Enregistré dans:
Détails bibliographiques
Auteurs principaux: Xia, Yihan, Wang, Taotao
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2605.28282
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913168079454208
author Xia, Yihan
Wang, Taotao
author_facet Xia, Yihan
Wang, Taotao
contents AI-assisted research compresses ideation, implementation, evaluation, and manuscript writing into a single interactive loop. This compression is useful, but it also creates a publication risk: paper claims can become easier to state than to audit. We present ResearchLoop, an evidence-gated control plane for AI-assisted computational research. ResearchLoop treats research questions, task contracts, evidence objects, claim ledgers, closeouts, and paper bindings as durable project state, realized here as a repository-backed runtime. This technical report provides the complete protocol specification, state model, transition rules, claim-admission algorithm, and insight-compounding mechanism. It also reports the full experimental record spanning nine versions (V0--V9), including a self-hosting case study, a controlled task-suite study with component ablations, a mathematical olympiad evaluation, and a supplementary SciCode boundary experiment evaluated with the official generated-code harness. All artifacts, manifests, and verification reports are preserved in the project repository.
format Preprint
id arxiv_https___arxiv_org_abs_2605_28282
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ResearchLoop: An Evidence-Gated Control Plane for AI-Assisted Research
Xia, Yihan
Wang, Taotao
Artificial Intelligence
AI-assisted research compresses ideation, implementation, evaluation, and manuscript writing into a single interactive loop. This compression is useful, but it also creates a publication risk: paper claims can become easier to state than to audit. We present ResearchLoop, an evidence-gated control plane for AI-assisted computational research. ResearchLoop treats research questions, task contracts, evidence objects, claim ledgers, closeouts, and paper bindings as durable project state, realized here as a repository-backed runtime. This technical report provides the complete protocol specification, state model, transition rules, claim-admission algorithm, and insight-compounding mechanism. It also reports the full experimental record spanning nine versions (V0--V9), including a self-hosting case study, a controlled task-suite study with component ablations, a mathematical olympiad evaluation, and a supplementary SciCode boundary experiment evaluated with the official generated-code harness. All artifacts, manifests, and verification reports are preserved in the project repository.
title ResearchLoop: An Evidence-Gated Control Plane for AI-Assisted Research
topic Artificial Intelligence
url https://arxiv.org/abs/2605.28282