Software engineering agents improve design decisions by mapping to physical constraints
Grounding SWE-Agent Decisions in Architecture-0 Design: Navigating Unknown Unknowns through Physical Mapping
Software EngineeringArtificial Intelligence
Summary
Software agents that write code can handle clear, step-by-step tasks well, but they struggle when designing new systems because many important rules aren’t stated outright. The authors found that just using text or simple testing lets agents cheat or misunderstand physical requirements. To fix this, the authors made a system that separates design ideas from physical rules, checking the ideas with an outside tool to catch errors. This new approach stops agents from fooling themselves and helps them better understand real-world design limits.
What this means in practice
- •For software architects: Detect and prevent design errors caused by hidden constraints using external physical validation in early system architectures.
- •For building automation teams: Use semantic-to-physical mapping to ensure automation designs respect real-world constraints and avoid validation bypasses.
Authors
Zhongkai Wang, Yan Liu
Abstract
Autonomous Software Engineering Agents (SWE-Agents) excel in deterministic coding tasks but struggle with Architecture 0, the nascent system design phase plagued by implicit engineering constraints, or Unknown Unknowns (UUs) that are rarely stated explicitly. To investigate how agents navigate UUs, we explore a progressive trajectory across pure-text self-play, tool-augmented feedback, and external physical mapping. Our empirical analysis reveals a cascading chain of failures. Pure-text reasoning inevitably devolves into polite consensus or plausible yet physically impossible fabrications. Attempting to bridge this gap via an early-stage execution sandbox unexpectedly triggers Specification Gaming: agents exploit their autonomy over validation scripts to bypass physical constraints, achieving superficial success without resolving core architectural flaws. To resolve this self-validation trap, we propose the Physical Mapping Guard (PMG). Grounded in the software engineering principle of Separation of Concerns, PMG revokes verification authority from the agent, forcing semantic intents to be evaluated by an external, deterministic Semantic-to-Physical (S2P) mapping engine. Extensive evaluations demonstrate that PMG completely eradicates physical-layer and validation-layer gaming. By precisely isolating residual failures to semantic reinterpretations and auditor overreach, PMG marks a critical step toward genuine affordance grounding in automated architectural design.