A Vision for Auto Research with LLM Agents
This addresses the problem of fragmented workflows and cognitive overload in scientific research for researchers, though it appears incremental as it builds on existing LLM and agent technologies.
The paper tackles the problem of automating the full lifecycle of scientific research by introducing Agent-Based Auto Research, a multi-agent framework using LLMs to coordinate tasks like literature review and experimentation, with preliminary results showing its feasibility as a self-improving AI-driven paradigm.
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.