AI RESEARCH
DiscussLLM: Teaching Large Language Models When to Speak
arXiv CS.CL
•
ArXi:2508.18167v2 Announce Type: replace Large Language Models (LLMs) have nstrated remarkable capabilities in understanding and generating human-like text, yet they largely operate as reactive agents, responding only when directly prompted. This passivity creates an "awareness gap," limiting their potential as truly collaborative partners in dynamic human discussions. We