mlsanityData to 14 Oct 2026

HawkesLLM: Semantic Uncertainty Propagation in Agentic Text Simulation

arXiv 2605.23043 ↗First posted 21 May 2026cs.CL stat.MLcited by 0

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

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.

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.

Builds on

12 of 27 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Towards Uncertainty-Aware Language Agent25 Jan

Other references · 11

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  3. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  4. 2023Generating with Confidence: Uncertainty Quantification for Black-box Large Language Modelscited by 293
  5. 2024Decoding Echo Chambers: LLM-Powered Simulations Revealing Polarization in Social Networkscited by 33
  6. 2024Know When To Stop: A Study of Semantic Drift in Text Generationcited by 18
  7. 2017A Tutorial on Hawkes Processes for Events in Social Mediacited by 15
  8. 2025LLM as a Broken Telephone: Iterative Generation Distorts Informationcited by 12
  9. 2024TPP-LLM: Modeling Temporal Point Processes by Efficiently Fine-Tuning Large Language Modelscited by 9
  10. 2025Rhythm of Opinion: A Hawkes-Graph Framework for Dynamic Propagation Analysiscited by 4
  11. 2025Advances in Temporal Point Processes: Bayesian, Neural, and LLM Approachescited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Uncertainty Quantification for LLM Agents: A Taxonomy, an Evaluation Protocol, and an Empirical Study
  2. 2024Predicting vs. Acting: A Trade-off Between World Modeling & Agent Modeling
  3. 2024BayesAgent: Bayesian Agentic Reasoning Under Uncertainty via Verbalized Probabilistic Graphical Modeling
  4. 2025ToolACE-MT: Non-Autoregressive Generation for Agentic Multi-Turn Interaction
  5. 2026Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities
  6. 2026WorldReasoner: Evaluating Whether Language Model Agents Forecast Events with Valid Reasoning
  7. 2026Bridging the Agent-World Gap: Text World Models for LLM-based Agents
  8. 2026Forking Fast: Efficiently Estimating Uncertainty Dynamics in Text Generation