Tag
Microsoft introduces PEEK, a 1,024-token 'context map' that caches orientation knowledge for LLM agents, cutting redundant reasoning and achieving up to 34% accuracy gains with 93–145 fewer retries and 5.8× cost reduction.
PEEK introduces a context map as an orientation cache for LLM agents, enabling them to maintain persistent knowledge about external environments like code repositories. The system achieves 6.3-34.0% quality improvements at lower cost compared to baselines like RAG and ACE.
This paper introduces PEEK, a system that caches orientation knowledge about recurring external contexts as a context map, enabling LLM agents to reuse context knowledge across invocations and significantly improving efficiency and accuracy on long-context reasoning and information aggregation tasks.