Towards Structured, State-Aware, and Execution-Grounded Reasoning for Software Engineering Agents
This addresses the problem of incoherent reasoning in software engineering agents for developers and researchers, but it is a position paper outlining a roadmap rather than presenting new results.
The paper argues that current software engineering agents are reactive and lack structured memory, making long-horizon reasoning difficult, and proposes a shift towards structured, state-aware, and execution-grounded reasoning to improve coherence and reliability in such tasks.
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.