Watchdogs and Oracles: Runtime Verification Meets Large Language Models for Autonomous Systems
This vision paper addresses the problem of dependable autonomy for systems with learning-enabled components, but it is incremental as it builds on existing RV and LLM methods without presenting new empirical results.
The paper tackles the challenge of ensuring safety in autonomous systems with learning components by proposing a symbiotic integration of runtime verification (RV) and large language models (LLMs), where RV acts as a guardrail for LLMs and LLMs enhance RV capabilities like specification capture and reasoning.
Assuring the safety and trustworthiness of autonomous systems is particularly difficult when learning-enabled components and open environments are involved. Formal methods provide strong guarantees but depend on complete models and static assumptions. Runtime verification (RV) complements them by monitoring executions at run time and, in its predictive variants, by anticipating potential violations. Large language models (LLMs), meanwhile, excel at translating natural language into formal artefacts and recognising patterns in data, yet they remain error-prone and lack formal guarantees. This vision paper argues for a symbiotic integration of RV and LLMs. RV can serve as a guardrail for LLM-driven autonomy, while LLMs can extend RV by assisting specification capture, supporting anticipatory reasoning, and helping to handle uncertainty. We outline how this mutual reinforcement differs from existing surveys and roadmaps, discuss challenges and certification implications, and identify future research directions towards dependable autonomy.