Publications

Argumentation graph flowing into a claim adjudication verdict
Conference Paper

Jin Liu, Yunpeng Liu, Keyi Wang, Jie Shi, Xiao Xu, Wenkang Huang, Xingzhong Xu, Xin Liang, Yanghua Xiao

InsLogicBench: An Argumentation Logic Grounded Benchmark for Complex Insurance Claims Adjudication

ACL 2026 Main CCF-A

San Diego, CA · July 5–7, 2026

The traditional square of opposition diagram from term logic
Conference Paper

Sihang Jiang, Zhiyu Lu, Keyi Wang, Jiaqing Liang, Yanghua Xiao, Xiaojun Meng, Jiansheng Wei

Immediate Inference: The Missing Foundation in Large Language Model Logical Reasoning

ACL 2026 Main Oral CCF-A

San Diego, CA · July 5–7, 2026

An iceberg of latent cognitive capability, its hidden depth quantified on a measuring gauge
Conference Paper

Cui Danxin, Sihang Jiang, Keyi Wang, Zhiyi Duan, Yanghua Xiao, Bi Yude, Jiaqing Liang, Minggui He, Shimin Tao, Yilun Liu

Measuring the Unmeasurable: Unveiling Latent Cognitive Capabilities of LLMs

AAAI 2026 Poster CCF-A

Singapore · January 24, 2026

Paper

Preprints

A verbose context compressed into a dense, token-efficient core by a self-evolving agent
Preprint

Jiaqing Liang, Jinyi Han, Weijia Li, Xinyi Wang, Zhoujia Zhang, Zishang Jiang, Ying Liao, Tingyun Li, Ying Huang, Hao Shen, Hanyu Wu, Fang Guo, Keyi Wang, Zhonghua Hong, Zhiyu Lu, Lipeng Ma, Sihang Jiang, Yanghua Xiao

GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization

arXiv:2604.17091

April 2026

arXiv PDF
A rising capability trajectory of a self-evolving agent, evaluated continuously across tasks beyond single episodes
Preprint

Sihang Jiang, Lipeng Ma, Zhonghua Hong, Keyi Wang, Zhiyu Lu, Tengfei Wang, Shisong Chen, Jinghao Zhang, Tianjun Pan, Weijia Li, Jiaqing Liang, Yanghua Xiao

SEA-Eval: A Benchmark for Evaluating Self-Evolving Agents Beyond Episodic Assessment

arXiv:2604.08988

April 2026

arXiv PDF