Metraipolis › archive › dc_6125445e85be

IRAH: Hierarchical Agentic Tree Search for Retrieval Pipeline Optimization — arXiv:2610.30167

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.30167
License (as archived)
CC0-1.0
Archived
2026-10-25T20:54:38.074Z
SHA-256 of the archived text
6ac6e261865a687df412c43f6b44f3ac0bd55c1316625615cb996f53a3356289
Stable URL of this page
https://metraipolis.com/documento/dc_6125445e85be

How to cite

IRAH: Hierarchical Agentic Tree Search for Retrieval Pipeline Optimization — arXiv:2610.30167 — arXiv (en), https://arxiv.org/abs/2610.30167 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6125445e85be (Metraipolis archive dc_6125445e85be, sha256 6ac6e261865a687df412c43f6b44f3ac0bd55c1316625615cb996f53a3356289)
BibTeX
@misc{dc6125445e85be,
  title = {IRAH: Hierarchical Agentic Tree Search for Retrieval Pipeline Optimization — arXiv:2610.30167},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.30167},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6125445e85be; sha256 6ac6e261865a687df412c43f6b44f3ac0bd55c1316625615cb996f53a3356289},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.30167. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Optimizing Information Retrieval (IR) pipelines for Retrieval-Augmented Generation (RAG) requires jointly selecting structural components and numerical hyperparameters under limited evaluation budgets. We introduce the Information Retrieval Agentic Harness (IRAH), which combines Language Agent Tree Search for IR (LATS-IR) with offline meta-learned initialization. LATS-IR performs UCT-guided hierarchical search, first exploring macro-structural pipeline choices and then refining numerical parameters, with natural-language reflections to guide subsequent mutations and provide inspectable search traces. We evaluate IRAH on three in-distribution benchmarks and one out of-distribution benchmark to assess generalization under distribution shift. Under the same meta-learned initialization, LATS-IR outperforms TPE on two of three in-distribution benchmarks, with gains of up to 6.4%, and remains competitive on the out-of-distribution benchmark. Across all four benchmarks, warm-started IRAH achieves the highest average held-out nDCG@10 (0.4816) and improves over its cold-start counterpart. These results establish IRAH as a competitive approach to retrieval pipeline optimization under constrained evaluation budgets.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Information Retrieval (cs.IR) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.30167 — 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 2026-10-25T20:47:56.957Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).