# Stingy Context: 18:1 Hierarchical Code Compression for LLM Auto-Coding

arXiv: https://arxiv.org/abs/2601.19929 · HTML: https://mlsanity.com/paper/2601.19929/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 0 of its 6 references that are in the map.
- First posted on arXiv 11 Jan 2026.

## Abstract (arXiv)

We introduce Stingy Context, a hierarchical tree-based compression scheme achieving 18:1 reduction in LLM context for auto-coding tasks. Using our TREEFRAG exploit decomposition, we reduce a real source code base of 239k tokens to 11k tokens while preserving task fidelity. Empirical results across 12 Frontier models show 94 to 97% success on 40 real-world issues at low cost, outperforming flat methods and mitigating lost-in-the-middle effects.