对齐但非伙伴特定：区分多模态LLM智能体在参考游戏中如何成功而无需类人惯例
Aligned but Not Partner-Specific: How Multimodal LLM Agents Succeed in Reference Games Without Forming Conceptual Pacts
AI总结：
通过约束伪对基线方法，区分多模态LLM智能体在参考游戏中的标签对齐是源于伙伴特定交互还是共享任务词汇，发现智能体通过冗长描述而非压缩表达实现协调。
摘要：
重复参考游戏测试对话者是否用基于共享交互历史的更短、伙伴特定的惯例替换其初始长描述。先前工作表明，多模态LLM在轮次中未能变得更高效，尽管它们在使用的标签上对齐。我们如何确定这种对齐反映了伙伴特定的基础而非共享任务词汇？我们通过将有能力的多模态智能体对与来自KTH Tangrams语料库的人类对进行比较来解决这个问题。我们的新颖方法论贡献是一个受约束的伪对基线，它匹配原始指称任务结构，但打破了伙伴历史。该基线使我们能够测试观察到的标签对齐是否依赖于与特定伙伴的交互。在三个分析层面（任务能力、描述策略、对齐动态）上，我们发现了明显差异。人类通过适应减少努力，压缩描述并增加与伙伴的标签对齐。智能体反而保持固定的努力水平，从第一轮开始产生冗长的描述，标签重叠接近上限，在真实对和伪对之间统计上无法区分。因此，多模态LLM在没有惯例的情况下实现了协调，通过冗长描述而非形成人类对话特征的紧凑、依赖历史的指称表达来取得成功。
英文摘要：
Repeated reference games test whether interlocutors replace their initially long descriptions with shorter, partner-specific expressions grounded in shared interaction history; that is, with conceptual pacts. Prior work shows that multimodal LLMs fail to become more efficient across rounds, although they align on the labels they use. However, how can we determine whether this alignment reflects partner-specific grounding rather than a shared task vocabulary? We address this by comparing competent multimodal agent dyads with human dyads from the KTH Tangrams corpus. Our novel methodological contribution is a pragmatically constrained pseudo-dyad baseline: rounds from two different real dyads describing the same target at comparable trajectory positions are paired, preserving referential task structure while removing shared partner history. This enables us to test whether the observed label alignment depends on interaction with a specific partner. Across three measures (task competence, description strategy, alignment dynamics), we find clear differences. Humans reduce effort through entrainment, compressing descriptions and increasing label alignment with partners. Agents instead maintain fixed effort levels, producing verbose descriptions from round one, with near-ceiling label overlap that is statistically indistinguishable between real and pseudo dyads. MLLMs thus achieve coordination without conceptual pacts, succeeding by verbose description rather than by forming the compact, history-dependent referring expressions characteristic of human dialogue.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
