Linyuan Lü

Optimizing communication topology in LLM–based multi-agent system is critical for enabling collective intelligence. Existing methods mainly rely on spatio-temporal interaction paradigms, where the sequential execution of multi-round dialogues incurs high latency and computation. Motivated by the...

Evaluating semantic drift is essential for understanding dynamical discourse evolution and opinion formation in online discussions. However, sparse and uneven distributions of event-specific keywords prevent traditional models from capturing post-level semantic drift. Thus, to address this issue,...