Fine-grained action recognition in egocentric video is challenging for Vision-Language Models (VLMs): actions often differ only in small visual cues, and a single model tends to be biased toward a subset of these cues. We propose Divide, Deliberate, Decide, a fully-local, zero-shot multi-agent framework in which (i) a VLM orchestrator chunks the video and proposes a top-k candidate label list per segment, (ii) an ensemble of heterogeneous VLM specialists, drawn from different open model families, engages in a structured deliberation that includes a peer-consultation round of questions, and (iii) agent rankings are aggregated with a Borda count and the orchestrator re-ranks its own prediction in light of the specialists' evidence. The entire pipeline runs locally with no fine-tuning. Experiments show that our method positively improves zero-shot action recognition performance over the baseline, highlighting the influence of a heterogeneous deliberation step, showing that the gain stems from decorrelated model priors rather than from additional compute.

翻译：自我中心视频中的细粒度动作识别对视觉-语言模型（VLM）构成挑战：不同动作往往仅在小尺度视觉线索上存在差异，而单一模型容易偏向于这些线索中的某个子集。我们提出"分而析之，审而议之，决而断之"框架——一种完全本地化、零样本的多智能体框架，其中（i）VLM编排器将视频分段并为每段提出前k个候选标签列表；（ii）由来自不同开源模型家族的异构VLM专家组成的集成体，通过包含同伴咨询轮次的结构化审议进行协作；（iii）利用波达计数法聚合智能体排名，编排器根据专家提供的证据重新调整自身预测。整个流程在本地运行，无需微调。实验表明，本方法在零样本动作识别性能上较基准方法有显著提升，突出显示了异构审议步骤的关键作用——性能提升源于解耦的模型先验知识，而非额外计算量。