arXiv cs.AI· Yijie Hu, Wei Li, Junjie Zhou, Zhiqi Jiang, Yi Jin, Licong Xu, Xinkai Sun, Kai Duan, Lisha Zhang·· 2 小时前AI 评分35
PatentAgentBench：用专业专利任务套件评测 LLM 智能体的新基准
PatentAgentBench: Benchmarking LLM Agents with Professional Patent Task Suites
AI 导读
arXiv 论文提出 PatentAgentBench，一个包含 510 个实例、覆盖新颖性检索、FTO 检索、无效检索、权利要求图表、专利撰写、审查意见答复和专利翻译等 8 项任务套件的基准，素材来自真实专利记录并结合专家评审标注。研究团队在 4 种智能体框架下评测 7 个 LLM，发现现有系统仍难以识别新颖性、评估风险和理解专利从业者的意图。
正文 · 原文
Abstract:Patent practice lies at the intersection of technical, legal, and linguistic work, making it challenging yet crucial to technological innovation. Recently, rapid advances in large language models (LLMs) and agentic systems have demonstrated the potential to complete realistic business workflows and even patent works. This raises a question: can current AI systems perform patent work reliably? Existing benchmarks cover a limited range of patent tasks and simplify evidence acquisition by providing reference materials or candidate documents. In this paper, we introduce PatentAgentBench, a benchmark comprising 510 instances across eight task suites: novelty search, freedom-to-operate (FTO) search, design FTO, invalidity search, claim charting, patent drafting, office-action response, and patent translation. Curated from real patent records and professional materials, the benchmark combines task-specific metrics with expert-reviewed annotations and rubrics. Retrieval tasks such novelty search, FTO, etc., require agents to search and compare patent collections without a supplied candidate pool. The drafting and OAR tasks assess the quality of agents' work given technical disclosure and office action notice. We evaluate seven LLMs across four agent harnesses on PatentAgentBench, finding that current systems still struggle to identify novelty, assess risk, and understand practitioner intent throughout patent workflows.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.35031 [cs.AI] |
| (or arXiv:2610.35031v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.35031 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yijie Hu [view email]
[v1]
Mon, 26 Oct 2026 08:44:25 UTC (3,735 KB)
来源：arXiv cs.AI · arxiv.org