CycleResearcher: Improving Automated Research via Automated Review

• URL: http://arxiv.org/abs/2411.00816v1
• Date: Mon, 28 Oct 2024 08:10:21 GMT
• Title: CycleResearcher: Improving Automated Research via Automated Review
• Authors: Yixuan Weng, Minjun Zhu, Guangsheng Bao, Hongbo Zhang, Jindong Wang, Yue Zhang, Linyi Yang,
• Abstract summary: This paper explores the possibility of using open-source post-trained large language models (LLMs) as autonomous agents capable of performing the full cycle of automated research and review. To train these models, we develop two new datasets, reflecting real-world machine learning research and peer review dynamics. In research, the papers generated by the CycleResearcher model achieved a score of 5.36 in simulated peer reviews, surpassing the preprint level of 5.24 from human experts and approaching the accepted paper level of 5.69.
• Score: 37.03497673861402
• License:
• Abstract: The automation of scientific discovery has been a long-standing goal within the research community, driven by the potential to accelerate knowledge creation. While significant progress has been made using commercial large language models (LLMs) as research assistants or idea generators, the possibility of automating the entire research process with open-source LLMs remains largely unexplored. This paper explores the feasibility of using open-source post-trained LLMs as autonomous agents capable of performing the full cycle of automated research and review, from literature review and manuscript preparation to peer review and paper revision. Our iterative preference training framework consists of CycleResearcher, which conducts research tasks, and CycleReviewer, which simulates the peer review process, providing iterative feedback via reinforcement learning. To train these models, we develop two new datasets, Review-5k and Research-14k, reflecting real-world machine learning research and peer review dynamics. Our results demonstrate that CycleReviewer achieves a 26.89\% improvement in mean absolute error (MAE) over individual human reviewers in predicting paper scores, indicating that LLMs can surpass expert-level performance in research evaluation. In research, the papers generated by the CycleResearcher model achieved a score of 5.36 in simulated peer reviews, surpassing the preprint level of 5.24 from human experts and approaching the accepted paper level of 5.69. This work represents a significant step toward fully automated scientific inquiry, providing ethical safeguards and advancing AI-driven research capabilities. The code, dataset and model weight are released at \url{http://github/minjun-zhu/Researcher}.

Related papers

• Are Large Language Models Good Classifiers? A Study on Edit Intent Classification in Scientific Document Revisions [62.12545440385489]
  Large language models (LLMs) have brought substantial advancements in text generation, but their potential for enhancing classification tasks remains underexplored. We propose a framework for thoroughly investigating fine-tuning LLMs for classification, including both generation- and encoding-based approaches. We instantiate this framework in edit intent classification (EIC), a challenging and underexplored classification task.
  arXiv  Detail & Related papers  (2024-10-02T20:48:28Z)
• Towards Fully Autonomous Research Powered by LLMs: Case Study on Simulations [5.03859766090879]
  This study explores the feasibility of constructing an autonomous simulation agent powered by Large Language Models. Using a simulation problem of polymer chain conformations as a case study, we assessed the performance of ASAs powered by different LLMs. Our findings revealed that ASA-GPT-4o achieved near-flawless execution on designated research missions.
  arXiv  Detail & Related papers  (2024-08-28T03:48:05Z)
• LLAssist: Simple Tools for Automating Literature Review Using Large Language Models [0.0]
  LLAssist is an open-source tool designed to streamline literature reviews in academic research. It uses Large Language Models (LLMs) and Natural Language Processing (NLP) techniques to automate key aspects of the review process.
  arXiv  Detail & Related papers  (2024-07-19T02:48:54Z)
• SciRIFF: A Resource to Enhance Language Model Instruction-Following over Scientific Literature [80.49349719239584]
  We present SciRIFF (Scientific Resource for Instruction-Following and Finetuning), a dataset of 137K instruction-following demonstrations for 54 tasks. SciRIFF is the first dataset focused on extracting and synthesizing information from research literature across a wide range of scientific fields.
  arXiv  Detail & Related papers  (2024-06-10T21:22:08Z)
• MASSW: A New Dataset and Benchmark Tasks for AI-Assisted Scientific Workflows [58.56005277371235]
  We introduce MASSW, a comprehensive text dataset on Multi-Aspect Summarization of ScientificAspects. MASSW includes more than 152,000 peer-reviewed publications from 17 leading computer science conferences spanning the past 50 years. We demonstrate the utility of MASSW through multiple novel machine-learning tasks that can be benchmarked using this new dataset.
  arXiv  Detail & Related papers  (2024-06-10T15:19:09Z)
• Autonomous LLM-driven research from data to human-verifiable research papers [0.0]
  We build an automation platform that guides interacting through complete stepwise process. In mode provided annotated data alone, datapaper raised hypotheses, designed plans, wrote and interpreted analysis codes, generated and interpreted results. We demonstrate potential for AI-driven acceleration of scientific discovery while enhancing traceability, transparency and verifiability.
  arXiv  Detail & Related papers  (2024-04-24T23:15:49Z)
• Towards Data-Centric Automatic R&D [17.158255487686997]
  Researchers often seek the potential research directions by reading and then verifying them through experiments. The data-driven black-box deep learning method has demonstrated its effectiveness in a wide range of real-world scenarios. We propose a Real-world Data-centric automatic R&D Benchmark, namely RD2Bench.
  arXiv  Detail & Related papers  (2024-04-17T11:33:21Z)
• ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models [56.08917291606421]
  ResearchAgent is a large language model-powered research idea writing agent. It generates problems, methods, and experiment designs while iteratively refining them based on scientific literature. We experimentally validate our ResearchAgent on scientific publications across multiple disciplines.
  arXiv  Detail & Related papers  (2024-04-11T13:36:29Z)
• System for systematic literature review using multiple AI agents: Concept and an empirical evaluation [5.194208843843004]
  We introduce a novel multi-AI agent model designed to fully automate the process of conducting Systematic Literature Reviews. The model operates through a user-friendly interface where researchers input their topic. It generates a search string used to retrieve relevant academic papers. The model then autonomously summarizes the abstracts of these papers.
  arXiv  Detail & Related papers  (2024-03-13T10:27:52Z)
• DACO: Towards Application-Driven and Comprehensive Data Analysis via Code Generation [83.30006900263744]
  Data analysis is a crucial analytical process to generate in-depth studies and conclusive insights. We propose to automatically generate high-quality answer annotations leveraging the code-generation capabilities of LLMs. Our DACO-RL algorithm is evaluated by human annotators to produce more helpful answers than SFT model in 57.72% cases.
  arXiv  Detail & Related papers  (2024-03-04T22:47:58Z)

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.