Reading Stability from Traces: Certifying Multi-Agent LLM Loops with Unknown Delay from Short, Contaminated Execution Logs

Third paper in the series "Control Theory for AI Systems". Language-model agents that correct a shared state form a delayed feedback loop; prior work gave its exact stability boundary and showed that prompting does not control the agents' gain. This paper shows how to certify the stability of a running loop from a short execution log, with the delay unknown. The certifier combines a scale-invariant weighted-median estimator, a bounded delay-selection loss and a bootstrap that re-selects the delay, with five proven guarantees. It is evaluated on 2,880 synthetic traces, a model-mismatch study, 54 recorded runs of gpt-4o-mini agents and 4,050 production latencies, against least squares, Huber regression, ARX and delay-blind regression. The archive contains the LaTeX source, all code, data and raw outputs, the data-collection scripts, and a test suite (177 tests) that checks each proposition numerically, regenerates every number and table of the paper, and links every number typed in the text to the code or data. A mutation test plants 15 realistic bugs and verifies that the tests catch all of them.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-17
DOI
https://doi.org/10.5281/zenodo.24322429
Primary Topic
Stability and Control of Uncertain Systems
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Reading Stability from Traces: Certifying Multi-Agent LLM Loops with Unknown Delay from Short, Contaminated Execution Logs

Mohamed EID
3 links
Zenodo (CERN European Organization for Nuclear Research)
Stability and Control of Uncertain Systems
preprint

Reading Stability from Traces: Certifying Multi-Agent LLM Loops with Unknown Delay from Short, Contaminated Execution Logs

Mohamed EID
preprint en

Abstract

Third paper in the series "Control Theory for AI Systems". Language-model agents that correct a shared state form a delayed feedback loop; prior work gave its exact stability boundary and showed that prompting does not control the agents' gain. This paper shows how to certify the stability of a running loop from a short execution log, with the delay unknown. The certifier combines a scale-invariant weighted-median estimator, a bounded delay-selection loss and a bootstrap that re-selects the delay, with five proven guarantees. It is evaluated on 2,880 synthetic traces, a model-mismatch study, 54 recorded runs of gpt-4o-mini agents and 4,050 production latencies, against least squares, Huber regression, ARX and delay-blind regression. The archive contains the LaTeX source, all code, data and raw outputs, the data-collection scripts, and a test suite (177 tests) that checks each proposition numerically, regenerates every number and table of the paper, and links every number typed in the text to the code or data. A mutation test plants 15 realistic bugs and verifies that the tests catch all of them.

Zenodo (CERN European Organization for Nuclear Research)
Stability and Control of Uncertain Systems
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon