用Cognee、知识图谱与多跳推理，破解文档分块导致的结构丢失问题，重塑企业工作空间搜索。
The promise of Enterprise AI is simple: give an LLM access to your company’s internal tools, and let it answer complex organizational questions. But i…
LLM化身验证器，用证据链提升多跳推理的准确性与可信度
arXiv:2604.01993v2 Announce Type: replace-cross Abstract: Multi-hop QA benchmarks often reward Large Language Models (LLMs) for spurious correctness, …
探索多模态文档集合中的多跳推理新基准DocHop-QA，推动视觉与文本信息联合理解。
arXiv:2508.15851v2 Announce Type: replace Abstract: Despite rapid progress in large language models (LLMs), current QA benchmarks still overlook the c…
首个结合智能体主动感知与全模态交互的多跳视听推理框架，突破被动感知局限
arXiv:2605.28192v1 Announce Type: new Abstract: Multi-hop audio-visual reasoning remains challenging for Omni-LLMs, as relevant evidence is often spar…
探讨将大型语言模型的“幻觉”转化为有用推理能力，通过链式系统I/II思维解决复杂多跳问题的新思路。
arXiv:2605.27596v1 Announce Type: new Abstract: Recently, there has been increased interest in Small Language Models (SLMs), which are fast, show good…
图增强RAG架构如何破解向量搜索在复杂企业数据中的结构盲区，实现多跳推理与精准关联。
Retrieval-augmented generation (RAG) has become the de facto standard for grounding large language models (LLMs) in private data. The standard archite…