AIMay 27

ResearchLoop: An Evidence-Gated Control Plane for AI-Assisted Research

arXiv:2605.2828249.8
AI Analysis

For researchers using AI tools, this work addresses the risk of unverifiable claims in AI-assisted publications by providing a structured protocol for evidence tracking.

ResearchLoop introduces an evidence-gated control plane for AI-assisted research that enforces claim verification through durable project state and transition rules. The system was evaluated across nine versions with multiple studies including a self-hosting case study and controlled task-suite ablations.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes