PhoenixNest-Video: Evidence-Grounded Multimodal Agent Framework for Automated Video Interview Assessment

2026-09-02

AI Summary

为解决面试评估成本高、不一致问题，提出基于证据的多模态代理框架PhoenixNest-Video，通过构建语义视频图和评分强化学习方法实现可追溯的自动视频面试评估。

Abstract

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.

Problem

• Interview assessment
• behavioral evidence
• opaque scores
• automated video interview
• traceable rationale

Innovation

• evidence-grounded multimodal agent
• semantic video graph
• rubric-conditioned retrieval
• cross-modal verification
• rubrics-based reinforcement learning