The path to higher network autonomy in 6G lies beyond the mere optimization of key performance indicators (KPIs). While KPIs have enabled automation gains under TM Forum Levels 1--3, they remain numerical abstractions that act only as proxies for the real essence of communication networks: seamless connectivity, fairness, adaptability, and resilience. True autonomy requires perceiving and reasoning over the network environment as it is. Such progress can be achieved through \emph{agentic AI}, where large language model (LLM)-powered agents perceive multimodal telemetry, reason with memory, negotiate across domains, and act via APIs to achieve multi-objective goals. However, deploying such agents introduces the challenge of cognitive biases inherited from human design, which can distort reasoning, negotiation, tool use, and actuation. Between neuroscience and AI, this paper provides a tutorial on a selection of well-known biases, including their taxonomy, definition, mathematical formulation, emergence in telecom systems and the commonly impacted agentic components. The tutorial also presents various mitigation strategies tailored to each type of bias. The article finally provides two practical use-cases, which tackle the emergence, impact and mitigation gain of some famous biases in 6G inter-slice and cross-domain management. In particular, anchor randomization, temporal decay and inflection bonus techniques are introduced to specifically address anchoring, temporal and confirmation biases. This avoids that agents stick to the initial high resource allocation proposal or decisions that are recent and/or confirming a prior hypothesis. By grounding decisions in a richer and fairer set of past experiences, the quality and bravery of the agentic agreements in the second use-case, for instance, are leading to $\times 5$ lower latency and around $40\%$ higher energy saving.

翻译：实现6G网络更高自主性的路径，远不止于关键性能指标（KPIs）的优化。尽管KPIs在TM Forum 1-3级标准下推动了自动化水平的提升，但它们仍是数值抽象，仅作为通信网络真实本质——无缝连接、公平性、适应性与韧性——的代理指标。真正的自主性要求感知并基于网络环境的真实状况进行推理。这一进展可通过**代理人工智能**实现，即由大型语言模型（LLM）驱动的智能体感知多模态遥测数据、利用记忆进行推理、跨域协商，并通过API执行操作以实现多目标。然而，部署此类智能体带来了源自人类设计的认知偏见挑战，这些偏见可能扭曲推理、协商、工具使用与执行过程。本文立足于神经科学与人工智能交叉领域，针对一系列已知偏见提供教程式阐述，涵盖其分类、定义、数学表述、在电信系统中的显现方式以及通常受影响的代理组件。本教程还针对各类偏见提出了相应的缓解策略。文章最后提供了两个实际用例，分别处理6G网络切片间与跨域管理中某些典型偏见的产生、影响及缓解效果。特别地，文中介绍了锚点随机化、时间衰减与拐点奖励等技术，以针对性应对锚定效应、时间偏见与确认偏见。这避免了智能体固守初始的高资源分配方案，或过度依赖近期及/或证实先前假设的决策。通过将决策建立在更丰富、更公平的历史经验基础上，例如在第二个用例中，代理协商协议的质量与胆识使得延迟降低了5倍，节能效果提升了约40%。