A Closer Look at Agentic BBO: Benchmarking LLM Agents for Black-Box Optimization

arXiv 2026 45.2 method

TLDR

Introduces AgenticBBO-Bench, a cross-domain benchmark for LLM agents solving black-box optimization, showing performance gains and analyzing design factors.

Reasoning

The paper provides a new benchmark and systematic evaluation of LLM agents for BBO across five domains, with clear strengths in unified protocol and ablation of key factors. Weaknesses are limited to abstract-level info; no evidence of full AI-scientist scope or literature review tasks.

Read-first score

Read-first score 45.2, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 30.

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=benchmark,evaluation,experiment,result

Reproducibility 25%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=code,github

Topical relevance 42%

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: 29.

Keyword Scores

AI for scientific research

automated experimentation

research automation

scientific discovery agent

automated scientific discovery

autonomous research agent

experiment design agent

AI scientist

automated research

literature review agent

survey generation

paper writing agent

Resources

Paper