paper-with-me

Papers

On Problems of Implicit Context Compression for Software Engineering Agents

2026-05-11 · Kirill Gelvan, Igor Slinko, Felix Steinbauer, Egor Bogomolov, Florian Kofler, Yaroslav Zharov arxiv

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.

📄 PDF Abstract BibTeX arXiv:2605.11051

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Machine Learning Model Development from a Software Engineering Perspective: A Systematic Literature Review

2021-02-15 · Giuliano Lorenzoni, Paulo Alencar, Nathalia Nascimento, Donald Cowan

Data scientists often develop machine learning models to solve a variety of problems in the industry and academy but not without facing several challenges in terms of Model Development. The problems regarding Machine Lea…

BIG-bench Machine LearningSystematic Literature Review

SWE-MeM: Learning Adaptive Memory Management for Long-Horizon Coding Agents

2026-06-26 · Shuzheng Gao, Wenhao Zeng, Zhaojian Yu, Jianqiao Wangni 외 arxiv

Long-horizon software engineering agents often need to manage lengthy and noisy interaction histories under limited context budgets. Existing memory management methods typically rely on static compression workflows or im…

Studying Software Engineering Patterns for Designing Machine Learning Systems

2019-10-10 · Hironori Washizaki, Hiromu Uchida, Foutse khomh, Yann-Gael Gueheneuc

Machine-learning (ML) techniques have become popular in the recent years. ML techniques rely on mathematics and on software engineering. Researchers and practitioners studying best practices for designing ML application …

BIG-bench Machine LearningSystematic Literature Review

On the Evaluation of Engineering Artificial General Intelligence

2025-05-15 · Sandeep Neema, Susmit Jha, Adam Nagel, Ethan Lew 외

We discuss the challenges and propose a framework for evaluating engineering artificial general intelligence (eAGI) agents. We consider eAGI as a specialization of artificial general intelligence (AGI), deemed capable of…

Benchmarking

MASAI: Modular Architecture for Software-engineering AI Agents

2024-06-17 · Daman Arora, Atharv Sonwane, Nalin Wadhwa, Abhav Mehrotra 외

A common method to solve complex problems in software engineering, is to divide the problem into multiple sub-problems. Inspired by this, we propose a Modular Architecture for Software-engineering AI (MASAI) agents, wher…