Saved in:
Bibliographic Details
Main Authors: Gelvan, Kirill, Slinko, Igor, Steinbauer, Felix, Bogomolov, Egor, Kofler, Florian, Zharov, Yaroslav
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.11051
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917481593962496
author Gelvan, Kirill
Slinko, Igor
Steinbauer, Felix
Bogomolov, Egor
Kofler, Florian
Zharov, Yaroslav
author_facet Gelvan, Kirill
Slinko, Igor
Steinbauer, Felix
Bogomolov, Egor
Kofler, Florian
Zharov, Yaroslav
contents LLM-based Software Engineering agents face a critical bottleneck: context length limitations cause failures on complex, long-horizon tasks. One promising solution is to encode context as continuous embeddings rather than discrete tokens, enabling denser information storage. We apply the recently proposed In-Context Autoencoder for this purpose. While the method performs well on single-shot common-knowledge and code-understanding tasks, our experiments demonstrate that it fails on multi-step agentic coding tasks. In this paper, we explore this phenomenon and discuss possible factors contributing to this failure.
format Preprint
id arxiv_https___arxiv_org_abs_2605_11051
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle On Problems of Implicit Context Compression for Software Engineering Agents
Gelvan, Kirill
Slinko, Igor
Steinbauer, Felix
Bogomolov, Egor
Kofler, Florian
Zharov, Yaroslav
Software Engineering
Artificial Intelligence
Computation and Language
Machine Learning
LLM-based Software Engineering agents face a critical bottleneck: context length limitations cause failures on complex, long-horizon tasks. One promising solution is to encode context as continuous embeddings rather than discrete tokens, enabling denser information storage. We apply the recently proposed In-Context Autoencoder for this purpose. While the method performs well on single-shot common-knowledge and code-understanding tasks, our experiments demonstrate that it fails on multi-step agentic coding tasks. In this paper, we explore this phenomenon and discuss possible factors contributing to this failure.
title On Problems of Implicit Context Compression for Software Engineering Agents
topic Software Engineering
Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2605.11051