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

2026-02-04

AI Summary

Current software engineering agents generally lack structured memory and persistent state, hindering their ability to maintain coherent reasoning or effectively incorporate execution feedback over long-horizon tasks. This work proposes a novel agent architecture that systematically integrates structured reasoning, state awareness, and execution grounding through explicit structured memory, an evolvable state representation, and a closed-loop execution feedback mechanism. By moving beyond traditional reactive designs, the framework establishes a clear technical pathway for next-generation software engineering agents, significantly enhancing their reasoning consistency and execution reliability in complex, real-world tasks.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent/AI Theories and Architectures
• Knowledge Representation and Reasoning: Knowledge Engineering

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

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.

Problem

• Software Engineering Agents
• Reactive Reasoning
• Long-horizon Reasoning
• State Awareness
• Execution Feedback

Innovation

• structured reasoning
• state-awareness
• execution-grounded feedback
• software engineering agents
• long-horizon reasoning