paper-with-me

Papers

BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents

2025-04-16 · Jason Wei, Zhiqing Sun, Spencer Papay, Scott McKinney, Jeffrey Han, Isa Fulford, Hyung Won Chung, Alex Tachard Passos, William Fedus, Amelia Glaese

We present BrowseComp, a simple yet challenging benchmark for measuring the ability for agents to browse the web. BrowseComp comprises 1,266 questions that require persistently navigating the internet in search of hard-to-find, entangled information. Despite the difficulty of the questions, BrowseComp is simple and easy-to-use, as predicted answers are short and easily verifiable against reference answers. BrowseComp for browsing agents can be seen as analogous to how programming competitions are an incomplete but useful benchmark for coding agents. While BrowseComp sidesteps challenges of a true user query distribution, like generating long answers or resolving ambiguity, it measures the important core capability of exercising persistence and creativity in finding information. BrowseComp can be found at https://github.com/openai/simple-evals.

📄 PDF Abstract BibTeX arXiv:2504.12516

Code (1)

openai/simple-evals 공식 구현

Similar Papers 제목 키워드 기반

MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents

2025-08-14 · Shilong Li, Xingyuan Bu, Wenjie Wang, Jiaheng Liu 외 arxiv

AI agents with advanced reasoning and tool-use capabilities have demonstrated impressive performance in web browsing for deep search. However, existing benchmarks such as BrowseComp primarily focus on textual content, ov…

Multimodal Reasoning

BrowseComp-$V^3$: A Visual, Vertical, and Verifiable Benchmark for Multimodal Browsing Agents

2026-02-13 · Huanyao Zhang, Jiepeng Zhou, Bo Li, Bowen Zhou 외 arxiv

Multimodal large language models (MLLMs), equipped with increasingly advanced planning and tool-use capabilities, are evolving into autonomous agents capable of performing multimodal web browsing and deep search in open-…

K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts

2026-06-01 · Nahyun Lee, Dongkeun Yoon, Guijin Son, Geewook Kim 외 arxiv

Frontier model evaluations are shifting from foundational capabilities (e.g., instruction following and reasoning) toward compositional, agentic ones, but Korean agentic benchmarks remain scarce. We introduce K-BrowseCom…

Instruction Following

BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinese

2025-04-27 · Peilin Zhou, Bruce Leon, Xiang Ying, Can Zhang 외

As large language models (LLMs) evolve into tool-using agents, the ability to browse the web in real-time has become a critical yardstick for measuring their reasoning and retrieval competence. Existing benchmarks such a…

BenchmarkingProper NounRetrieval

EvoBrowseComp: Benchmarking Search Agents on Evolving Knowledge

2026-06-11 · Yunhan Wang, Jiaan Wang, Lianzhe Huang, Xianfeng Zeng 외 arxiv

Search Agents -- large language models augmented with search tools -- have intensified the need for future-proof evaluation benchmarks. Existing benchmarks such as BrowseComp rely on static knowledge, making them vulnera…