A DbC Inspired Neurosymbolic Layer for Trustworthy Agent Design

TL;DR

This paper introduces a contract layer inspired by Design by Contract to enhance trustworthiness in Large Language Models by ensuring semantic and type compliance through probabilistic validation.

Contribution

It adapts DbC principles to LLMs, creating a contract layer that enforces semantic and type requirements, improving verifiability and functional equivalence.

Findings

Contract layer improves LLM reliability

Probabilistic validation ensures compliance

Agents satisfying same contracts are functionally equivalent

Abstract

Generative models, particularly Large Language Models (LLMs), produce fluent outputs yet lack verifiable guarantees. We adapt Design by Contract (DbC) and type-theoretic principles to introduce a contract layer that mediates every LLM call. Contracts stipulate semantic and type requirements on inputs and outputs, coupled with probabilistic remediation to steer generation toward compliance. The layer exposes the dual view of LLMs as semantic parsers and probabilistic black-box components. Contract satisfaction is probabilistic and semantic validation is operationally defined through programmer-specified conditions on well-typed data structures. More broadly, this work postulates that any two agents satisfying the same contracts are \emph{functionally equivalent} with respect to those contracts.