Safer 6G AI: Stop Averaging, Start Managing Tail Risk

LLM-powered network agents often decide based on simple averages—ignoring rare but catastrophic events. In 6G, that bias can break service guarantees.

This work introduces a risk-aware negotiation framework for 6G network slicing that teaches agents to plan for the worst, not just the mean.

• Predict the full latency distribution with Digital Twins (not just an average).
• Score decisions using Conditional Value-at-Risk (CVaR) from extreme value theory, shifting focus to the tail.
• Quantify epistemic uncertainty—agents measure confidence in their own predictions and act cautiously when it’s low.

In an eMBB–URLLC negotiation test, the usual mean-based approach failed SLAs 25% of the time. The CVaR-aware agent eliminated SLA violations and cut both slices’ p99.999 latency by ~11%. The trade-off? Slightly lower energy savings (around 17%)—a rational cost that avoids the false economy of risky shortcuts.

Bottom line: to build trustworthy 6G autonomy, make agents uncertainty-aware and tail-focused.

Paper: https://arxiv.org/abs/2511.19175v1

Register: https://www.AiFeta.com

6G AI LLM AutonomousSystems NetworkSlicing DigitalTwins CVaR RiskManagement ExtremeValueTheory URLLC eMBB Telecom