Poster · Sydney

When the Most Disruptive Messages Are Safe to Prune in Aggregate: Functional Analysis of Communication Pruning in Two-Agent LLM Systems

Name: When the Most Disruptive Messages Are Safe to Prune in Aggregate: Functional Analysis of Communication Pruning in Two-Agent LLM Systems
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: Zhen Sun, Xueyang Zhou, Yongchao Chen
Organisations: East China Normal University, Huazhong University of Science and Technology, Tsinghua University
QRS classification: Agentic AI, Language models, Safety, fairness and privacy, Efficient and distributed ML systems

Open in schedule Official page