MODF-SIR: A Multi-agent Omni-modal Distilled Framework for Social Intelligence Reasoning

Computer Science > Artificial Intelligence [Submitted on 10 Jun 2026] MODF-SIR: A Multi-agent Omni-modal Distilled Framework for Social Intelligence Reasoning Shang Ma, Jisheng Dang, Wencan Zhang, Yifan Zhang, Bimei Wang, Hong Peng, Bin Hu, Qi Tian, Tat-Seng Chua 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 this https URL, demo is available at this https URL, LoRA is available at this https URL and the dataset for training router is available at this https URL. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2606.12018 [cs.AI]   (or arXiv:2606.12018v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2606.12018 Focus to learn more Submission history From: Shang Ma [view email] [v1] Wed, 10 Jun 2026 12:44:02 UTC (778 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-06 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)