发表机构
Institute of Information Engineering, CAS; University of Aberdeen; The University of Western Australia; Brown University（中国科学院信息工程研究所; 阿伯丁大学; 西澳大学; 布朗大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
ClueWeaver是用于紧凑型本地模型的双智能体证据推理框架，可提升本地语言模型在长篇叙事问答与声明验证任务中的性能，提供可检查的证据推理轨迹。
AI 中文摘要
人文社科研究需要对小说、剧本、档案、案例报告等长篇叙事材料进行精读，但许多用户难以获取昂贵的专有长上下文模型。紧凑型、可本地部署的语言模型是实用替代方案，但直接向其输入完整长上下文仍成本高昂、难以检查，且容易遗漏稀疏证据。我们提出ClueWeaver，一种用于紧凑型本地模型的长篇叙事问答的证据感知双智能体框架。Finder（查找器）通过检索引导的分段识别包含答案关键线索的段落，而Interpreter（解释器）从选定证据中推导答案，生成带有段落ID引用的理由，并对高风险问题应用内部自校准步骤。两个智能体均通过奖励引导的强化学习进行优化：Finder的奖励强调证据保留和忠实的段落ID引用，Interpreter的奖励强调正确性、证据依据和简洁解释。这种分解使证据选择和推理比端到端提示更具可检查性。在多个长上下文叙事问答和声明验证设置上的实验表明，ClueWeaver大幅提升了本地端到端语言模型的性能，同时提供证据覆盖和段落引用的推理轨迹。代码可在this https URL获取。
英文摘要
Humanities and social science research requires close reading of long narrative materials such as novels, scripts, archives, and case reports, yet many users have limited access to costly proprietary long-context models. Compact, locally deployable language models are a practical alternative, but directly feeding them an entire long context remains costly, hard to inspect, and prone to missing sparse evidence. We present ClueWeaver, an evidence-aware dual-agent framework for long-narrative question answering with compact local models. A Finder identifies passages containing answer-critical clues through retrieval-guided segmentation, while an Interpreter derives the answer from the selected evidence, produces rationales with paragraph-ID citations, and applies an internal self-calibration pass for high-risk questions. Both agents are optimized with reward-guided reinforcement learning: Finder rewards emphasize evidence retention and faithful paragraph-ID references, and Interpreter rewards emphasize correctness, grounding, and concise explanations. This decomposition makes evidence selection and reasoning more inspectable than end-to-end prompting. Experiments across multiple long-context narrative question answering and claim verification settings show that ClueWeaver substantially improves local end-to-end language models while providing evidence coverage and paragraph-referenced reasoning traces. Code is available at https://github.com/Ameame1/ClueWeaver.
CommentsAccepted by ICONIP 2026
