Uncertainty-Aware Sequential Decision Rules for Event-Triggered LLM Invocation in Streaming Systems
A new framework treats the decision of when to invoke a large language model (LLM) in streaming inference as a risk-based sequential stopping problem. The authors prove six theoretical results covering minimum inter-event times, optimality of threshold policies, and regret bounds. Empirical tests on turbofan degradation data show that anomaly-score-driven risk functions outperform baseline methods by an order of magnitude in Pareto AUC.
-->
[Submitted on 27 Jun 2026]
Title:Uncertainty-Aware Sequential Decision Rules for Event-Triggered LLM Invocation in Streaming Systems
View a PDF of the paper titled Uncertainty-Aware Sequential Decision Rules for Event-Triggered LLM Invocation in Streaming Systems, by Zhaohui Wang
View PDF HTML (experimental)
Abstract:Streaming inference pipelines increasingly pair lightweight fast models with Large Language Models (LLMs) that provide rich semantic understanding at substantial cost. The central question of when to invoke the LLM has received limited formal treatment. We cast this as a risk-based sequential stopping problem, where a trigger policy fires when a risk functional over the observation history exceeds a threshold. Within this framework, we prove six results: a minimum inter-event time bound excluding trigger chattering; optimality of threshold policies via smooth pasting; approximate SPRT guarantees under estimated parameters; O(sqrt(T log T)) regret for stationary streams, extending to O(sqrt((C_T + 1) T log T)) under C_T changepoints; O(1/sqrt(T)) convergence of online gradient descent for adaptive thresholds; and a calibration-to-miss-rate transfer inequality. Several classical trigger families, including event-triggered, optimal stopping, SPRT, CUSUM, and Bayesian triggers, can be expressed as special cases of this framework. On turbofan degradation data (CMAPSS) with real LLM calls, we empirically verify the theoretical assumptions, ablate the risk function design, compare against six baselines including a RouteLLM-style router and contextual bandits, and analyze cost sensitivity and LLM failure modes. The results confirm sublinear regret, with alpha = 0.75 under our rubric; and that anomaly-score-driven risk functions dominate alternatives by roughly an order of magnitude on the Pareto AUC.
Comments: 18 pages, 5 figures. Accepted to the ECML PKDD 2026 Research Track
Subjects:
Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Machine Learning (stat.ML)
Cite as: arXiv:2607.13048 [cs.LG]
(or arXiv:2607.13048v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2607.13048
arXiv-issued DOI via DataCite
Submission history
From: Zhaohui Wang [view email] [v1] Sat, 27 Jun 2026 08:18:09 UTC (906 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Uncertainty-Aware Sequential Decision Rules for Event-Triggered LLM Invocation in Streaming Systems, by Zhaohui Wang
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.LG
new | recent | 2026-07
Change to browse by:
cs cs.AI stat stat.ML
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
IArxiv recommender toggle
IArxiv Recommender (What is IArxiv?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)