RENDER: Controlling Reader-Facing Evidence in LLM Memory Evaluation
Source
Yuan Si, Simeng Han, Daming Li, Jialu Zhang
Author
Yuan Si, Simeng Han, Daming Li, Jialu Zhang
Date
Terms in this piece · Glossary
benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.
token budget — A cap on how many tokens a task, session, or agent run may consume — the practical control on both cost and how long an agent will grind.
Why it matters
How you render retrieved memory can swing accuracy by tens of points at a matched token budgetA cap on how many tokens a task, session, or agent run may consume — the practical control on both cost and how long an agent will grind.Full definition → — three models score 0% on formal typed ledger packets but 45-53% on the same facts as natural-language entries.
articleInter-dimension Dependence for Multi-Dimensional Evaluation of Open-Ended TextHaoyuan Li, Snigdha Chaturvedi
articleCompliance, Capability, and Conflict: Benchmarking Multimodal LLMs under System MessagesJuan Yeo, Geewook Kim
articleDoes It Render Everywhere? A Study of Cross-Environment Compatibility in MLLM-Generated WebpagesZiyun Guo, Jingyu Xiao, Yuqiang Sun, Yintong Huo