AINeutralarXiv – CS AI · 18h ago6/10
🧠
Aligned but Not Partner-Specific: Distinguishing How Multimodal LLM Agents Succeed in Reference Games Without Human-Like Conventions
Researchers analyzed how multimodal large language models (MLLMs) perform in repeated reference games compared to humans, finding that while agents align on vocabulary labels, they lack true partner-specific conventions. Using a novel constrained pseudo-dyad baseline, they discovered agents succeed through verbose descriptions rather than the compressed, history-dependent expressions humans develop through entrainment.