing legal AI benchmarks show that leveraging the skill library through the proposed harness significantly outperforms direct problem solving without structured support, verifying the effectiveness of our skills and harness.
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 9036-9040
Open AccessLexSkill: A Systematic Chinese Legal Skill Framework with High-Quality Annotations and an Execution Harness
Agents in knowledge-intensive domains require not only knowledge retrieval, but also the skills to effectively use retrieved knowledge. Since domain knowledge is often highly complex, agents must possess strong reasoning capabilities in order to perform tasks effectively. In the legal domain, different legal systems exhibit substantial differences, and the reasoning logic for applying legal knowledge varies significantly across systems. Meanwhile, existing skill collections lack a systematic skill framework grounded in domain knowledge, limiting their scalability and extensibility. To address these challenges, we present LexSkill, a reasoning-oriented legal skill library for the Chinese legal system. Within this framework, legal experts construct 36 atomic skills, further organized into 180 sub-atomic skills and 2 compound skills. Since legal problem solving also requires grounded access to legal resources and coordinated reasoning across multiple steps, we further introduce Chinese-Law-Harness, which augments the skill library with MCP modules built over a case repository and a statutory repository, and incorporates a multi-agent system for skill orchestration and execution. Evaluations on existing legal AI benchmarks show that leveraging the skill library through the proposed harness significantly outperforms direct problem solving without structured support, verifying the effectiveness of our skills and harness.
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 5411-5416
HCLeK: Hierarchical Compression of Legal Knowledge for Retrieval-Augmented Generation
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 5411-5416
Open AccessHCLeK: Hierarchical Compression of Legal Knowledge for Retrieval-Augmented Generation