cs.AINov 14, 2026

Auditable Authorization for LLM Agents: Empirical Evidence Across Model, Harness, and Workflow Layers

Authors: Bangjie Deng, Xiaoxuan Lu, Wenjun Chen, Chengge Wen, Yulin Wang, Jiayue Meng, Yao Yu, Liying Liang, 

Organizations: University of Pennsylvania · Independent Researcher · Columbia University · Northeastern University · 

Abstract

Human approval provides effective control only if rejected work stops and authorized work completes. We formalize refusal safety and bounded authorization completeness, and audit three execution boundaries: the model selects a call, the harness schedules and resumes it, and the workflow routes the decision to a protected effect. Paired decisions, exact traces, and native business-state witnesses support experiments with three models, five prompt arms, four runtime approval designs, two additional framework replays, and 100 public workflow sources. The paired model panel leaves seven of 300 approvals unfinished despite zero denied effects; parallel confirmation loses an approved branch in three tasks per model, restoration omits 336/672 CrewAI approvals, and four of 59 comparable n8n workflows execute after Reject. Comparing intent, generated calls, dispatch, and native effects identifies the first observable divergence and its repair target. This yields a practical audit contract that makes both refusal safety and authorization completeness independently verifiable, converting human approval from a procedural formality into an enforceable control boundary between intent and real-world effect.

Figures & tables

Explore similar work

CardsList
  1. AuthGateBench: Benchmarking LLMs as Authorization Gate

    Oct 12, 2026Zhixiong Zhuang, Jin Jia, Zhiwei Shang +1Tool Access Control for LLM AgentsAI Agent Safety Benchmarks

  2. Act on Your Behalf, Beyond Your Authorization: Benchmarking LLM Agent Authorization Alignment

    Oct 20, 2026Zhiping Zhang, Franklin Mingzhe Li, Zihao Huang +1LLM Agent EvaluationAI Agent Safety Benchmarks