Tag
This paper presents a Bayesian uncertainty propagation framework for Agentic RAG systems, evaluating it on multi-hop QA benchmarks with GPT models, showing promise for monitoring reliability in industrial decision support.
This paper introduces HawkesLLM, a framework that models semantic uncertainty propagation in multi-step agentic text simulations by combining a multivariate Hawkes process for temporal influence and memory selection with a language model for text generation. Evaluation on a GDELT news-cascade case study shows improved late-stage semantic alignment under compact prompt-memory constraints.