Deep Research Bench: Evaluating AI Web Research Agents

“Interactive Fiction Games: A Colossal Adventure”

Matthew Hausknecht, Prithviraj Ammanabrolu, Marc-Alexandre C\ˆot\’e and Xingdi Yuan · 1909

Earlier work this paper cites.

“ALFWorld: Aligning Text and Embodied Environments for Interactive Learning”

Mohit Shridhar et al · 2010

Earlier work this paper cites.

“Trafilatura: A Web Scraping Library and Command-Line Tool for Text Discovery and Extraction”

Adrien Barbaresi · 2021

Earlier work this paper cites.

“WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents”

Shunyu Yao, Howard Chen, John Yang and Karthik Narasimhan · 2023

Earlier work this paper cites.

“AgentSims: An Open-Source Sandbox for Large Language Model Evaluation”

Jiaju Lin et al · 2023

Earlier work this paper cites.

“AgentBench: Evaluating LLMs as Agents”

Xiao Liu et al · 2023

Earlier work this paper cites.

“GAIA: A Benchmark for General AI Assistants”

Gr\’egoire Mialon et al · 2023

Cited alongside, same era.

“ReAct: Synergizing Reasoning and Acting in Language Models”, 2023

Original

Shunyu Yao et al · 2023

Cited alongside, same era.

“WebArena: A Realistic Web Environment for Building Autonomous Agents”

Shuyan Zhou et al · 2024

Cited alongside, same era.

“Towards a Realistic Long-Term Benchmark for Open-Web Research Agents”

Peter M\"uhlbacher, Nikos. Bosse and Lawrence Phillips · 2024

Cited alongside, same era.

“Serper API: Google Search API” Available at https://serper.dev/ , Web API, 2025

Serper, Inc · 2025

Cited alongside, same era.

“Playwright: Fast and reliable end-to-end testing for modern web apps” Browser automation framework, 2025

“ScraperAPI: Web Scraping API” Available at https://www.scraperapi.com/ , Web API, 2025

ScraperAPI · 2025

Closest in time.

“Gemini thinking” Available at https://ai.google.dev/gemini-api/docs/thinking , Web Documentation, 2025

Google · 2025

Closest in time.

“Reasoning models” Available at https://platform.openai.com/docs/guides/reasoning , Web Documentation, 2025

OpenAI · 2025

Closest in time.

“Common Crawl: An open repository of web crawl data” Open web crawl corpus, Web Archive, 2025

Common Crawl Foundation · 2025

Closest in time.

“Humanity’s Last Exam”

Long Phan et al · 2025

Closest in time.