Author

Shichun Liu

Observed name: Liu, Shichun

Institutions: Shanghai Jiao Tong University, Fudan University, Honor Device (China), University of Hong Kong

Observed institutions: Shanghai Jiao Tong University, Fudan University, Honor Device (China), University of Hong Kong

OpenAlex ID: A5125712096

Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses

2026 · Lin, Jiahang, Liu, Shichun, et al. · arXiv (Cornell University) · 1

Agents in the Large: Perception-Centered Architecture for Persistent Agents

2026 · Dou, Shihan, Jia, Haoxiang, et al. · arXiv (Cornell University)

IACM-RL: Intent-Aware Context Management and Reinforcement Learning for Complex Tool Invocation under Dynamic Intent Fluctuations

2026 · Zhu, Dingwei, Li, Jiahan, et al. · arXiv (Cornell University)

Entropy Polarity in Reinforcement Fine-Tuning: Direction, Asymmetry, and Control

2026 · Zhang, Jiazheng, Fu, Ziche, et al. · arXiv (Cornell University)

CL-bench Life: Can Language Models Learn from Real-Life Context?

2026 · Dou, Shihan, Shen, Yujiong, et al. · arXiv (Cornell University)

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training

2026 · Pan, Chengjun, Liu, Shichun, et al. · arXiv (Cornell University)

MM-Doc-R1: Training Agents for Long Document Visual Question Answering through Multi-turn Reinforcement Learning

2026 · Lin, Jiahang, Hu, Kai, et al. · arXiv (Cornell University)

MetaAct-RL: Training Language Models for Reasoning Through Meta-Action-Based Reinforcement Learning

2026 · Association for Artificial Intelligence 2026, Ding, Yiwen, et al. · Underline Science Inc.

Works count: 8

Citation count: 1

H-index: 1

I10-index: