Think Like an Engineer: A Neuro-Symbolic Collaboration Agent for Generative Software Requirements Elicitation and Self-Review
🤖 AI Summary
To address the ambiguity in causal logic and unclear relationships between preconditions and behavioral actions in natural language requirements articulated by non-expert users, this paper proposes a neuro-symbolic collaborative architecture. Its core innovations include a Causal Effect Graph (CEG) embedding mechanism and a feature-tree-based hierarchical parsing method, enabling the construction of a self-repairing CEG that explicitly models causal dependencies in requirements. The architecture supports automated requirement acquisition, logical self-validation, and Gherkin scenario consistency optimization. Experimental evaluation on the custom-built RGPair dataset demonstrates an 87% requirement coverage rate and a 51.88% improvement in scenario diversity, significantly enhancing the completeness, logical consistency, and verifiability of generated system behaviors.
Application Category
📝 Abstract
The vision of End-User Software Engineering (EUSE) is to empower non-professional users with full control over the software development lifecycle. It aims to enable users to drive generative software development using only natural language requirements. However, since end-users often lack knowledge of software engineering, their requirement descriptions are frequently ambiguous, raising significant challenges to generative software development. Although existing approaches utilize structured languages like Gherkin to clarify user narratives, they still struggle to express the causal logic between preconditions and behavior actions. This paper introduces RequireCEG, a requirement elicitation and self-review agent that embeds causal-effect graphs (CEGs) in a neuro-symbolic collaboration architecture. RequireCEG first uses a feature tree to analyze user narratives hierarchically, clearly defining the scope of software components and their system behavior requirements. Next, it constructs the self-healing CEGs based on the elicited requirements, capturing the causal relationships between atomic preconditions and behavioral actions. Finally, the constructed CEGs are used to review and optimize Gherkin scenarios, ensuring consistency between the generated Gherkin requirements and the system behavior requirements elicited from user narratives. To evaluate our method, we created the RGPair benchmark dataset and conducted extensive experiments. It achieves an 87% coverage rate and raises diversity by 51.88%.
Problem
Research questions and friction points this paper is trying to address.
Addresses ambiguity in end-user natural language software requirements
Captures causal logic between preconditions and behavioral actions
Ensures consistency between generated and elicited system requirements
Innovation
Methods, ideas, or system contributions that make the work stand out.
Uses neuro-symbolic collaboration for requirement elicitation
Embeds causal-effect graphs to clarify logic
Self-healing CEGs optimize Gherkin scenarios
🔎 Similar Papers
No similar papers found.
