PulseAugur
EN
LIVE 06:45:59

NeoResearch uses LLMs to autonomously discover time series forecasting models

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]

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

NeoResearch uses LLMs to autonomously discover time series forecasting models

How we ranked this

Signal score
40 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The cluster contains a research paper detailing a new autonomous framework for model discovery. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.LG TIER_1 English(EN) · Ze Guo, Mingyue Cheng, Xiaoyu Tao, Shuo Yu, Shangtong Ye ·

    NeoResearch: Literature- and Experience-Guided Autonomous Time Series Model Discovery

    arXiv:2611.18235v1 Announce Type: new Abstract: Developing effective forecasting models for diverse time-series domains requires substantial expert knowledge, evidence from scientific literature on the web, and iterative experimentation. However, translating this knowledge and re…