AIBuildAI-2: A Knowledge-Enhanced Agent for Automatically Building AI Models

arXiv 2026 35.9 method

TLDR

A knowledge-enhanced agent with hierarchical external knowledge to automatically build AI models, addressing limitations of static LLM knowledge.

Reasoning

The paper presents a novel approach to automate AI model building using an evolving knowledge system, which is a strength. However, the abstract lacks empirical results or real-world validation, making it unclear how effective the system is.

Read-first score

Read-first score 35.9, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 29.

Recency 8%

100

Uses a gentle age decay so recent papers surface without erasing older foundations. 2026

Methodology quality 25%

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=metric,result

Reproducibility 25%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=none

Topical relevance 42%

24.2

Uses existing LLM keyword relevance scores normalized to 0-100. AI scientist,automated scientific discovery,autonomous research agent,automated research,literature review agent,survey generation,automated experimentation,experiment design agent,AI for scientific research,paper writing agent,research automation,scientific discovery agent

Field roles

Frontier

Rank sensitivity

Stability: volatile; rank range: 47.

Keyword Scores

AI for scientific research

research automation

AI scientist

automated scientific discovery

autonomous research agent

scientific discovery agent

automated research

automated experimentation

experiment design agent

literature review agent

survey generation

paper writing agent

Resources

Paper