Metraipolis › archive › dc_bd566252d325
Librarian Agents: Training LLMs to Curate Long-Context Workspaces that Anticipate Future Queries — arXiv:2610.22273
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.22273
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T09:31:08.474Z
- SHA-256 of the archived text
c3d692b63df033e11ad4d43d7f28bb4b78c0078f1610193d501da388f85b7853- Stable URL of this page
https://metraipolis.com/documento/dc_bd566252d325
How to cite
Librarian Agents: Training LLMs to Curate Long-Context Workspaces that Anticipate Future Queries — arXiv:2610.22273 — arXiv (en), https://arxiv.org/abs/2610.22273 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bd566252d325 (Metraipolis archive dc_bd566252d325, sha256 c3d692b63df033e11ad4d43d7f28bb4b78c0078f1610193d501da388f85b7853)
BibTeX
@misc{dcbd566252d325,
title = {Librarian Agents: Training LLMs to Curate Long-Context Workspaces that Anticipate Future Queries — arXiv:2610.22273},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.22273},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bd566252d325; sha256 c3d692b63df033e11ad4d43d7f28bb4b78c0078f1610193d501da388f85b7853},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22273. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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, while precomputed structures like knowledge graphs often fall short because they rely on rigid heuristics. Instead, can we allow agents to perform anticipatory directed curation: learning to proactively reorganize unstructured corpora prior to inference to efficiently serve diverse future queries. We build on a key asymmetry in modern agentic harnesses (e.g., Claude Code): while LLM agents are adept at navigating existing filesystems to solve an immediate task, they are rarely trained to construct reusable workspaces for future use. To instantiate this capability, we introduce Librarian Agents, a framework in which a builder agent transforms raw documents into a hierarchical filesystem of synthetic files and reference links, which forms a workspace tailored for a downstream answering agent. We formulate workspace construction as a Markov decision process and optimize the builder policy via reinforcement learning to directly maximize downstream answering accuracy. Empirically, Librarian Agents outperforms the strongest retrieval and precomputation baselines by 33 percentage points on BrowseComp-Plus, amortizes upfront construction costs across repeated queries, and generalizes zero-shot to unseen domains on BRIGHT with a 31-point average accuracy improvement. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.22273 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T08:44:18.047Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).