AI RESEARCH
BOHM: Zero-Cost Hierarchical Attribution for Compound AI Systems
arXiv CS.AI
•
ArXi:2605.22866v1 Announce Type: new Compound AI systems route tasks through hierarchies of specialised components. Attribution is dominated by Shapley-based methods (SHAP), which decompose a coalition value function into per-component marginal contributions and require evaluation of the system on arbitrary component subsets. That requirement fails for third-party APIs, opaque endpoints, and agentic orchestrators that concentrate routing on a few tools, leaving most coalitions un-evaluable from the deployed orchestrator. We.