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

Kari Jaaskelainen

25 Nov 2025 — 1 min read

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

Meet GRACE: a moral governor for safer, more transparent AI

AI agents are getting powerful—so how do we make sure they do the right thing, not just the effective thing? Meet GRACE, a reason-based moral governor that keeps AI behavior aligned with human norms by separating moral reasoning from goal-driven decision-making. * Moral Module: uses deontic logic and explicit reasons

Why some fine-tuned LLMs miss phishing—and how to fix it

Not all fine-tuned LLMs spot phishing equally. A new study tests Llama 3.1 8B, Gemma 2 9B, and Mistral on high-stakes phishing detection—and uses SHAP and mechanistic interpretability to reveal why models do (or don’t) generalize. * Architecture × data diversity matters: Gemma 2 9B hits state-of-the-art performance (F1

AI that explains itself—by following the science

AI that explains itself—by following the science Black-box AI can be powerful, but it often can’t tell us why it made a decision. Concept Bottleneck Models (CBMs) try to fix that by predicting human-understandable concepts first, then the final answer. The catch: standard CBMs ignore domain-specific cause-and-effect and

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

TL;DR: Finding reliable answers in genomics is hard. GenomAgent turns one big AI into a coordinating team of specialists—and beats the current leader by 12% on a key benchmark. Genomic facts live across many databases. Standard chatbots struggle because they can’t flexibly query those sources. GeneGPT added

Read more

Meet GRACE: a moral governor for safer, more transparent AI

Why some fine-tuned LLMs miss phishing—and how to fix it

AI that explains itself—by following the science

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A