Skip to content
AI Atlas
PaperActive

Causal Past Logic for Runtime Verification of Distributed LLM Agent Workflows

arxiv.org/abs/2605.20923

quality89

Updated 2 h ago · first seen 12 Sept 2026

paper_01M29X3596NV4CZK99916PHDXX

Published
12 Sept 2026
T1 · 2 h ago
arXiv
2605.20923
T1 · 2 h ago
Category
cs.LO
T1 · 2 h ago

Abstract

-cross Abstract: We study runtime monitoring for distributed LLM-agent workflows. 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), an adaptation of PT-DTL to guards in if-constructs 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 owner evaluates the guard online to select the next branch or loop step. We adapt the knowledge-vector monitor to ZipperGen and prove that the locally computed monitor value coincides with the denotational semantics of the guard at the current event.

Authors 1

Benedikt Bollig

Specification

Official page

Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

Arxiv announce type
replace

Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

arXiv id
2605.20923

Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

Categories
cs.AI, cs.LO, cs.PL

Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

PDF

Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

Primary category
cs.LO

Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

Published
12 Sept 2026

Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

9

Source tiers

T19

Freshest observation

2 h ago

Conflicts

None