{"ID":3053296,"CreatedAt":"2026-06-04T04:41:36.695875263Z","UpdatedAt":"2026-06-06T00:15:09.974762002Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.04306","arxiv_id":"2606.04306","title":"Organizational Control Layer: Governance Infrastructure at the Execution Boundary of LLM Agent Systems","abstract":"LLM-based agents are increasingly deployed in workflows where generated outputs may directly trigger state-changing actions. This creates an execution-boundary problem: proposed actions must be governed before they are executed. We study this problem through economically consequential multi-agent interactions and argue that deployment-grade agent systems should separate proposal generation from environment-facing execution. To operationalize this principle, we introduce the Organizational Control Layer (OCL), a model-agnostic governance infrastructure that intercepts generated actions before execution through policy enforcement and escalation, without modifying the underlying LLM generator. We evaluate OCL on adversarial buyer--seller negotiation environments adapted from AgenticPay. Across multiple frontier LLM backends, OCL reduces unsafe executions from 88% to near-zero while increasing valid success from 12% to 96%. Results further reveal a safety--utility tradeoff: strict governance improves compliance and reliability against policy and constraint violations, but can reduce flexibility in tightly constrained markets. These findings suggest that deployment-grade LLM agent systems require explicit governance at the boundary between language generation and executable actions. The source code is available at: https://github.com/SHITIANYU-hue/amai_ocl","short_abstract":"LLM-based agents are increasingly deployed in workflows where generated outputs may directly trigger state-changing actions. This creates an execution-boundary problem: proposed actions must be governed before they are executed. We study this problem through economically consequential multi-agent interactions and argue...","url_abs":"https://arxiv.org/abs/2606.04306","url_pdf":"https://arxiv.org/pdf/2606.04306v1","authors":"[\"Tianyu Shi\",\"Yang Mo\",\"Yiou Liu\",\"Zhuonan Hao\",\"Yin Wang\",\"Wenzhuo Hu\",\"Nan Yu\",\"Meng Zhou\",\"Jiangbo Yu\"]","published":"2026-06-03T00:25:56Z","proceeding":"cs.MA","tasks":"[\"cs.MA\"]","methods":"[\"Large Language Model\",\"Generative Adversarial Network\"]","has_code":false,"code_links":[{"ID":612805,"CreatedAt":"2026-06-04T04:41:36.695875263Z","UpdatedAt":"2026-06-04T04:41:36.695875263Z","DeletedAt":null,"paper_id":3053296,"paper_url":"https://arxiv.org/abs/2606.04306","paper_title":"Organizational Control Layer: Governance Infrastructure at the Execution Boundary of LLM Agent Systems","repo_url":"https://github.com/SHITIANYU-hue/amai_ocl","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}