arXiv：cs.AI（全量分类）· J\'er\'emie Lumbroso·· 5 小时前AI 评分36
可信智能体委托缺失的词汇：控制论与认知的双重语言
Cybernetic and Epistemic: A Missing Vocabulary for Trustworthy Agentic Delegation
AI 导读
随着代码生成日益委托给 AI 系统，瓶颈正从写代码转向监督写代码的系统，而现有词汇无法区分委托通道中语言的两种功能：协调行动（控制论）与协调理解（认知）。研究提出智能体系统治理准则：每个重要选择都应附带其本可另作他选的条件，并以第三方可检验的形式呈现，同时给出两部分重建测试与 ORRCF 审议记录约定。
正文
Abstract:As code generation is increasingly delegated to AI systems, the bottleneck is shifting from writing code to supervising the systems that write it --- a shift CS-education researchers have begun to name. This shift exposes a vocabulary gap: the field asks for "human oversight" without a working distinction between the two things language does in a delegation channel --- coordinate action (cybernetic: words succeed when the world comes to match them) and coordinate understanding (epistemic: they succeed when they answer to the world and a hearer can check that they do). The failure this names is not cybernetic language but epistemic-form language doing cybernetic work: explanation-shaped output calibrated for approval rather than truth. Oversight that checks only whether an output was approved is satisfiable by rubber-stamping; oversight that holds an agent accountable requires the reasoning behind its work be retrievable and checkable. We present three delegation episodes --- illustrations, not controlled evidence --- in which epistemic engagement proved practicable while remaining auditable, one public record where a recommendation was withdrawn on its own stated terms, and one failure case illustrating oversight that requires no reasons for its discretionary choices. We propose a criterion for agentic-system governance, alongside existing technical trust properties: every consequential choice should carry the condition under which it would have gone otherwise, in a form a third party can test. Without such a condition, a third party cannot distinguish a decision from a rubber stamp. We give the criterion an operational form --- a two-part reconstruction test scoring a delegation record by whether a second reader can predict what the agent does under a perturbation --- and a deliberation-recording convention, ORRCF, that makes the condition a required component of every recorded choice.
| Comments: | Accepted at TAS 2026 (AAAI Fall Symposium Series), Nov 5-7, 2026, Arlington VA |
| Subjects: | Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC) |
| Cite as: | arXiv:2610.00961 [cs.AI] |
| (or arXiv:2610.00961v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.00961 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jérémie Lumbroso [view email]
[v1]
Thu, 1 Oct 2026 02:46:49 UTC (29 KB)
来源：arXiv：cs.AI（全量分类） · arxiv.org