When Does Experience Memory Help Closed-Loop LLM Driving Agents? A Controlled Evaluation with Resampled Warmup Pools, Token-Matched Fillers, and Audited Baselines | Radar arXiv · portela.dev
PAPER / ARXIV:2610.27714
When Does Experience Memory Help Closed-Loop LLM Driving Agents? A Controlled Evaluation with Resampled Warmup Pools, Token-Matched Fillers, and Audited Baselines
Pan Wang , Siwei Song , Hui Ji , Siqi Cao , Heng Yu , Zhijian Liu , Huanrui Yang , Yingyan Celine Lin , Beidi Chen , Mohit Bansal , Xiaoming Liu , Pengfei Zhou , Ming-Hsuan Yang , Tianlong Chen , Jingtong Hu
Marco S. Tayar , Felipe Tommaselli , Gianluca Capezutto , Pedro Antonio Rabelo Saraiva , Pedro H. V. de Freitas , Lucas Kido , Guilherme Sonego , Ricardo V. Godoy , Marcelo Becker