Metraipolis › archive › dc_c8fa24c8ccbf

Personalized Deep Research Query Refinement with Graph-Scaffolded Evidence Grounding — arXiv:2608.05876

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.05876
License (as archived): CC0-1.0
Archived: 2026-10-25T21:31:13.249Z
SHA-256 of the archived text: 0556f8c1e25e22d795552ffb6f13090699937a847a1f96e658b2d175334a6ff6
Stable URL of this page: https://metraipolis.com/documento/dc_c8fa24c8ccbf

How to cite

Personalized Deep Research Query Refinement with Graph-Scaffolded Evidence Grounding — arXiv:2608.05876 — arXiv (en), https://arxiv.org/abs/2608.05876 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c8fa24c8ccbf (Metraipolis archive dc_c8fa24c8ccbf, sha256 0556f8c1e25e22d795552ffb6f13090699937a847a1f96e658b2d175334a6ff6)

BibTeX

@misc{dcc8fa24c8ccbf,
  title = {Personalized Deep Research Query Refinement with Graph-Scaffolded Evidence Grounding — arXiv:2608.05876},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.05876},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c8fa24c8ccbf; sha256 0556f8c1e25e22d795552ffb6f13090699937a847a1f96e658b2d175334a6ff6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05876. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

User requests serve as research specifications for deep research agents, shaping what evidence to seek and how to synthesize it. In personalized deep research, these specifications must additionally reflect user goals, constraints, preferences, and evaluation criteria. User context can be incorporated either within the deep research pipeline or into the research specification provided as its input. We focus on the latter, refining the user request into a personalized research specification before passing it to an unchanged deep research agent. This requires resolving three coupled decisions: which framing factors are relevant, whether the available user context sufficiently supports them, and whether to retrieve user memory, ask the user, or stop and refine the query. For training, G-STEER organizes framing factors as elicitation targets in an Intent Elicitation Graph that captures their dependencies. It learns a clarification policy from graph-scaffolded trajectories spanning diverse factor dependencies and evidence conditions. The policy produces a refined query while balancing target coverage against the costs of evidence acquisition. Experiments show that G-STEER achieves the strongest overall weighted target coverage and the highest downstream report personalization across both evaluated DRAs, while asking roughly one third as many user questions as a strong clarification baseline.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CL).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.05876 — 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 2026-10-25T21:24:38.267Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).