发表机构
Beijing Jiaotong University; Virginia Polytechnic Institute and State University（北京交通大学; 弗吉尼亚理工学院暨州立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
ReCast是一个智能体插件框架，通过本地转换、重写和数值映射保护固定接口多模态推理中的私有输入，在ChartQA和NMSQA上保留92.43%的远程准确率并减少内容泄漏。
AI 中文摘要
远程多模态模型在图表和语音上提供了强大的数值推理能力，但发送私有输入存在暴露敏感内容的风险。仅文本净化无法直接满足固定媒体接口的要求，而身份匿名化则使底层任务内容暴露在外。我们提出了ReCast，一个智能体插件框架，它在保留任务相关关系和所需输入模态的同时，替换来源特定内容。ReCast在本地将输入转换为共享的文本证据-查询记录，使用蒸馏的4B模型联合重写实体和主题，并通过本地可逆的、角色感知的数值映射替换数值。一个重建智能体从受保护的记录生成并验证所需的媒体。远程求解器返回一个程序，其受保护的操作数在执行前在本地恢复。在4,000个保留的ChartQA和NMSQA示例上，ReCast达到了75.10%的准确率，保留了未受保护远程准确率的92.43%，而基于模型的审计在7.95%的求解器绑定请求中标记了来源内容泄漏。它优于所有评估的本地基线，在现有媒体接口下减少了来源内容暴露的同时，保留了远程推理的优势。
英文摘要
Remote multimodal models offer strong numerical reasoning capabilities over charts and speech, but sending private inputs risks exposing sensitive content. Text-only sanitization cannot directly satisfy fixed media interfaces, while identity anonymization leaves the underlying task content exposed. We introduce ReCast, an agentic plug-in framework that replaces source-specific content while preserving task-relevant relations and the required input modality. ReCast locally converts inputs into a shared textual evidence-query record, jointly rewrites entities and topics with a distilled 4B model, and substitutes values through a locally invertible, role-aware numerical map. A reconstruction agent generates and validates the required media from the protected record. The remote solver returns a program whose protected operands are restored locally before execution. On 4,000 held-out ChartQA and NMSQA examples, ReCast achieves 75.10% accuracy, retaining 92.43% of unprotected remote accuracy, while a model-based audit flags source-content leakage in 7.95% of solver-bound requests. It outperforms all evaluated local baselines, preserving the benefit of remote reasoning while reducing source-content exposure under existing media interfaces.
Comments24 pages, 10 figures
