English(EN) DocSkill: Skill-Integrated Agentic Reasoning for Multilingual Multi-Hop Document Question Answering

新的DocSkill框架通过自适应推理增强多语言文档问答能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-28 04:00

研究人员推出了一种新的代理框架DocSkill，旨在改进多语言多跳文档问答。该框架利用学习到的技能编排策略，在复杂的文档和多种语言中自适应地获取和推理证据。为了训练该策略，他们采用了受限蒙特卡洛树搜索进行离线轨迹探索，然后进行监督微调和直接偏好优化。该团队还开发了MMHop-DocBench，这是一个包含10种语言的60,000个问答对的新数据集，证明了DocSkill在现有基线上的优越性能。 AI

影响该框架可以显著改善AI系统处理和回答复杂、多语言文档中问题的能力。

排序理由研究论文，详细介绍了一种用于特定NLP任务的新模型/框架。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 14 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 研究论文，详细介绍了一种用于特定NLP任务的新模型/框架。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Jing Huang, Zhiya Tan, Changtao Miao, Shutao Gong, Yang Wang, Joey Tianyi Zhou, Jianshu Li, Ying Yan · 2026-10-28 04:00

DocSkill：集成技能的智能体推理，用于多语言多跳文档问答

arXiv:2610.36759v1 Announce Type: new Abstract: Multilingual multi-hop document question answering (MMHop-DocQA) requires locating and integrating evidence across complex layouts, document pages, and diverse languages. Existing approaches include single-pass processing and adapti…

本文如何被排名

报道来源 [1]

DocSkill：集成技能的智能体推理，用于多语言多跳文档问答

相关实体

相关话题