# HawkesLLM: Semantic Uncertainty Propagation in Agentic Text Simulation

arXiv: https://arxiv.org/abs/2605.23043 · HTML: https://mlsanity.com/paper/2605.23043/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 12 of its 27 references that are in the map.
- First posted on arXiv 21 May 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 12 of 12)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models](https://mlsanity.com/paper/2305.19187/) (2023)
- [Decoding Echo Chambers: LLM-Powered Simulations Revealing Polarization in Social Networks](https://mlsanity.com/paper/2409.19338/) (2024)
- [Towards Uncertainty-Aware Language Agent](https://mlsanity.com/paper/2401.14016/) (2024)
- [Know When To Stop: A Study of Semantic Drift in Text Generation](https://mlsanity.com/paper/2404.05411/) (2024)
- [A Tutorial on Hawkes Processes for Events in Social Media](https://mlsanity.com/paper/1708.06401/) (2017)
- [LLM as a Broken Telephone: Iterative Generation Distorts Information](https://mlsanity.com/paper/2502.20258/) (2025)
- [TPP-LLM: Modeling Temporal Point Processes by Efficiently Fine-Tuning Large Language Models](https://mlsanity.com/paper/2410.02062/) (2024)
- [Rhythm of Opinion: A Hawkes-Graph Framework for Dynamic Propagation Analysis](https://mlsanity.com/paper/2504.15072/) (2025)
- [Advances in Temporal Point Processes: Bayesian, Neural, and LLM Approaches](https://mlsanity.com/paper/2501.14291/) (2025)

## Abstract (arXiv)

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.