跳到正文
arXiv cs.MA· Abbas Raza Ali, Muhammad Ajmal Siddiqui, Moona Zahid·· 23 小时前AI 评分34

受监管企业如何评估 Agentic AI 平台:一个九维能力框架与“先门控后打分”协议

A Capability Framework for Evaluating Agentic AI Platforms in Regulated Enterprises

AI 导读

一家全球银行创新实验室对 10 个 Agentic AI 平台开展“bakeoff”评测,覆盖开源框架、商业产品与超大规模云生态,由跨职能专家组在对手方信用风险、RAG 和流程自动化三类金融工作负载上按九个能力维度打分,结果稳定分为三个梯队。

正文 · 原文

View PDF HTML (experimental)

Abstract:Agentic AI platforms-systems in which LLM agents plan, invoke tools, retain memory and coordinate to change the state of enterprise systems-are being procured faster than they can be measured. Public agent benchmarks score models in fixed harnesses; enterprises buy integrated platforms whose orchestration, memory, governance and tooling layers dominate outcomes, and they buy them largely on the strength of vendor demonstrations. We report an industrial evaluation programme ("bakeoff") run by the innovation laboratory of a global bank in which ten platforms-spanning open-source frameworks, proprietary products and hyperscaler ecosystems-were assessed by a cross-functional panel on nine capability dimensions across three financial-services workloads: counterparty credit risk, retrieval-augmented generation and process automation. Scores separate the field into three tiers that are stable under alternative weightings, and surface workload-specific strengths that aggregates hide. A secondary analysis, however, finds Cronbach's alpha = 0.98 across nominally distinct dimensions and rank correlations >= 0.93 with the total for eight of nine: a halo effect indicating that demonstration-based scoring measures presentation as much as capability. From these lessons we propose a gate-then-score evaluation protocol with four layers (capability, execution reliability, governance gates, business value), trace-level reliability metrics estimated over repeated runs, an autonomy-readiness scale and a reproducibility protocol. We state precisely what the present evidence supports, and what a controlled harness must add to turn enterprise platform evaluation from structured judgement into measurement.
Subjects: Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA); Machine Learning (stat.ML)
Cite as: arXiv:2611.24039 [cs.AI]
  (or arXiv:2611.24039v1 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2611.24039

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Abbas Raza Ali [view email]
[v1] Wed, 18 Nov 2026 08:28:02 UTC (221 KB)

来源:arXiv cs.MA · arxiv.org