让文本和图记忆同步进化，无需训练就能更好答多跳问题
Co-Evolving Graph and Text Memory for Training-Free Multi-Hop Question Answering
- 文本与图记忆双向同步，动态更新知识
- 在6个基准上超越同类无训练系统
- 适合需要高效多跳推理的开放域问答场景
多跳问答需协调多个推理步骤中的关系与文本证据，单一文本语料库或知识图谱均无法满足。以往工作多侧重其中一环：图增强的RAG依赖预构建或查询更新的图，KGQA在主题子图中搜索，而记忆增强型代理虽能演化记忆，却未持续对齐图与文本。我们提出Co-E，一个无需训练的系统，基于双向同步的图-文工作记忆。同步周期内，整合文本记忆，提取关系三元组至图记忆，并将图事实注入生成上下文。两者持续相互影响，塑造后续检索与生成。在六个多跳问答基准上评估，Co-E优于可比的无训练开源模型，并媲美更大或有训练的系统。
原文摘要 · Abstract (English)
Multi-hop question answering requires coordinating relational and textual evidence across reasoning steps, a combination neither a text corpus nor a knowledge graph can supply alone. Prior work often emphasizes only part of this loop: graph-augmented RAG retrieves from a pre-built or query-updated graph, KGQA systems search within topic-centered subgraphs, and memory-augmented agents maintain evolving memories without continuously reconciling graph memory with textual context. We propose Co-E, a training-free system built around synchronized bidirectional graph-text working memory. A synchronization cycle consolidates textual memory, extracts relational triples into graph memory, and injects graph facts back into the generation context. Because both memories are maintained, they shape subsequent retrieval and generation. Evaluated on six multi-hop QA benchmarks, Co-E improves over comparable training-free open-backbone baselines and is competitive with larger or trained systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。