A Tutorial on Cognitive Biases in Agentic AI-Driven 6G Autonomous Networks

TL;DR

This tutorial argues that achieving higher 6G network autonomy requires moving beyond KPI-centric optimization to goal-directed agentic AI, where LLM-powered agents perceive multimodal telemetry, reason with memory, negotiate across domains, and act via network APIs. It provides a structured taxonomy of cognitive biases, maps them to agentic components, and details mitigation strategies, including bias-aware reasoning hooks and system-level defenses. Two practical use-cases demonstrate that anchor randomization and memory-based debiasing can substantially improve performance metrics such as latency and energy efficiency while reducing premature convergence in negotiation. The work highlights the need for bias-aware autonomy, co-evolving beyond local agents toward robust, multi-agent coordination and grounded representations to ensure fair, reliable, and scalable 6G management.

Abstract

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.

Figures (15)

• Figure 1: Typical components of a 6G agentic system.
• Figure 2: Anchoring bias in 6G agentic negotiation.
• Figure 3: Availability bias concept.
• Figure 4: Suggestion Bias shifts the agent's decision in the multi-objective space.
• Figure 5: Groupthink emergence.