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

Oct 12, 2026

AuthGateBench: Benchmarking LLMs as Authorization Gate

Automated approval systems let coding agents execute high-risk actions with minimal human oversight by delegating the authorization decision to a classifier, typically a large language model (LLM). Such systems, adopted in tools like Claude Code and Codex, remain vulnerable to failure modes such as scope escalation, where the agent takes actions exceeding what the user authorized. Existing benchmarks focus mainly on malicious requests, evaluating refusal under an implicit policy. We introduce AuthGateBench, the first policy-guided benchmark for authorization gating under benign requests. We implement a novel pipeline where an LLM generates contrast pairs with identical action and trajectory but differing request, flipping the label between block and allow. This allows us to assess whether models reason over context rather than the action alone. We further examine whether auxiliary environment signals can help models make better decisions. The resulting benchmark comprises 1,400 instances spanning five failure modes drawn from real-world Claude Code incidents. Evaluations show accuracy degrades unevenly across failure modes as models over-rely on internal safety alignment, and models still block most actions even when explicitly authorized, revealing unstable rather than deterministic decisions; retrospectively retrieved environment signals, however, substantially improve authorization accuracy.
Oct 20, 2026

Runtime Control for AI Agents: Closing the Evaluation--Execution Gap in Operational Workflows

Language-model agents increasingly participate in operational workflows where approvals, binds, and payments create commitments. An approval valid when issued may no longer authorize execution after relevant facts, evidence, policy, or authority change. We call this the evaluation--execution gap. We specify a state-bound runtime assurance layer that separates probabilistic measurement from deterministic adjudication, binds an execution allowance to the decision-relevant basis of an approval, invalidates that allowance after relevant logged changes, and rechecks admissibility at dispatch. This distinguishes the continued validity of a prior approval from a current-state policy check. We describe eight failure modes, an assurance model, a reference architecture, and prospective interventions with retrospective remediation. In a scripted 42-case replay, the state-bound configuration identifies 15 later-invalidated approvals that a deliberately non-re-evaluating point-in-time comparator does not revisit; it holds 14 affected actions before dispatch and compensates one landed effect. These results illustrate behavior under the stipulated policies and event orders, not superiority over dispatch-time enforcement designs or production effectiveness. Under explicit interception, ingestion, dependency, and serialization assumptions, the model establishes dispatch-time validity within the registered execution surface.
Oct 20, 2026

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

When an LLM agent acts on behalf of a user, it is expected to act within the authorization scope the user grants. Existing agent evaluations largely measure task completion or harmful consequences and can therefore overlook actions that violate this delegation without producing conventional safety or privacy harms. We introduce AuthorizationBench, a benchmark of authorization alignment grounded in documented real-world cases. A scalable construction pipeline produces 286 executable tasks spanning situational triggers, the presence or absence of direct harmful consequences, and ten application domains. We execute every task with four models at two reasoning-effort settings across three agent harnesses in an authorization-aware sandbox that keeps authorized and out-of-authorization paths executable and observable, yielding 6,864 trajectories. Agents act out of authorization in 19.2% of trajectories, with rates ranging from 10.5% to 26.6% across the 24 configurations. Task completion does not imply authorization. Increasing reasoning effort leaves the aggregate rate nearly unchanged, with effects varying across models. On controlled pairs, agents act out of authorization at similar rates with (17.9%) and without (20.8%) direct harmful consequences, and more often under benign pressures than malicious injections (23.5% versus 17.6%, p=0.002). Our results show that task capability, additional reasoning, and consequence-oriented safety evaluation do not by themselves ensure authorization alignment. Moreover, agents that consult the principal before completing a task exhibit lower rates of out-of-authorization behavior (14.0% versus 21.6%, p<0.001), pointing to a tension between agent autonomy and preserving users' decision authority that calls for further human-centered study. Dataset and code are available at https://github.com/PEACH-Research-Lab/AuthorizationBench .