PaperDebugger：基于插件的多智能体系统，实现编辑器内学术写作、评审与编辑

PaperDebugger: A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editing

December 2, 2025

作者: Junyi Hou, Andre Lin Huikai, Nuo Chen, Yiwei Gong, Bingsheng He

cs.AI

摘要

大型语言模型正日益融入学术写作流程，但现有助手始终独立于编辑器之外，无法深度交互文档状态、结构与修订历史。这种隔离导致无法在Overleaf等LaTeX编辑器内直接支持具有自主性与上下文感知能力的操作。我们推出PaperDebugger——一款内嵌于编辑器、基于多智能体与插件架构的学术写作助手，将LLM驱动的推理能力直接引入写作环境。实现此类编辑器内交互存在显著技术挑战：需要可靠的编辑器双向同步、细粒度版本控制与补丁管理、安全状态维护、多智能体调度，以及与外部工具的可扩展通信。PaperDebugger通过Chrome官方认证的扩展程序、Kubernetes原生编排层，以及集成文献检索、参考文献查找、文档评分与修订流水线的模型上下文协议（MCP）工具链应对这些挑战。我们的演示展现了一套完全集成的工作流，包括局部化编辑、结构化审阅、并行智能体执行与基于差异对比的更新，所有功能均封装在低干扰用户界面中。早期聚合数据分析显示用户活跃参与度高，验证了编辑器原生型智能写作助手的实用性。更多演示详情与视频请访问：https://github.com/PaperDebugger/PaperDebugger。

English

Large language models are increasingly embedded into academic writing workflows, yet existing assistants remain external to the editor, preventing deep interaction with document state, structure, and revision history. This separation makes it impossible to support agentic, context-aware operations directly within LaTeX editors such as Overleaf. We present PaperDebugger, an in-editor, multi-agent, and plugin-based academic writing assistant that brings LLM-driven reasoning directly into the writing environment. Enabling such in-editor interaction is technically non-trivial: it requires reliable bidirectional synchronization with the editor, fine-grained version control and patching, secure state management, multi-agent scheduling, and extensible communication with external tools. PaperDebugger addresses these challenges through a Chrome-approved extension, a Kubernetes-native orchestration layer, and a Model Context Protocol (MCP) toolchain that integrates literature search, reference lookup, document scoring, and revision pipelines. Our demo showcases a fully integrated workflow, including localized edits, structured reviews, parallel agent execution, and diff-based updates, encapsulated within a minimal-intrusion user interface (UI). Early aggregated analytics demonstrate active user engagement and validate the practicality of an editor-native, agentic writing assistant. More details about this demo and video could be found at https://github.com/PaperDebugger/PaperDebugger.