PhoenixNest-Video：基于证据的多模态智能体框架用于自动视频面试评估
PhoenixNest-Video: Evidence-Grounded Multimodal Agent Framework for Automated Video Interview Assessment
浏览论文内容
中文总结 AI 辅助
针对纯人工视频面试评估成本高、一致性差及现有AI方法分数不透明的问题，提出PhoenixNest-Video多模态智能体框架，在VInterview-2025数据集上获91.50%等级准确率，优于更大的专有模型，且分数可追溯。
中文摘要 AI 辅助
面试评估需要基于行为证据的各维度判断，但激增的申请者规模使纯人工评估成本高昂且一致性差，现有AI方法却生成无追溯依据的不透明分数。我们提出PhoenixNest-Video，一种基于证据的多模态智能体框架用于自动视频面试评估。它构建语义视频图作为结构化工作记忆，进行基于评分标准的检索，同时在视觉、音频和文本流间执行跨模态验证，生成锚定候选人材料的各维度分数。通过基于评分标准的强化学习训练的评分器，兼具评分标准对齐和分数级区分的双重奖励，内化了多级评分标准的判别结构。PhoenixNest-Video在VInterview-2025数据集上达到91.50%的等级准确率，显著优于规模大得多的专有模型。因此，紧凑的基于评分标准的智能体对候选人的评分与专家小组的一致性，优于直接提示大得多的模型，且为人类审查公开了每个分数背后的证据。
英文摘要
Interview assessment requires per-criterion judgments grounded in behavioral evidence, yet surging applicant volumes have made human-only evaluation costly and inconsistent, while existing AI approaches yield opaque scores without traceable rationale. We introduce PhoenixNest-Video, an evidence-grounded multimodal agent framework for automated video interview assessment. It builds a semantic video graph as structured working memory, performs rubric-conditioned retrieval with cross-modal verification across visual, audio, and textual streams, and produces per-criterion scores anchored to the candidate's materials. A Scorer trained via Rubrics-based Reinforcement Learning with dual rewards for rubric alignment and score-level differentiation internalizes the discriminative structure of multi-level rubrics. PhoenixNest-Video attains 91.50\% grade-level accuracy on VInterview-2025, outperforming substantially larger proprietary models. A compact, rubric-grounded agent therefore scores candidates in closer agreement with an expert panel than direct prompting of much larger models, and exposes the evidence behind each score for human review.
发表机构
- The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
机构由 AI 辅助整理，请以论文原文为准。
