mlsanityData to 7 Oct 2026

AutoResearch: An Execution-Grounded Multi-Agent Framework for Reliable Research Workflow Automation

arXiv 2607.02520 ↗First posted 4 May 2026cs.CY cs.AI cs.SEcited by 0

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

Automated research agents increasingly generate code, retrieve literature, and draft scientific artifacts, but they often fail to verify whether generated experiments execute correctly or whether cited sources support generated claims. We present AutoResearch, an execution-grounded multi-agent framework for reliable research workflow automation. AutoResearch couples sandboxed Python/PyTorch execution, iterative code repair, citation verification, claim-support auditing, decision control, and structured LaTeX artifact generation. The system treats runtime errors, citation-verification failures, and review-agent feedback as practical filtering signals for generated research artifacts. In controlled evaluations on HumanEval, MBPP, a SciCode subset, citation-validation tasks, claim-support auditing, and small end-to-end workflow stress tests, AutoResearch improves execution success, citation validity, local claim support, and workflow completion relative to directly comparable baselines. Code-oriented agents are reported separately as partial comparisons. AutoResearch is intended as a reliability-oriented research assistant, not as a fully autonomous scientist or a standalone manuscript-quality benchmark. Source Code: https://github.com/raja21068/AutoResearch

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 20 of its 34 references that are in the map. First posted on arXiv 4 May 2026.

Builds on

20 of 34 references.

References · 20

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  4. 2024GPT-4o System Cardcited by 4,467
  5. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  6. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  7. 2021Program Synthesis with Large Language Modelscited by 3,509
  8. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  9. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  10. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  11. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineeringcited by 1,628
  12. 2023Teaching Large Language Models to Self-Debugcited by 963
8 more
  1. 2024OpenHands: An Open Platform for AI Software Developers as Generalist Agentscited by 956
  2. 2023ChatDev: Communicative Agents for Software Developmentcited by 893
  3. 2023RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generationcited by 357
  4. 2023Chain-of-Verification Reduces Hallucination in Large Language Modelscited by 317
  5. 2024MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolutioncited by 132
  6. 2023InferFix: End-to-End Program Repair with LLMscited by 113
  7. 2025Assemble Your Crew: Automatic Multi-agent Communication Topology Design via Autoregressive Graph Generationcited by 57
  8. 2026PaperOrchestra: A Multi-Agent Framework for Automated AI Research Paper Writingcited by 10

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026How Do Agents Fail on AutoResearch: End-to-End Diagnostic Evaluation on 100 Real-World Frontier Research Tasks
  2. 2026Can Coding Agents Reproduce Findings in Computational Materials Science?
  3. 2026Automating Computational Reproducibility in Social Science: Comparing Prompt-Based and Agent-Based Approaches
  4. 2026R-LAM: Reproducibility-Constrained Large Action Models for Scientific Workflow Automation
  5. 2026Beyond the Text: Verifying That Agent-Written Papers Are Backed by Their Artifacts
  6. 2026ScienceFlow: A long-horizon agent for ML research, scientific discovery and beyond
  7. 2026Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research Agents
  8. 2026AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration