AINeutralarXiv – CS AI · 6h ago6/10
🧠
Constructing coherent spatial memory in LLM agents through graph rectification
Researchers introduce LLM-MapRepair, a framework enabling large language models to incrementally construct and repair topological navigation graphs from stepwise observations. The system addresses limitations of context-dependent spatial reasoning in LLMs by detecting and correcting structural inconsistencies, achieving 94.3% node recall and 88.2% edge recall on benchmark evaluations.
🏢 OpenAI🏢 Anthropic🧠 GPT-4