Stingy Context: 18:1 Hierarchical Code Compression for LLM Auto-Coding
Year: 2026
Type: preprint
Abstract: 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.
Source: arXiv (Cornell University)
Author: Ostby, David Linus
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7126045470
Cites:
Cited by:
Related to: