Towards Structured, State-Aware, and Execution-Grounded Reasoning for Software Engineering Agents

TL;DR

This paper advocates for developing software engineering agents with explicit structure, persistent state, and execution-grounded reasoning to improve their ability to handle complex, long-term tasks effectively.

Contribution

It proposes a shift from reactive to structured, state-aware, and execution-grounded reasoning in SE agents, outlining a roadmap for future development.

Findings

Current SE agents are mostly reactive and lack persistent memory.

Structured and state-aware reasoning can improve long-horizon task performance.

Integration of execution feedback enhances reasoning coherence.

Abstract

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.