J-tau: A Fully Localized Japanese Benchmark for Tool-Agent-User Interaction

arXiv:2610.19638 · cs.CL · Submitted 2026-10-14 · Read on arXiv

cs.CL

Submitted: 2026-10-14

Updated: 2026-10-14

Code: https://github.com/sbintuitions/j-tau-bench

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 1× in this paper · explained in 2 episodes

Sources

• Ticket-Bench: A Kickoff for Multilingual and Regionalized Agent Evaluation
• OmnilingualGAIA2: Evaluating the Multilingual Gap in Frontier AI Agents
• SABER: Small Actions, Big Errors -- Safeguarding Mutating Steps in LLM Agents
• GLM-5: from Vibe Coding to Agentic Engineering
• Kimi K3: Open Frontier Intelligence
• BabelArena: A Large-Scale Multilingual Benchmark for LLM Agents
• K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts
• PolyWorkBench: Benchmarking Multilingual Long-Horizon LLM Agents
• LLM-jp: A Cross-organizational Project for the Research and Development of Fully Open Japanese LLMs
• SEATauBench: Progressively Adapting Tool-Agent-User Evaluation Into Low-Resource Southeast Asian Languages
• gpt-oss-120b & gpt-oss-20b Model Card
• Qwen3 Technical Report
• tau-Multilingual: Benchmarking Voice Agents Across Languages
• Agents' Last Exam
• BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinese

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering