Beyond Benchmark Islands: Toward Representative Trustworthiness Evaluation for Agentic AI

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Qi, Jinhu, Li, Yifan, Zhao, Minghao, Zhang, Wentao, Zhang, Zijian, Li, Yaoman, King, Irwin
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914586668564480
author Qi, Jinhu
Li, Yifan
Zhao, Minghao
Zhang, Wentao
Zhang, Zijian
Li, Yaoman
King, Irwin
author_facet Qi, Jinhu
Li, Yifan
Zhao, Minghao
Zhang, Wentao
Zhang, Zijian
Li, Yaoman
King, Irwin
contents Agentic AI systems increasingly act through tool-augmented, multi-step workflows whose failures (unsafe tool use, unauthorised actions, social harm) carry deployment-level consequences. Evaluation practice remains fragmented across isolated benchmark slices, and "trustworthiness" is frequently invoked but rarely defined operationally. We argue the central limitation is twofold: (i) the absence of a measurable specification of what agent trustworthiness means, and (ii) the lack of a principled notion of representativeness allowing assessment over a socio-technical scenario distribution rather than disconnected benchmark instances. We address (i) by defining agentic trustworthiness as a five-property profile (Reliability, Robustness, Safety, Social-Ethical Alignment, Operational Integrity) grounded in current AI risk frameworks, and (ii) with the Holographic Agent Assessment Framework (HAAF), which measures this profile over a scenario manifold through static policy analysis, sandbox simulation, social-ethical alignment assessment, and distribution-aware sampling, connected through an iterative Trustworthy Optimization Factory that converts red-team diagnoses into blue-team interventions. Our contributions are: (1) an operational five-property definition of agentic trustworthiness; (2) a distribution-aware scenario-sampling framework that surfaces property-level trade-offs invisible to scalar leaderboards; and (3) a cross-family transfer experiment in which interventions designed from a single focal model generalise -- without per-model or per-scenario tuning -- to 13 systems from seven model families (Llama, Mistral, Kimi, GLM, Qwen, GPT, DeepSeek) on a 100-scenario suite, where all 13 systems improve and two reach a perfect risk-weighted profile, establishing HAAF's Factory as a model-agnostic deployment-readiness pipeline. Code: https://github.com/TonyQJH/haaf-pilot
format Preprint
id arxiv_https___arxiv_org_abs_2603_14987
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Beyond Benchmark Islands: Toward Representative Trustworthiness Evaluation for Agentic AI
Qi, Jinhu
Li, Yifan
Zhao, Minghao
Zhang, Wentao
Zhang, Zijian
Li, Yaoman
King, Irwin
Computation and Language
Databases
I.2.7; I.2.11; K.6.5
Agentic AI systems increasingly act through tool-augmented, multi-step workflows whose failures (unsafe tool use, unauthorised actions, social harm) carry deployment-level consequences. Evaluation practice remains fragmented across isolated benchmark slices, and "trustworthiness" is frequently invoked but rarely defined operationally. We argue the central limitation is twofold: (i) the absence of a measurable specification of what agent trustworthiness means, and (ii) the lack of a principled notion of representativeness allowing assessment over a socio-technical scenario distribution rather than disconnected benchmark instances. We address (i) by defining agentic trustworthiness as a five-property profile (Reliability, Robustness, Safety, Social-Ethical Alignment, Operational Integrity) grounded in current AI risk frameworks, and (ii) with the Holographic Agent Assessment Framework (HAAF), which measures this profile over a scenario manifold through static policy analysis, sandbox simulation, social-ethical alignment assessment, and distribution-aware sampling, connected through an iterative Trustworthy Optimization Factory that converts red-team diagnoses into blue-team interventions. Our contributions are: (1) an operational five-property definition of agentic trustworthiness; (2) a distribution-aware scenario-sampling framework that surfaces property-level trade-offs invisible to scalar leaderboards; and (3) a cross-family transfer experiment in which interventions designed from a single focal model generalise -- without per-model or per-scenario tuning -- to 13 systems from seven model families (Llama, Mistral, Kimi, GLM, Qwen, GPT, DeepSeek) on a 100-scenario suite, where all 13 systems improve and two reach a perfect risk-weighted profile, establishing HAAF's Factory as a model-agnostic deployment-readiness pipeline. Code: https://github.com/TonyQJH/haaf-pilot
title Beyond Benchmark Islands: Toward Representative Trustworthiness Evaluation for Agentic AI
topic Computation and Language
Databases
I.2.7; I.2.11; K.6.5
url https://arxiv.org/abs/2603.14987