Skip to main content
Search

# Foundation Model Agents

1 related articles

Subscribe to updates
  1. After step-by-step exploration of 20×20 symbolic maps, node-sequence memory lifts GPT-5.2 total accuracy from 43.89% to 77.78%, while further model versions and parameter scale add little spatial reasoning

    The study proposes an interactive evaluation framework in which foundation model agents incrementally explore partially observable 20×20 grid-based symbolic maps of roads, intersections, and POIs, then probes spatial understanding with direction judgment, distance estimation, proximity judgment, POI density recognition, and path planning; by systematically varying exploration strategies, memory representations, and reasoning prompts, it finds that exploration has limited impact on final reasoning accuracy, that memory representation (especially node-sequence and graph memory) is central, that structured memory and advanced prompts repair reasoning failures through explicit spatial reconstruction, and that spatial reasoning performance saturates across model versions and scales beyond a cap

You’re all caught up