Guardado en:
Detalles Bibliográficos
Autores principales: Lin, Lanbo, Liu, Jiayao, Yang, Tianyuan, Cai, Li, Xu, Yuanwu, Wei, Lei, Xie, Sicong, Zhang, Guannan
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2602.06486
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918325812985856
author Lin, Lanbo
Liu, Jiayao
Yang, Tianyuan
Cai, Li
Xu, Yuanwu
Wei, Lei
Xie, Sicong
Zhang, Guannan
author_facet Lin, Lanbo
Liu, Jiayao
Yang, Tianyuan
Cai, Li
Xu, Yuanwu
Wei, Lei
Xie, Sicong
Zhang, Guannan
contents Evaluating agentic AI on open-ended professional tasks faces a fundamental dilemma between rigor and flexibility. Static rubrics provide rigorous, reproducible assessment but fail to accommodate diverse valid response strategies, while LLM-as-a-judge approaches adapt to individual responses yet suffer from instability and bias. Human experts address this dilemma by combining domain-grounded principles with dynamic, claim-level assessment. Inspired by this process, we propose JADE, a two-layer evaluation framework. Layer 1 encodes expert knowledge as a predefined set of evaluation skills, providing stable evaluation criteria. Layer 2 performs report-specific, claim-level evaluation to flexibly assess diverse reasoning strategies, with evidence-dependency gating to invalidate conclusions built on refuted claims. Experiments on BizBench show that JADE improves evaluation stability and reveals critical agent failure modes missed by holistic LLM-based evaluators. We further demonstrate strong alignment with expert-authored rubrics and effective transfer to a medical-domain benchmark, validating JADE across professional domains. Our code is publicly available at https://github.com/smiling-world/JADE.
format Preprint
id arxiv_https___arxiv_org_abs_2602_06486
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle JADE: Expert-Grounded Dynamic Evaluation for Open-Ended Professional Tasks
Lin, Lanbo
Liu, Jiayao
Yang, Tianyuan
Cai, Li
Xu, Yuanwu
Wei, Lei
Xie, Sicong
Zhang, Guannan
Artificial Intelligence
Evaluating agentic AI on open-ended professional tasks faces a fundamental dilemma between rigor and flexibility. Static rubrics provide rigorous, reproducible assessment but fail to accommodate diverse valid response strategies, while LLM-as-a-judge approaches adapt to individual responses yet suffer from instability and bias. Human experts address this dilemma by combining domain-grounded principles with dynamic, claim-level assessment. Inspired by this process, we propose JADE, a two-layer evaluation framework. Layer 1 encodes expert knowledge as a predefined set of evaluation skills, providing stable evaluation criteria. Layer 2 performs report-specific, claim-level evaluation to flexibly assess diverse reasoning strategies, with evidence-dependency gating to invalidate conclusions built on refuted claims. Experiments on BizBench show that JADE improves evaluation stability and reveals critical agent failure modes missed by holistic LLM-based evaluators. We further demonstrate strong alignment with expert-authored rubrics and effective transfer to a medical-domain benchmark, validating JADE across professional domains. Our code is publicly available at https://github.com/smiling-world/JADE.
title JADE: Expert-Grounded Dynamic Evaluation for Open-Ended Professional Tasks
topic Artificial Intelligence
url https://arxiv.org/abs/2602.06486