PaperDebugger：基於外掛程式的多代理系統，用於編輯器內學術寫作、審閱與修訂

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

大型語言模型正日益融入學術寫作流程，然而現有輔助工具仍游離於編輯器外部，無法深度交互文檔狀態、結構與修訂歷史。這種分離性導致無法在Overleaf等LaTeX編輯器內直接支持具備自主性與情境感知的操作。本文提出PaperDebugger——一款基於插件架構的多智能體編輯器內嵌學術寫作輔助系統，將LLM驅動的推理能力直接引入寫作環境。實現此類編輯器內交互存在顯著技術挑戰：需確保與編輯器的可靠雙向同步、精細化的版本控制與補丁管理、安全狀態維護、多智能體調度，以及可擴展的外部工具通信。PaperDebugger通過Chrome認證擴展組件、Kubernetes原生編排層，以及集成文獻檢索、參考文獻查找、文檔評分與修訂管道的模型上下文協議（MCP）工具鏈解決這些難題。我們的演示展現了完全集成的工作流，包括局部化編輯、結構化審閱、並行智能體執行與基於差異比對的更新機制，所有功能均封裝於低侵入性用戶界面（UI）中。初期聚合數據顯示用戶活躍參與度，驗證了編輯器原生自主型寫作輔助工具的實用性。更多演示詳情與視頻可訪問：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.