Metraipolis › archive › dc_8a19bcea6312

The Fellowship of the Query: Learning Retrieval Actions — arXiv:2609.28653

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.28653
License (as archived)
CC0-1.0
Archived
2026-10-08T04:27:04.351Z
SHA-256 of the archived text
499be4d8661ca71346f9336f3cc37912d23a763961cfd4127d03246b72ba2e21
Stable URL of this page
https://metraipolis.com/documento/dc_8a19bcea6312

How to cite

The Fellowship of the Query: Learning Retrieval Actions — arXiv:2609.28653 — arXiv (en), https://arxiv.org/abs/2609.28653 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8a19bcea6312 (Metraipolis archive dc_8a19bcea6312, sha256 499be4d8661ca71346f9336f3cc37912d23a763961cfd4127d03246b72ba2e21)
BibTeX
@misc{dc8a19bcea6312,
  title = {The Fellowship of the Query: Learning Retrieval Actions — arXiv:2609.28653},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.28653},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8a19bcea6312; sha256 499be4d8661ca71346f9336f3cc37912d23a763961cfd4127d03246b72ba2e21},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28653. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Retrieval-augmented question answering requires control decisions about when to decompose a question, search, reformulate, extract evidence, synthesize facts, verify progress, and stop. We study whether trajectory fine-tuning can improve small language models (SLMs) as next-action controllers. We additionally evaluate a low-resource setting in which a single SLM serves as both the controller and the final-answer generator. From accepted teacher search traces, we build a seven-way action-prediction task, where the model predicts the next structured teacher action from the current trajectory state, and evaluate LoRA-supervised fine-tuning across SLMs and xSLMs as controllers. On 1,646 held-out action examples, Granite 4.1 3B trained on 13,194 actions reaches macro-F1 0.6536, compared with 0.1736 for zero-shot prompting of the same model and 0.5399 for a TF-IDF logistic-regression baseline. In an end-to-end controller/generator swap evaluation over 149 held-out trajectories, using the fine-tuned model for both roles improves Exact Match from 0.7530 to 0.7946 and token F1 from 0.7783 to 0.8295 compared with using the base model as both controller and generator. The cross-role conditions show that the fine-tuned controller increases evidence-fact recording when the generator is fixed, while controller-only final-answer gains are not statistically clear. Overall, trajectory supervision improves action prediction and evidence-recording behaviour in this evaluated pipeline. Code is available at this https URL

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.AI).
Categorie arXiv: Information Retrieval (cs.IR) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.28653 — 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 2026-10-08T03:50:57.942Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).