发表机构
University of Oregon（俄勒冈大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究多跳问答中协调关系与文本证据问题，提出基于同步双向图-文本工作记忆的无训练系统Co-E，通过同步周期巩固记忆并注入事实，在多跳问答基准测试中表现出色，优于可比基线且与其他系统有竞争力。
AI 中文摘要
多跳问答需要在推理步骤中协调关系和文本证据，这是单独的文本语料库或知识图谱无法提供的。先前工作往往只强调这一循环的一部分。我们提出Co-E，一个围绕同步双向图-文本工作记忆构建的无训练系统。同步周期巩固文本记忆，将关系三元组提取到图记忆中，并将图事实注入生成上下文。在六个多跳问答基准上评估，Co-E优于可比的无训练开放主干基线，且与更大或经过训练的系统具有竞争力。
英文摘要
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.
