Librarian Agents: Anticipatory Filesystem Construction via Reinforcement Learning

Reasoning over long document contexts remains a challenge for large language models (LLMs). Standard retrieval methods are inherently reactive, bottlenecking agents with complex, cross-document reasoning at inference time. Existing approaches that pre-compute corpus structure, such as knowledge graphs, often fall short due to their reliance on rigid heuristics such as identifying interdocument relationships via named entity recognition. We propose an anticipatory approach to memory: proactively reorganizing unstructured document corpora to efficiently serve diverse future queries. This pre-computation synthesizes and restructures information within documents in advance, significantly improving an answering agent’s downstream performance and inference efficiency. While agentic scaffolds (e.g., Claude Code) are heavily trained to navigate and extend filesystems while solving the task currently in front of them, they do not pre-construct one in anticipation of future queries, as our approach aims to do. We introduce Librarian Agents, a novel framework that restructures unstructured corpora into file-based memories arranged around the operations that LLM agents already perform well, such as reading summaries and following links. The Librarian Agents framework is trained to maximize downstream success rate via end-to-end reinforcement learning. Empirically, Librarian Agents improves accuracy over the best performing baseline by 77% relative improvement on BrowseComp+ and additionally generalizes to out-of-distribution corpora such as BRIGHT.