paper-with-me

홈 › Papers

HawkesLLM: Semantic Uncertainty Propagation in Agentic Text Simulation

2026-05-21 · Zewei Deng, Tinghan Ye, Liyan Xie 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.

📄 PDF Abstract BibTeX arXiv:2605.23043

Code (0)

등록된 구현이 없습니다.

Tasks

Text Generation

Similar Papers 제목 키워드 기반

Bayesian Uncertainty Propagation for Agentic RAG Pipelines: A Proof-of-Concept Study on Multi-Hop Question Answering

2026-07-01 · Louis Donaldson, Connor Walker, Koorosh Aslansefat, Yiannis Papadopoulos arxiv

Trustworthy deployment of Agentic Retrieval-Augmented Generation (RAG) systems requires mechanisms for estimating when multi-stage reasoning pipelines may fail. This paper presents an uncertainty-aware Agentic Retrieval-…

Multi-hop Question Answering

How to Correctly do Semantic Backpropagation on Language-based Agentic Systems

2024-12-04 · Wenyi Wang, Hisham A. Alyahya, Dylan R. Ashley, Oleg Serikov 외

Language-based agentic systems have shown great promise in recent years, transitioning from solving small-scale research problems to being deployed in challenging real-world tasks. However, optimizing these systems often…

GSM8K

UProp: Investigating the Uncertainty Propagation of LLMs in Multi-Step Agentic Decision-Making

2025-06-20 · Jinhao Duan, James Diffenderfer, Sandeep Madireddy, Tianlong Chen 외

As Large Language Models (LLMs) are integrated into safety-critical applications involving sequential decision-making in the real world, it is essential to know when to trust LLM decisions. Existing LLM Uncertainty Quant…

Decision MakingQuestion AnsweringSequential Decision MakingUncertainty Quantification

V-CAGE: Vision-Closed-Loop Agentic Generation Engine for Robotic Manipulation

2026-04-10 · Yaru Liu, Ao-bo Wang, Nanyang Ye arxiv

Scaling Vision-Language-Action (VLA) models requires massive datasets that are both semantically coherent and physically feasible. However, existing scene generation methods often lack context-awareness, making it diffic…

Scene Generation

Beyond Relevance: Bayesian Evidence Acquisition for Agentic Whole-Slide Image Reasoning

2026-08-06 · Bryan Wong, Xun Xu, Huazhu Fu, Nancy F. Chen 외 arxiv

Whole-slide image (WSI) reasoning requires an agent to sequentially acquire visual evidence before answering a diagnostic question. Existing training-free agentic frameworks formulate this process as iterative patch retr…