The field of artificial intelligence is moving towards more sophisticated understanding and reasoning of complex narratives, leveraging advances in large language models and multi-agent systems. Recent developments have focused on improving the ability of models to extract and analyze narrative arcs, as well as to reason over graphs and long-range contexts. Notably, researchers are exploring the use of memory-centric approaches, combining AI-driven memory processing with human expertise, to enhance narrative comprehension. Additionally, symmetry-aware training methods and multi-head transformers are being developed to improve the efficiency and effectiveness of automated planning and multi-step reasoning tasks. Overall, the field is shifting towards more integrated and dynamic approaches to narrative understanding and reasoning, with a focus on combining different techniques and modalities to achieve more human-like comprehension and problem-solving abilities. Noteworthy papers include: Narrative Memory in Machines, which introduces a multi-agent system for extracting and analyzing narrative arcs, and ComoRAG, which proposes a cognitive-inspired memory-organized approach for stateful long narrative reasoning.