Authors

Yisen Gao

Publications 2

Preprint Open access

Safe, Persistent, and Evolving Agent Harness for Understanding Partially Observable Worlds

Yisen Gao, Yue Guo, Qing Zong et al. · 2026

Large language model agents can invoke tools fluently, but enterprise workflows demand more than selecting the right tools: actions must strictly comply with organizational policies, tool feedback often conceals hidden side effects under partial observability, and long-horizon tasks require persistent state tracking ac …

Preprint Open access

Towards In-Parameter Memory Augmentation for Large Language Models

Haoyu Huang, Zhongwei Xie, Jiaxin Bai et al. · 2026

Recently Large Language Models (LLMs) and LLM-based agents increasingly need to incorporate knowledge acquired after pretraining, e.g., domain facts, user preferences, documents, and interaction experience. In-context learning (ICL) and ICL-based agent harness remain flexible, but they consume context capacity and incu …

Co-authors