Poster · Sydney

Task-Aware KV Cache Compression for LLM Agents via Utility-Driven Step Pruning

Name: Task-Aware KV Cache Compression for LLM Agents via Utility-Driven Step Pruning
Start: 2026-12-08T10:00:00+11:00
End: 2026-12-08T13:00:00+11:00
Location: Hall 1-4, ICC Sydney

When: Tue 8 Dec 2026, 10:00–13:00 AEDT
Where: Hall 1-4, ICC Sydney
Exhibition Centre, Level 1
Session: Sydney Poster Session 1
Authors: Yusen Wu, Yefan Wang, Jia Yee Tan, Guangyuan Dong, Shuang Chen, Jing Yang, Rongfeng Guo, Por L Yee, Yongtai Liu
Organisations: University of Shanghai for Science and Technology, Renmin University of China, National University of Singapore, University of California, Los Angeles, Tencent, Universiti Malaya, Shenzhen University, Hanyang University
QRS classification: Agentic AI, Language models, Efficient and distributed ML systems

Open in schedule Official page