发表机构
University of Southern Denmark（南丹麦大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对企业AI智能体难以持续运行的问题，提出重建共享认知基底，以Markdown等表示匹配推理表面，并通过四层框架和同步智能体实现治理与可审计性。
AI 中文摘要
企业AI智能体常常在演示中取得成功，但一旦需要日复一日地运行便会停滞。一份行业报告估计，大多数试点项目从未进入生产阶段，已部署的系统也很少保留反馈或随时间改进，而智能体基准测试显示单次运行的成功掩盖了不可靠的重复性。我们认为这些失败模式有一个共同的架构根源：智能体推理所依据的数据是为人类操作者和传统应用程序而结构化的，而非为驱动它们的语言模型所设计。本立场论文提出，在持续运营中部署智能体的公司应重建其认知基底——智能体作为工作上下文读取的共享环境——使其围绕与推理表面相匹配的表示，并将模式转换隔离到行动边界。Markdown是当今可用的实例化形式，而非经过验证的智能体原生原语。两个机制支撑了这一论点：上下文带宽不对称性，即一次性阅读连贯散文与逐字段类型化访问（剥离关系）之间的差距；以及跨循环耦合，即行动、技能和策略循环只有在共享一个基底时才会复合。一个四层框架（数据、知识、智能、治理）将该立场操作化，其中同步智能体强制执行行动边界和每技能信任梯度，使治理和可审计性成为基底的结构属性。该立场在LLM时代经济学下复兴了经典多智能体系统的共享基底传统。我们分析了主要反对意见和风险，包括编译路径上的间接提示注入，并概述了直接评估基底的研究议程。
英文摘要
Enterprise AI agents often succeed in a demonstration and then stall once they must operate day after day. An industry report estimates that most pilots never reach production and that deployed systems rarely retain feedback or improve over time, while agent benchmarks show single-run successes masking unreliable repetition. We argue that these failure modes share a common architectural root: agents reason over data structured for human operators and traditional applications, not for the language models that power them. This position paper proposes that companies deploying agents in sustained operation should rebuild their cognitive substrate, the shared environment agents read as working context, around representations matched to that reasoning surface, isolating schema translation to the action boundary. Markdown is the instantiation available today, not a proven agent-native primitive. Two mechanisms ground the argument: context-bandwidth asymmetry, the gap between one-pass reading of connected prose and field-by-field typed access that strips relations; and cross-loop coupling, the claim that action, skill, and policy loops compound only if they share one substrate. A four-layer framework (Data, Knowledge, Intelligence, Governance) operationalizes the position, with a Sync Agent enforcing the action boundary and a per-skill trust gradient, making governance and auditability structural properties of the substrate. The position revives the shared-substrate tradition of classical multi-agent systems under LLM-era economics. We analyze the main objections and risks, including indirect prompt injection on the compile path, and outline a research agenda for evaluating substrates directly.
Comments19 pages, 3 figures, 2 tables. Accepted as a peer-reviewed short paper (position-paper track) at the 2nd International Conference on Agentic and Generative Techniques in Intelligent Computational Systems (AGENTICS 2026), Angers, France, 28-30 October 2026, part of IJCCI 2026, and for publication in the Springer CCIS proceedings. This is the author's accepted manuscript
