# Cross-Lingual Token Arbitrage: Optimizing Code Agent Context Windows via Local LLM Preprocessing

arXiv: https://arxiv.org/abs/2606.03618 · HTML: https://mlsanity.com/paper/2606.03618/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 14 of its 25 references that are in the map.
- First posted on arXiv 2 Jun 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 14 of 14)

- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://mlsanity.com/paper/2305.03495/) (2023)
- [RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation](https://mlsanity.com/paper/2303.12570/) (2023)
- [LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression](https://mlsanity.com/paper/2403.12968/) (2024)
- [Language Model Tokenizers Introduce Unfairness Between Languages](https://mlsanity.com/paper/2305.15425/) (2023)
- [Reducing Cost of LLM Agents with Trajectory Reduction](https://mlsanity.com/paper/2509.23586/) (2025)
- [GraphCoder: Enhancing Repository-Level Code Completion via Code Context Graph-based Retrieval and Language Model](https://mlsanity.com/paper/2406.07003/) (2024)
- [LongCodeZip: Compress Long Context for Code Language Models](https://mlsanity.com/paper/2510.00446/) (2025)
- [COFFE: A Code Efficiency Benchmark for Code Generation](https://mlsanity.com/paper/2502.02827/) (2025)
- [Compressing Code Context for LLM-based Issue Resolution](https://mlsanity.com/paper/2603.28119/) (2026)
- [OckBench: Measuring the Efficiency of LLM Reasoning](https://mlsanity.com/paper/2511.05722/) (2025)
- [Model Cascading for Code: A Cascaded Black-Box Multi-Model Framework for Cost-Efficient Code Completion with Self-Testing](https://mlsanity.com/paper/2405.15842/) (2024)
- [EfficientXLang: Towards Improving Token Efficiency Through Cross-Lingual Reasoning](https://mlsanity.com/paper/2507.00246/) (2025)
- [Balancing Latency and Accuracy of Code Completion via Local-Cloud Model Cascading](https://mlsanity.com/paper/2603.05974/) (2026)

## Built on by (most cited first, 1 of 1)

- [Lost in Compression: A Controlled Cross-Lingual Audit of Extractive Prompt Compressors](https://mlsanity.com/paper/2608.26175/) (2026)

## Abstract (arXiv)

AI-assisted coding agents are bottlenecked by input-token cost. Two pathologies of raw human input drive much of this overhead: tokenization inefficiency for non-English text and structural entropy in conversational prompts. Existing approaches act reactively by compressing already-bloated contexts or intervening after failures occur. We introduce a pre-flight, edge-side prompt-rewriting middleware that operates between the developer and the cloud agent. A local Llama 3.2 (3B) model performs cross-lingual translation into English, structural rewriting into a compact task-oriented format, and regex-validated rewrite-with-fallback safeguards to ensure the optimized prompt is never larger than the original. We evaluate on OMH-Polyglot, a multilingual coding benchmark spanning Turkish, Arabic, Chinese, and code-switched specifications. Across three commercial LLM backends, the middleware reduces prompt tokens by 34-47 percent and total tokens by up to 18.8 percent while preserving or improving task accuracy. Ablation studies show that gains arise primarily from the rewriting stage rather than simple function-name extraction. Compared with LLMLingua-2 at matched compression rates, our method consistently achieves superior OckScore performance across all evaluated backends. These results demonstrate that proactive prompt optimization can substantially reduce inference costs without sacrificing coding quality.