Tag
This paper introduces MemoryForge, a framework for synthesizing lifelong autobiographical memory from brief target personas to enable frozen LLMs to exhibit more human-like behaviors in role-play and user-simulation, outperforming descriptive conditioning baselines.
Introduces EvolvingWorld, an open-schema framework and benchmark for co-evolving role-play agents and world models in interactive literary worlds, enabling long-horizon simulation with persistent character and world state updates.