arXiv Artificial Intelligence

The Fellowship of the Query: Learning Retrieval Actions

1 hour ago 25.09.2026 07:00 👁 1 views
The Fellowship of the Query: Learning Retrieval Actions

Quick summary

arXiv:2609.28653v1 Announce Type: cross Abstract: 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 structu

Key takeaways

  • arXiv:2609.28653v1 Announce Type: cross Abstract: 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.

Why it matters

The value of this work lies as much in how it was tested as in the claim itself. Sample design, baselines, uncertainty and replication help separate a laboratory result from real-world impact.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗