SphUnc: Hyperspherical Uncertainty Decomposition and Causal Identification via Information Geometry

arXiv:2603.01168v2 Announce Type: replace-cross Abstract: Reliable decision-making in complex multi-agent systems requires calibrated predictions and interpretable uncertainty. We introduce SphUnc, a unified framework combining hyperspherical representation learning with structural causal modeling. The model maps features to unit hypersphere latents using von Mises-Fisher distributions, decomposing uncertainty into epistemic and aleatoric components through information-geometric fusion. A structural causal model on spherical latents enables directed influence identification and interventional reasoning via sample-based simulation. Empirical evaluations on social and affective benchmarks demonstrate improved accuracy, better calibration, and interpretable causal signals, establishing a geometric-causal foundation for uncertainty-aware reasoning in multi-agent settings with higher-order interactions.

Every Response Counts: Quantifying Uncertainty of LLM-based Multi-Agent Systems through Tensor Decomposition
Deep Learning for Sequential Decision Making under Uncertainty: Foundations, Frameworks, and Frontiers
Explicit Trait Inference for Multi-Agent Coordination
Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning

Source: arXiv cs.AI | 2026-04-23

Related