Researchers have developed NeoResearch, an autonomous framework designed to discover lightweight, domain-specific time series forecasting models. This system utilizes large language models as researchers, employing a dual-loop workflow that combines hypothesis-driven architecture exploration with iterative experimental feedback for training and optimization. NeoResearch autonomously mines scientific literature to extract modeling mechanisms and empirical evidence, formulating testable architecture hypotheses. It also incorporates a hierarchical experience memory to link literature findings with experimental outcomes, guiding future discoveries and supporting reuse across different forecasting tasks. AI
IMPACT This framework could accelerate the development of specialized forecasting models by automating literature review and experimentation.
RANK_REASON The cluster contains a research paper detailing a new autonomous framework for model discovery. [lever_c_demoted from research: ic=1 ai=1.0]
- alphaXiv
- arXiv
- CatalyzeX
- Connected Papers
- CORE Recommender
- DagsHub
- Gotit.pub
- Hugging Face
- IArxiv Recommender
- Litmaps
- NeoResearch
- ScienceCast
- scite Smart Citations
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →