Tag
This paper introduces HASSUM, a semantic-uncertainty-guided orchestration framework for hierarchical multi-agent systems that uses semantic entropy and density to improve reliability and adapt decision-making.
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.