SWE-AGILE: A Software Agent Framework for Efficiently Managing Dynamic Reasoning Context
Shuquan Lian, Juncheng Liu, Yazhe Chen, Yuhong Chen, Hui Li
Feedback
Why It Matters
This paper addresses critical challenges in autonomous software engineering by enhancing reasoning capabilities, which could lead to more effective and efficient AI systems in complex environments.
Contributions
- Introduction of the Dynamic Reasoning Context strategy and Reasoning Digests to improve reasoning efficiency in software agents.
Insights
- The sliding window approach allows for immediate continuity in reasoning without overwhelming the system with excessive historical data.
Limitations
- The empirical results are based on a limited number of trajectories and tasks, which may affect the generalizability of the findings.
Tags
- agent
- benchmark
- reasoning
Abstract
arXiv:2604.11716v1 Announce Type: new Abstract: 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.