让编程助手具备持续记忆与执行反馈能力，实现更可靠的长期推理。
Towards Structured, State-Aware, and Execution-Grounded Reasoning for Software Engineering Agents
- 引入显式结构与持续状态，突破传统对话式响应局限。
- 通过执行反馈动态调整推理路径，提升任务连贯性。
- 适合构建复杂软件开发任务的下一代智能助手。
当前软件工程（SE）代理主要依赖对话历史和最新回复做出反应，缺乏显式结构与持久状态，难以支持长周期推理。这导致其在跨步骤理解、假设更新及整合执行反馈方面表现不足。本文主张，为推动SE代理发展，需从被动反应转向结构化、状态感知与执行锚定的推理范式。我们提出通过显式结构、持续演化的状态表示以及执行反馈的集成，使代理在长周期任务中实现更连贯、可靠的推理。同时，本文初步勾勒了下一代SE代理的发展路线图，以更好地应对真实世界中的复杂开发任务。
原文摘要 · Abstract (English)
Software Engineering (SE) agents have shown promising abilities in supporting various SE tasks. Current SE agents remain fundamentally reactive, making decisions mainly based on conversation history and the most recent response. However, this reactive design provides no explicit structure or persistent state within the agent's memory, making long-horizon reasoning challenging. As a result, SE agents struggle to maintain a coherent understanding across reasoning steps, adapt their hypotheses as new evidence emerges, or incorporate execution feedback into the mental reasoning model of the system state. In this position paper, we argue that, to further advance SE agents, we need to move beyond reactive behavior toward a structured, state-aware, and execution-grounded reasoning. We outline how explicit structure, persistent and evolving state, and the integration of execution-grounded feedback can help SE agents perform more coherent and reliable reasoning in long-horizon tasks. We also provide an initial roadmap for developing next-generation SE agents that can more effectively perform real-world tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。