HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry

Tingyang Chen*, Shuo Lu*, Kang Zhao*, Weicheng Meng, Hanlin Teng, Tianhao Li, Chao Li, Xule Liu, Jian Liang, Zhizhong Zhang, Yuan Xie, Heng Qu, Kun Shao, Jian Luan

Arxiv , GitHub

R^3: Replay, Reflection, and Ranking Rewards for LLM Reinforcement Learning

Zhizheng Jiang*, Kang Zhao*, Weikai Xu, Xinkui Lin, Wei Liu, Jian Luan, Shuo Shang, Peng Han

Arxiv

Unimc: A unified framework for long-term memory conversation via relevance representation learning

Kang Zhao, Wei Liu, Jian Luan, Minglei Gao, Li Qian, Hanlin Teng, Bin Wang

Arxiv

GAR-Net: A graph attention reasoning network for conversation understanding[J]

Hua Xu*, Ziqi Yuan*, Kang Zhao*, Yunfeng Xu, Jiyun Zou, Kai Gao

GitHub

Consistent representation learning for continual relation extraction[C]

Kang Zhao, Hua Xu, Jiangong Yang, Kai Gao

Arxiv , GitHub

Representation iterative fusion based on heterogeneous graph neural network for joint entity and relation extraction[J]

Kang Zhao, Hua Xu, Yue Cheng, Xiaoteng Li, Kai Gao

GitHub , PDF

Subllm: A novel efficient architecture with token sequence subsampling for llm[C]

Quandong Wang, Yuxuan Yuan, Xiaoyu Yang, Ruike Zhang, Kang Zhao, Wei Liu, Jian Luan, Daniel Povey, Bin Wang

Arxiv , GitHub

TEXTOIR: An integrated and visualized platform for text open intent recognition[C]

Hanlei Zhang, Xiaoteng Li, Hua Xu, Panpan Zhang, Kang Zhao, Kai Gao

Arxiv , GitHub