arXiv:2611.16879v1 Announce Type: cross
Abstract: AI-RAN distributes network control across multiple autonomous agents, namely xApps and rApps operating over shared radio resources. When an alert or degradation appears, operators currently lack a structured way to trace which decision caused it, what context triggered that decision, and how other agents interacted. Existing explainability tools focus on single-model feature attribution or linear event logging, neither of which captures cross-agent decision chains. We propose the Context Graph, a heterogeneous directed graph that organizes policies, measurements, decisions, and alerts into a queryable explanation layer. Its foundational primitive is the Decision-Event node acting as a causal junction, where incoming edges capture triggering context and outgoing edges track downstream consequences that are progressively upgraded through counterfactual verification. Instantiated over existing E2, A1, and O1 data flows, our proof-of-concept demonstrates that compliance and diagnosis queries are resolved at sub-millisecond latency over graphs of tens of thousands of nodes, while reliably distinguishing true causal impacts from spurious correlations.
arxiv
Context Graph: Explainable Multi-Agent Decision Chains in AI-RAN
The paper introduces Context Graph, a heterogeneous directed graph for tracing multi-agent decision chains in AI-RAN networks. It uses Decision-Event nodes as causal junctions to link policies, measurements, decisions, and alerts, with counterfactual verification to separate true causes from spurious correlations. A proof-of-concept over E2, A1, and O1 data flows shows sub-millisecond query latency on graphs with tens of thousands of nodes.
Offers a concrete research contribution addressing explainability and causal tracing in multi-agent AI-RAN systems, a timely operational challenge.
Comments & Questions (0)
No comments yet
Be the first to comment!