mlsanityData to 14 Oct 2026

A Vision for Auto Research with LLM Agents

arXiv 2504.18765 ↗First posted 26 Apr 2025cs.AIcited by 18

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

Abstract (arXiv)

This paper introduces Agent-Based Auto Research, a structured multi-agent framework designed to automate, coordinate, and optimize the full lifecycle of scientific research. Leveraging the capabilities of large language models (LLMs) and modular agent collaboration, the system spans all major research phases, including literature review, ideation, methodology planning, experimentation, paper writing, peer review response, and dissemination. By addressing issues such as fragmented workflows, uneven methodological expertise, and cognitive overload, the framework offers a systematic and scalable approach to scientific inquiry. Preliminary explorations demonstrate the feasibility and potential of Auto Research as a promising paradigm for self-improving, AI-driven research processes.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 14 of its 26 references that are in the map. First posted on arXiv 26 Apr 2025.

Builds on

14 of 26 references.

References · 14

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  3. 2024The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Surveycited by 168
  4. 2024AutoSurvey: Large Language Models Can Automatically Write Surveyscited by 119
  5. 2025Plan-Then-Execute: An Empirical Study of User Trust and Team Performance When Using LLM Agents As A Daily Assistantcited by 54
  6. 2025SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writingcited by 49
  7. 2024Agent-Oriented Planning in Multi-Agent Systemscited by 36
  8. 2025SurveyX: Academic Survey Automation via Large Language Modelscited by 29
  9. 2023Large language models for aspect-based sentiment analysiscited by 17
  10. 2022Paving the Way for Mature Secondary Research: The Seven Types of Literature Reviewcited by 6
  11. 2025Complex LLM Planning via Automated Heuristics Discoverycited by 6
  12. 2024A Comprehensive Evaluation of Large Language Models on Aspect-Based Sentiment Analysiscited by 5
2 more
  1. 2024A Literature Review of Literature Reviews in Pattern Analysis and Machine Intelligencecited by 3
  2. 2024Large Language Models in Targeted Sentiment Analysiscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 8; 2026: 10.

18 papers.

Sort:

By area:

  1. 2025From Automation to Autonomy: A Survey on Large Language Models in Scientific Discoverycited by 93
  2. 2026Frontier-Eng: Benchmarking Self-Evolving Agents on Real-World Engineering Tasks with Generative Optimizationcited by 16
  3. 2026AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discoverycited by 10
  4. 2025BadScientist: Can a Research Agent Write Convincing but Unsound Papers that Fool LLM Reviewers?cited by 8
  5. 2025Stop DDoS Attacking the Research Community with AI-Generated Survey Paperscited by 7
  6. 2025SGSimEval: A Comprehensive Multifaceted and Similarity-Enhanced Benchmark for Automatic Survey Generation Systemscited by 3
  7. 2025GenCellAgent: Generalizable, Training-Free Cellular Image Segmentation via Large Language Model Agentscited by 3
  8. 2025Agentic Inequalitycited by 3
  9. 2026HLER: Human-in-the-Loop Economic Research via Multi-Agent Pipelines for Empirical Discoverycited by 3
  10. 2025AutoPR: Let's Automate Your Academic Promotion!cited by 2
  11. 2026ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomescited by 2
  12. 2025Eliminating Agentic Workflow for Introduction Generation with Parametric Stage Tokenscited by 1
6 more
  1. 2026EngiAgent: Fully Connected Coordination of LLM Agents for Solving Open-ended Engineering Problems with Feasible Solutionscited by 1
  2. 2026Malicious Repurposing of Open Science Artefacts by Using Large Language Modelscited by 0
  3. 2026MAGNET: Autonomous Expert Model Generation via Decentralized Autoresearch and BitNet Trainingcited by 0
  4. 2026Thinking Like a Scientist? A Structural Study of LLM-Generated Research Methodscited by 0
  5. 2026Clarus: Coordinating Autonomous Research Agents toward Web-Scale Scientific Collaborationcited by 0
  6. 2026Internalizing Academic Writing Workflows for Introduction Generation via Struct-Aware Policy Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Agentic AutoSurvey: Let LLMs Survey LLMs
  2. 2025Agent4S: The Transformation of Research Paradigms from the Perspective of Large Language Models
  3. 2025Agent Laboratory: Using LLM Agents as Research Assistants
  4. 2026Towards End-to-End Automation of AI Research
  5. 2026AutoSci: A Memory-Centric Agentic System for the Full Scientific Research Lifecycle
  6. 2025Towards Scientific Intelligence: A Survey of LLM-based Scientific Agents
  7. 2026LLM Agents as Social Scientists: A Human-AI Collaborative Platform for Social Science Automation
  8. 2026PARNESS: A Paper Harness for End-to-End Automated Scientific Research with Dynamic Workflows, Full-Text Indexing, and Cross-Run Knowledge Accumulation