Directed Information $γ$-covering: An Information-Theoretic Framework for Context Engineering

We introduce Directed Information $γ$-covering, a simple but general framework for redundancy-aware context engineering. Directed information (DI), a causal analogue of mutual information, measures asymmetric predictiveness between chunks. If DIi → j ≥ H(Cⱼ) - γ, then Cᵢ suffices to represent Cⱼ up to $γ$ bits. Building on this criterion, we formulate context selection as a $γ$-cover problem and propose a greedy algorithm with provable guarantees: it preserves query information within bounded slack, inherits (1+ln n) and $(1-1/e)$ approximations from submodular set cover, and enforces a diversity margin. Importantly, building the $γ$-cover is query-agnostic: it incurs no online cost and can be computed once offline and amortized across all queries. Experiments on HotpotQA show that $γ$-covering consistently improves over BM25, a competitive baseline, and provides clear advantages in hard-decision regimes such as context compression and single-slot prompt selection. These results establish DI $γ$-covering as a principled, self-organizing backbone for modern LLM pipelines.