Neuro-Symbolic Multi-Agent System for Requirements Reuse
A new neuro-symbolic multi-agent system re-conceptualizes requirements reuse as a model-driven elicitation process. The system uses a large language model (LLM) as a non-deterministic heuristic to traverse a deterministic domain model represented by a formal OOMRAM requirement lattice. A deterministic symbolic validator enforces structural constraints, eliminating hallucinated requirement combinations. This approach addresses the limitations of the Object-Oriented Method for Requirements Authoring and Management (OOMRAM), which relies on exact identifier matching and rigid templates. The system prevents LLMs from generating structurally invalid or inconsistent requirement combinations.
Key facts
- arXiv:2605.01562v1
- OOMRAM is a requirements reuse framework
- OOMRAM relies on exact identifier matching and rigid templates
- LLMs offer flexibility but risk generating invalid requirement combinations
- The neuro-symbolic system re-conceptualizes requirements reuse as Model-Driven Elicitation
- An LLM serves as a non-deterministic heuristic
- A deterministic domain model is represented by a formal OOMRAM requirement lattice
- A deterministic symbolic validator enforces structural constraints
Entities
—