Metraipolis › archive › dc_237a5d8bb855

PRIME: Predictive Routing of Interventions by Modeling Effects for Scientific Ideation — arXiv:2611.03055

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.03055
License (as archived): CC0-1.0
Archived: 2026-11-03T10:54:20.806Z
SHA-256 of the archived text: d9713679ca9ed2cf3563facf7d289893fc816f6ecb41a65d49f8be52a9ea0e3f
Stable URL of this page: https://metraipolis.com/documento/dc_237a5d8bb855

How to cite

PRIME: Predictive Routing of Interventions by Modeling Effects for Scientific Ideation — arXiv:2611.03055 — arXiv (en), https://arxiv.org/abs/2611.03055 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_237a5d8bb855 (Metraipolis archive dc_237a5d8bb855, sha256 d9713679ca9ed2cf3563facf7d289893fc816f6ecb41a65d49f8be52a9ea0e3f)

BibTeX

@misc{dc237a5d8bb855,
  title = {PRIME: Predictive Routing of Interventions by Modeling Effects for Scientific Ideation — arXiv:2611.03055},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03055},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_237a5d8bb855; sha256 d9713679ca9ed2cf3563facf7d289893fc816f6ecb41a65d49f8be52a9ea0e3f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03055. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Feedback-driven iteration is widely used to improve LLM-generated scientific ideas, but existing systems either leave revision decisions implicit in generation, align revisions with feedback-localized weaknesses, or restrict action selection to system-specific operations. This is problematic because problems, hypotheses, and solutions are interdependent: the location where a weakness manifests does not itself determine the revision scope that will produce a better successor. We term this phenomenon diagnosis-intervention mismatch. We introduce Predictive Routing of Interventions by Modeling Effects (PRIME), a plug-and-play feedback-to-revision decision layer for existing scientific ideators. PRIME operates in three stages: (1) Structural Attribution interprets feedback over the problem-hypothesis-solution structure without fixing a revision target; (2) Counterfactual Routing constructs alternative scope-conditioned interventions and compares their projected successor utility and risks through lightweight rollouts; and (3) Intervention Execution compiles the selected intervention into an ordered generator-facing plan with semantic actions, preservation constraints, and dependency requirements for successor generation. We validate diagnosis intervention mismatch on 112 human-annotated idea-feedback pairs. Across four benchmarks, two ideators, and fixed- and open-problem settings, PRIME improves successor quality and routing reliability over strong baselines; removing counterfactual routing reduces quality from 3.463 to 1.960 and increases route regret from 0.426 to 1.929, confirming cross-scope effect modeling as the primary source of its gains.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.03055 — 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 2026-11-03T10:49:38.405Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).