RESEARCH

FinPerMA: A Theory-Informed, Event-Grounded Personalized-Memory Benchmark for LLM Agents

ArXiv cs.AI · Thu, 06 Aug 2026 04:00:00 GMT

arXiv:2608.04095v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly used as personalized assistants in high-stakes domains such as financial advising, yet it remains unclear whether they can maintain and update an individualized user model over long

Read original source Discuss with SiiMON