BOOKMARKS introduces searchable bookmarks as reusable answers to storyline questions, enabling active initialization and passive synchronization for more consistent role-playing agent memory than recurrent summarization.
arXiv preprint arXiv:2503.23512 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Authors propose a new framework for automated LLM creativity evaluation that separates measurement from the task, using semantic entropy and multi-agent judges, validated on problem-solving, research ideation, and creative writing domains.
citing papers explorer
-
BOOKMARKS: Efficient Active Storyline Memory for Role-playing
BOOKMARKS introduces searchable bookmarks as reusable answers to storyline questions, enabling active initialization and passive synchronization for more consistent role-playing agent memory than recurrent summarization.
-
Automated Creativity Evaluation of Language Models Across Open-Ended Tasks
Authors propose a new framework for automated LLM creativity evaluation that separates measurement from the task, using semantic entropy and multi-agent judges, validated on problem-solving, research ideation, and creative writing domains.