Article

LogLook: Execution-Log Memory for Frontier-Model Robot Planners

LogLook proposes an execution-log-style memory that lets frontier vision-language model planners record executed actions and earlier notes, and selectively review image frames based on expected changes. With the benchmark's built-in motion planner, it matches the success rate of note-only memory while using 43% fewer tokens and less than half the images, and it causes notably fewer failures due to memory or observation errors; under direct control, it solves 93.5% of the RoboMME test set.

Part of the event: LogLook proposes execution-log-style memory for robot planners

This page provides a summary and source link only.