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

Source: https://huggingface.co/papers/2606.02404 Authors:

,

,

,

,

,

,

,

,

,

,

,

Abstract

Korean web-browsing agent benchmark K-BrowseComp evaluates frontier LLMs’ capabilities with 400 problems, showing significant performance gaps compared to English benchmarks and highlighting the need for more robust Korean AI development.

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-BrowseComp, aweb-browsing agent benchmarkgrounded inKorean contexts, consisting of 400 problems. The 300-problem K-BrowseComp-Verified subset is manually constructed and validated by native Korean speakers. On this subset, frontierLLMs, including GPT-5.5, DeepSeek-V4-Pro, and GLM-5.1, reach only 30.00--45.67\%, a substantial drop fromBrowseComp, while KoreanLLMsreleased through Korea’s Proprietary AI Foundation Model program obtain only 0.00--10.33\%. We further construct a 100-problemsynthetic splitusing hardfew-shot exemplarsandfailure-mode-targeted generationto exploit the asymmetry between solving and creating web browsing problems. On the adversarially filtered synthetic diagnostic split, the strongest model reaches only 26.00\%, and we report this split separately as a targeted stress test. We publicly release our data and code.

View arXiv pageView PDFGitHub9Add to collection

Get this paper in your agent:

hf papers read 2606\.02404

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.02404 in a model README.md to link it from this page.

Datasets citing this paper1

#### prometheus-eval/k-browsecomp Viewer• Updatedabout 12 hours ago • 700 • 91 • 3

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.02404 in a Space README.md to link it from this page.

Collections including this paper1