Reducing Token Usage of State-in-Context Agents using Minification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hrubec, Nicolas, Cito, Jürgen
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911738514898944
author Hrubec, Nicolas
Cito, Jürgen
author_facet Hrubec, Nicolas
Cito, Jürgen
contents This paper presents a replication and extension of the recently introduced state-in-context agent framework. We independently re-implement the DirectSolve variant and evaluate it on the SWE-bench Verified benchmark. We report end-to-end full-benchmark results using GPT-5-mini and run selected ablations with GPT-4.1. In addition, we investigate a complementary research question: What is the impact of token-reducing input transformation strategies on the performance of software engineering agents? Based on a preliminary prompt analysis, we identify source code as the dominant contributor to token consumption. We therefore apply a series of code minification techniques that remove or shorten non-essential lexical elements while preserving program semantics. The proposed transformations are integrated into the agent and systematically evaluated. Experiments show that minification reduces average input token usage by 42% with a 12 percentage-point drop in resolution rate. These findings demonstrate that lightweight source code transformations can yield substantial efficiency gains while retaining a substantial fraction of the baseline performance, indicating a promising path toward more cost-effective agents. The full implementation is publicly available on GitHub: https://github.com/ipa-lab/minified-state-in-context-agent
format Preprint
id arxiv_https___arxiv_org_abs_2606_01326
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Reducing Token Usage of State-in-Context Agents using Minification
Hrubec, Nicolas
Cito, Jürgen
Software Engineering
This paper presents a replication and extension of the recently introduced state-in-context agent framework. We independently re-implement the DirectSolve variant and evaluate it on the SWE-bench Verified benchmark. We report end-to-end full-benchmark results using GPT-5-mini and run selected ablations with GPT-4.1. In addition, we investigate a complementary research question: What is the impact of token-reducing input transformation strategies on the performance of software engineering agents? Based on a preliminary prompt analysis, we identify source code as the dominant contributor to token consumption. We therefore apply a series of code minification techniques that remove or shorten non-essential lexical elements while preserving program semantics. The proposed transformations are integrated into the agent and systematically evaluated. Experiments show that minification reduces average input token usage by 42% with a 12 percentage-point drop in resolution rate. These findings demonstrate that lightweight source code transformations can yield substantial efficiency gains while retaining a substantial fraction of the baseline performance, indicating a promising path toward more cost-effective agents. The full implementation is publicly available on GitHub: https://github.com/ipa-lab/minified-state-in-context-agent
title Reducing Token Usage of State-in-Context Agents using Minification
topic Software Engineering
url https://arxiv.org/abs/2606.01326