Search papers, labs, and topics across Lattice.
PhoenixNest-Video is an evidence-grounded multimodal agent framework designed for automated video interview assessment, addressing the challenges of high applicant volumes and the limitations of existing AI evaluation methods. By constructing a semantic video graph and employing rubric-conditioned retrieval across visual, audio, and textual data, it generates per-criterion scores that are closely aligned with expert evaluations. The framework achieves a remarkable 91.50% grade-level accuracy on the VInterview-2025 dataset, outperforming larger proprietary models while providing transparent evidence for each assessment score.
Automated video interview assessments can now achieve expert-level accuracy with a compact model that reveals the evidence behind each score.
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.
