HawkesLLM: Semantic Uncertainty Propagation in Agentic Text Simulation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Deng, Zewei, Ye, Tinghan, Xie, Liyan
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913154363031552
author Deng, Zewei
Ye, Tinghan
Xie, Liyan
author_facet Deng, Zewei
Ye, Tinghan
Xie, Liyan
contents Agentic text-simulation systems write in sequence, with each item becoming possible context for later steps. That makes uncertainty path-dependent: an early ambiguity can affect later outputs. This paper studies this problem with HawkesLLM, a framework that separates temporal influence modeling from text generation. We represent the cascade as a network whose nodes are text-generating agents. A multivariate Hawkes process models how these nodes activate over time and which earlier node outputs should influence later prompts. A language model then writes each new event from the compact memory selected by this temporal model. We evaluate the framework on a held-out Global Database of Events, Language, and Tone (GDELT) news-cascade case study. The diagnostics track semantic alignment with local held-out references and separate local drift from global drift. In this setting, HawkesLLM improves late-stage semantic alignment under a compact prompt-memory budget.
format Preprint
id arxiv_https___arxiv_org_abs_2605_23043
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle HawkesLLM: Semantic Uncertainty Propagation in Agentic Text Simulation
Deng, Zewei
Ye, Tinghan
Xie, Liyan
Computation and Language
Machine Learning
Agentic text-simulation systems write in sequence, with each item becoming possible context for later steps. That makes uncertainty path-dependent: an early ambiguity can affect later outputs. This paper studies this problem with HawkesLLM, a framework that separates temporal influence modeling from text generation. We represent the cascade as a network whose nodes are text-generating agents. A multivariate Hawkes process models how these nodes activate over time and which earlier node outputs should influence later prompts. A language model then writes each new event from the compact memory selected by this temporal model. We evaluate the framework on a held-out Global Database of Events, Language, and Tone (GDELT) news-cascade case study. The diagnostics track semantic alignment with local held-out references and separate local drift from global drift. In this setting, HawkesLLM improves late-stage semantic alignment under a compact prompt-memory budget.
title HawkesLLM: Semantic Uncertainty Propagation in Agentic Text Simulation
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2605.23043