π€ AI Summary
This work addresses the challenge of runtime monitoring in distributed large language model (LLM) agent workflows, where asynchronous execution limits visibility into event causality, rendering traditional sequential logs inadequate. To overcome this, the paper integrates Causal Past Logic (CPL) into the ZipperGen framework by embedding it within the control flow of the coordination language, serving as source-level guards for conditional and loop constructs to enable real-time verification based on causal visibility. A vector-clock-based monitor, combined with a latest-value view, evaluates CPL formulas online while ensuring consistency between local computations and denotational semantics. This approach supports cross-lifeline queries over causally visible events and variables, significantly enhancing the accuracy and efficiency of runtime verification in distributed LLM agent workflows and guaranteeing that decisions rely solely on causally reachable historical information.
π Abstract
Distributed LLM agent workflows should not be monitored as if they produced a single sequential log. In an asynchronous execution, a decision can only depend on events that are causally visible to the lifeline that makes it: an event that appears earlier in some log may still be unknown locally. We extend the ZipperGen agent-workflow framework with Causal Past Logic (CPL), a small past-time temporal logic for guards in conditionals and while loops. In addition to standard past-time modalities such as previous and since, a guard can inspect the latest causally visible event of another lifeline and selected variables stored there. The formula is a source-level guard: it is evaluated online by the owner lifeline and can influence control flow at runtime. We give a vector-clock monitor with latest-value views and prove that the locally computed monitor value coincides with the denotational semantics of the guard at the current event. Thus runtime verification becomes part of the coordination language itself, rather than a post-hoc check over an execution log.