Saved in:
Bibliographic Details
Main Authors: Lian, Shuquan, Liu, Juncheng, Chen, Yazhe, Chen, Yuhong, Li, Hui
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.11716
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914469645385728
author Lian, Shuquan
Liu, Juncheng
Chen, Yazhe
Chen, Yuhong
Li, Hui
author_facet Lian, Shuquan
Liu, Juncheng
Chen, Yazhe
Chen, Yuhong
Li, Hui
contents Prior representative ReAct-style approaches in autonomous Software Engineering (SWE) typically lack the explicit System-2 reasoning required for deep analysis and handling complex edge cases. While recent reasoning models demonstrate the potential of extended Chain-of-Thought (CoT), applying them to the multi-turn SWE task creates a fundamental dilemma: retaining full reasoning history leads to context explosion and ``Lost-in-the-Middle'' degradation, while discarding it would force the agent to redundantly re-reason at every step. To address these challenges, we propose SWE-AGILE, a novel software agent framework designed to bridge the gap between reasoning depth, efficiency, and context constraints. SWE-AGILE introduces a Dynamic Reasoning Context strategy, maintaining a ``sliding window'' of detailed reasoning for immediate continuity to prevent redundant re-analyzing, while compressing historical reasoning content into concise Reasoning Digests. Empirically, SWE-AGILE sets a new standard for 7B-8B models on SWE-Bench-Verified using only 2.2k trajectories and 896 tasks. Code is available at https://github.com/KDEGroup/SWE-AGILE.
format Preprint
id arxiv_https___arxiv_org_abs_2604_11716
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SWE-AGILE: A Software Agent Framework for Efficiently Managing Dynamic Reasoning Context
Lian, Shuquan
Liu, Juncheng
Chen, Yazhe
Chen, Yuhong
Li, Hui
Artificial Intelligence
Computation and Language
Prior representative ReAct-style approaches in autonomous Software Engineering (SWE) typically lack the explicit System-2 reasoning required for deep analysis and handling complex edge cases. While recent reasoning models demonstrate the potential of extended Chain-of-Thought (CoT), applying them to the multi-turn SWE task creates a fundamental dilemma: retaining full reasoning history leads to context explosion and ``Lost-in-the-Middle'' degradation, while discarding it would force the agent to redundantly re-reason at every step. To address these challenges, we propose SWE-AGILE, a novel software agent framework designed to bridge the gap between reasoning depth, efficiency, and context constraints. SWE-AGILE introduces a Dynamic Reasoning Context strategy, maintaining a ``sliding window'' of detailed reasoning for immediate continuity to prevent redundant re-analyzing, while compressing historical reasoning content into concise Reasoning Digests. Empirically, SWE-AGILE sets a new standard for 7B-8B models on SWE-Bench-Verified using only 2.2k trajectories and 896 tasks. Code is available at https://github.com/KDEGroup/SWE-AGILE.
title SWE-AGILE: A Software Agent Framework for Efficiently Managing Dynamic Reasoning Context
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2604.11716