发表机构
School of Cyber Science and Engineering, Wuhan University; National University of Singapore（武汉大学网络安全学院; 新加坡国立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有引用推荐系统易错误归属的问题，提出解耦智能体框架ReCite，通过位置感知、意图查询规划和反思验证实现主张级推理，在严格引用准确率上超越大规模生成模型。
AI 中文摘要
准确的引用是学术写作的基础，它追溯思想起源并支撑核心主张。然而，面对日益增长的科技文献，人工查阅变得越来越困难，这促使人们依赖自动引用推荐。虽然现代检索增强架构已在很大程度上缓解了虚构不存在的论文的问题，但当前依赖语义相似性的系统在错误归属方面仍存在不足，常常引用那些无法在逻辑上支持作者主张的真实论文。为应对这一挑战，我们认为，准确的引用需要从基于相似性的搜索转向主动的、主张层面的推理。我们提出了ReCite，一个解耦的智能体框架，它协调位置感知、意图感知的查询规划和反思性验证。基于合成的推理轨迹进行训练，我们的智能体验证主张与证据的一致性，并在检索到的候选缺乏逻辑支持时触发自我修正循环。实验表明，我们的轻量级框架在严格引用准确率上优于最先进的大规模生成模型。通过将文献匹配建立在可验证的逻辑而非语义重叠之上，ReCite为自动化学术写作奠定了可靠的基础。
英文摘要
Accurate citations are the foundation of academic writing, tracing intellectual origins and substantiating core claims. However, manually navigating the growing volume of scientific literature is increasingly difficult, prompting reliance on automatic citation recommendation. While modern retrieval-augmented architectures have largely mitigated the fabrication of non-existent papers, current systems relying on semantic similarity struggle with misattribution, often citing authentic papers that fail to logically support the author's claim. To address this challenge, we argue that accurate citation requires a shift from similarity-based search to active, claim-level reasoning. We propose ReCite, a decoupled agentic framework that orchestrates location perception, intent-aware query planning, and reflective verification. Trained on synthesized reasoning trajectories, our agent verifies claim-evidence consistency and triggers self-correction loops when retrieved candidates lack logical support. Experiments demonstrate that our lightweight framework outperforms state-of-the-art massive generative models in strict citation accuracy. By grounding literature matching in verifiable logic rather than semantic overlap, ReCite establishes a reliable foundation for automated academic writing.
CommentsFindings of EMNLP 2026. Project page: https://hyy279.github.io/ReCite
