社交智能推理是 AI 理解人类互动的关键，MODF-SIR 用轻量模型和蒸馏技术解决了长尾事件被忽略的痛点，做多模态社交分析或人机交互的团队可以直接用开源代码复现。
研究者提出了一种名为 MODF-SIR 的多智能体协作框架，基于轻量级多模态大语言模型，专门用于社交智能推理。该框架通过知识蒸馏增强训练和推理阶段，能够精确定位多模态社交数据，并提取长尾事件以格式化文本呈现，避免关键信息被噪声淹没。它集成了测试时自适应（TTA）、思维链提示和自反思机制，并利用 LoRA 微调基础模型。在多个基准测试中，仅用约 30% 的训练数据就达到了最先进的结果。代码、演示和模型均已开源。
MODF-SIR: A Multi-agent Omni-modal Distilled Framework for Social Intelligence Reasoning
We propose a multi-agent collaborative framework built upon a lightweight Multimodal Large Language Model (MLLM), specifically designed for social intelligence reasoning. A key feature of our approach is that both the training and inference phases are augmented via knowledge distillation. Within this architecture, multi-modal data pertinent to social intelligence is precisely localized. Furthermore, relevant long-tail events are identified, extracted, and rendered as formatted, explicit text. This formatting strategy prevents critical long-tail information from being overshadowed by head events and environmental noise during the tokenization process. Specifically, we integrate Test-Time Adaptation (TTA) across the entire reasoning pipeline, encompassing the extraction and representation of long-tail events, Chain-of-Thought (CoT) prompting, and self-reflection. This TTA mechanism is also distillation-enhanced, utilizing Low-Rank Adaptation (LoRA) to fine-tune the foundation model exclusively for instance-level reasoning. Extensive evaluations against various open-source and proprietary AI models across multiple benchmarks demonstrate the effectiveness of the proposed framework. With around 30% of training data from IntentTrain, we achieve state-of-the-art results. Codes are available at https://github.com/eeee-sys/MODF-SIR, demo is available at https://huggingface.co/spaces/Harry-1234/MODF-SIR, LoRA is available at https://huggingface.co/Harry-1234/MODF-SIR and the dataset for training router is available at https://huggingface.co/datasets/Harry-1234/IntentRouterTrain.