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

• URL: http://arxiv.org/abs/2605.28282v1
• Date: Wed, 27 May 2026 10:29:00 GMT
• Title: ResearchLoop: An Evidence-Gated Control Plane for AI-Assisted Research
• Abstract summary: ResearchLoop is an evidence-gated control plane for AI-assisted computational research.<n>ResearchLoop treats research questions, task contracts, evidence objects, claim ledgers, closeouts, and paper bindings as durable project state.<n>This technical report provides the complete protocol specification, state model, transition rules, claim-admission algorithm, and insight-compounding mechanism.
• Score: 4.9833735627186435
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• CausalForge: A Formally Grounded, Self-Improving Agentic Framework for Automated Research in Causal Inference [17.447741518678374]
  CausalForge is a framework for automated theoretical research in causal inference.<n>It combines Causalean, a Lean library for causal inference, with CausalSmith, a self-improving agentic pipeline.
  arXiv  Detail & Related papers  (2026-07-24T17:32:35Z)
• SciForge: An AI-Native, Multimodal Workbench for Scientific Discovery [48.99744520105086]
  SciForge is a multimodal research-native AI workbench.<n>It reserves the graphical interface for human judgment while search, parsing, model routing, workflow execution, plotting, writing, and presentation generation run as modular agent-accessible services.
  arXiv  Detail & Related papers  (2026-07-17T15:13:03Z)
• FARS: A Fully Automated Research System Deployed at Scale [19.413175066072302]
  We present FARS (Fully Automated Research System), a fully automated AI-for-AI research system.<n> FARS autonomously generates and advances projects through ideation, planning, experimentation, and writing.<n>In its first public deployment, FARS produced 166 complete research papers spanning 67 fine-grained AI/ML topics.
  arXiv  Detail & Related papers  (2026-06-30T13:30:24Z)
• Review the Code, Not the Story: A Vision and Protocol for Code-First Peer Review [2.531440973296736]
  This vision and protocol paper proposes code-first peer review.<n>Authors submit executable research artifacts and minimal claim manifests.<n>A venue-controlled AI system builds the environment, executes experiments, audits code paths, maps claims to evidence, and generates a standardized Review Package for human reviewers.
  arXiv  Detail & Related papers  (2026-06-05T01:26:07Z)
• PAIRED: A Process-Anchored Framework for Transparent Reporting of AI Contributions in Scientific Research [0.7614628596146601]
  Existing frameworks for reporting AI contributions are uniformly output-oriented.<n>No current framework can distinguish between a researcher who originated a research direction and one who adopted a direction proposed by AI.
  arXiv  Detail & Related papers  (2026-05-23T01:10:56Z)
• Claw AI Lab: An Autonomous Multi-Agent Research Team [73.07229229907435]
  We present Claw AI Lab, a lab-native autonomous research platform.<n>Rather than centering the system around a single agent or a fixed serial workflow, we allow users to instantiate a full research team from one prompt.<n>Claw-Code Harness connects locals, datasets, and checkpoints to runnable experiments and feeds execution artifacts back into the research loop.
  arXiv  Detail & Related papers  (2026-05-21T16:02:53Z)
• AI for Auto-Research: Roadmap & User Guide [107.0834449839233]
  We present an end-to-end analysis of AI across the complete research lifecycle.<n>We identify a sharp, stage-dependent boundary between reliable assistance and unreliable autonomy.<n>We show that greater automation can obscure rather than eliminate failure modes.
  arXiv  Detail & Related papers  (2026-05-18T17:08:26Z)
• ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration [10.076972559007116]
  ARIS (Auto-Research-in-sleep) is an open-source research harness for autonomous research.<n>ARIS coordinates machine-learning research through cross-model adversarial collaboration.
  arXiv  Detail & Related papers  (2026-05-04T18:10:15Z)
• The Last Human-Written Paper: Agent-Native Research Artifacts [106.47848184955576]
  We introduce the Agent-Native Research Artifact (ARA), a protocol that replaces the narrative paper with a machine-executable research package.<n>Three mechanisms support the ecosystem: a Live Research Manager that captures decisions and dead ends during ordinary development; an ARA Compiler that translates legacy PDFs and repos into ARAs; and an ARA-native review system that automates objective checks so human reviewers can focus on significance, novelty, and taste.
  arXiv  Detail & Related papers  (2026-04-27T16:23:09Z)
• Inspectable AI for Science: A Research Object Approach to Generative AI Governance [35.790980610679384]
  This paper introduces AI as a Research Object (AI-RO)<n>Instead of debating whether AI is an author or merely a tool, we propose treating AI interactions as structured, inspectable components of the research process.
  arXiv  Detail & Related papers  (2026-04-13T10:13:20Z)
• ResearchPilot: A Local-First Multi-Agent System for Literature Synthesis and Related Work Drafting [3.272585676511349]
  ResearchPilot is an open-source, self-hostable multi-agent system for literature-review assistance.<n>Given a natural-language research question, it retrieves papers from Semantic Scholar and arXiv.<n>It extracts structured findings from paper abstracts, synthesizes cross-paper patterns, and drafts a citation-aware-work section.
  arXiv  Detail & Related papers  (2026-03-15T22:02:59Z)
• DeepSynth-Eval: Objectively Evaluating Information Consolidation in Deep Survey Writing [53.85037373860246]
  We introduce Deep Synth-Eval, a benchmark designed to objectively evaluate information consolidation capabilities.<n>We propose a fine-grained evaluation protocol using General Checklists (for factual coverage) and Constraint Checklists (for structural organization)<n>Our results demonstrate that agentic plan-and-write significantly outperform single-turn generation.
  arXiv  Detail & Related papers  (2026-01-07T03:07:52Z)
• OpenNovelty: An LLM-powered Agentic System for Verifiable Scholarly Novelty Assessment [63.662126457336534]
  OpenNovelty is an agentic system for transparent, evidence-based novelty analysis.<n>It grounds all assessments in retrieved real papers, ensuring verifiable judgments.<n>OpenNovelty aims to empower the research community with a scalable tool that promotes fair, consistent, and evidence-backed peer review.
  arXiv  Detail & Related papers  (2026-01-04T15:48:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.