Librarian Agents: Training LLMs to Curate Long-Context Workspaces that Anticipate Future Queries

Key points

The authors built the Librarian Agents framework, in which a builder agent transforms raw documents into a hierarchical filesystem of synthetic files and reference links.
They formalize filesystem workspace construction as an MDP and optimize the builder policy directly with reinforcement learning to raise answering accuracy.
On BrowseComp-Plus it outperforms the strongest baseline by 33 percentage points on average and reaches 0.77 accuracy with the Gemini 3.1 Flash Lite answering agent.
On the unseen BRIGHT domains it scores pass@1 52% and pass@3 67% zero-shot.
Construction cost is amortized across repeated queries, with accuracy of 0.64 versus 0.24 for the base builder on reuse.
As a limitation, compression may discard details needed for needle-in-a-haystack tasks, so the system keeps reference links for fallback access.

External research summaries. These are not HDATF publications or measured product results.