mlsanityData to 14 Oct 2026

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

arXiv 2605.28282 ↗First posted 27 May 2026cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 15 of its 47 references that are in the map. First posted on arXiv 27 May 2026.

Builds on

15 of 47 references.

References · 15

  1. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineeringcited by 1,737
  2. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,071
  3. 2025Agent Laboratory: Using LLM Agents as Research Assistantscited by 425
  4. 2025The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Searchcited by 422
  5. 2025Accelerating scientific discovery with Co-Scientistcited by 401
  6. 2025An AI system to help scientists write expert-level empirical softwarecited by 60
  7. 2024Autonomous LLM-driven research from data to human-verifiable research paperscited by 53
  8. 2026AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agentscited by 38
  9. 2026ARIS: Autonomous Research via Adversarial Multi-Agent Collaborationcited by 16
  10. 2026PaperOrchestra: A Multi-Agent Framework for Automated AI Research Paper Writingcited by 13
  11. 2026DeepFact: Co-Evolving Benchmarks and Agents for Deep Research Factualitycited by 10
  12. 2026PARNESS: A Paper Harness for End-to-End Automated Scientific Research with Dynamic Workflows, Full-Text Indexing, and Cross-Run Knowledge Accumulationcited by 5
3 more
  1. 2025Can AI Validate Science? Benchmarking LLMs for Accurate Scientific Claim rightarrow Evidence Reasoningcited by 4
  2. 2026Sibyl-AutoResearch: Autonomous Research Needs Self-Evolving Trial-and-Error Harnesses, Not Paper Generatorscited by 3
  3. 2026Rethinking Artifact Evaluation for Software Engineering in the Age of Generative AIcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Proof-or-Stop: Don't Trust the Agent, Trust the Evidence -- Loop Engineering for Verifiable Evidence-Gated Lifecycle Controlcited by 5
  2. 2026Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligencecited by 3
  3. 2026EvoCast: Reliable Autonomous Research Agents for Iterative Forecasting Architecture Evolutioncited by 0