FusionAgent：一种具有动态模型选择的多模态代理用于人体识别
FusionAgent: A Multimodal Agent with Dynamic Model Selection for Human Recognition
AI总结：
FusionAgent通过动态模型选择提升人体识别鲁棒性，利用多模态大语言模型进行样本特定的模型选择，结合ACT分数融合方法，实验表明其在效率和性能上优于现有方法。
摘要：
模型融合是无约束场景中稳健识别的关键策略，不同模型提供互补优势。在全身人体识别中，生物特征如面部、步态和身体形状在样本间变化较大，通常通过分数融合集成。然而，现有分数融合策略通常是静态的，对每个测试样本都调用所有模型，无论样本质量或模态可靠性。为克服这些限制，我们提出了FusionAgent，一种新的代理框架，利用多模态大语言模型（MLLM）进行动态、样本特定的模型选择。每个专家模型被视为一种工具，通过基于度量的奖励的强化微调（RFT），代理学习适应性地确定每个测试输入的最佳模型组合。为了解决模型分数不一致和嵌入异质性问题，我们引入了基于锚点的置信度Top-k（ACT）分数融合，该方法以最自信的模型为锚点，以置信度意识的方式整合互补预测。在多个全身生物特征基准上的广泛实验表明，FusionAgent显著优于现有方法，同时通过较少的模型调用实现了更高的效率，凸显了动态、可解释和稳健的模型融合在现实识别系统中的关键作用。项目页面：https://fusionagent.github.io/FusionAgent.
英文摘要：
Model fusion is a key strategy for robust recognition in unconstrained scenarios, as different models provide complementary strengths. This is especially important for whole-body human recognition, where biometric cues such as face, gait, and body shape vary across samples and are typically integrated via score-fusion. However, existing score-fusion strategies are usually static, invoking all models for every test sample regardless of sample quality or modality reliability. To overcome these limitations, we propose \textbf{FusionAgent}, a novel agentic framework that leverages a Multimodal Large Language Model (MLLM) to perform dynamic, sample-specific model selection. Each expert model is treated as a tool, and through Reinforcement Fine-Tuning (RFT) with a metric-based reward, the agent learns to adaptively determine the optimal model combination for each test input. To address the model score misalignment and embedding heterogeneity, we introduce Anchor-based Confidence Top-k (ACT) score-fusion, which anchors on the most confident model and integrates complementary predictions in a confidence-aware manner. Extensive experiments on multiple whole-body biometric benchmarks demonstrate that FusionAgent significantly outperforms SoTA methods while achieving higher efficiency through fewer model invocations, underscoring the critical role of dynamic, explainable, and robust model fusion in real-world recognition systems. Project page: \href{https://fusionagent.github.io/}{FusionAgent}.
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。
