Paper 2512.02589
PaperDebugger: A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editing
- Published
- Dec 2025
- Research lab
- Independent
- Citations
- 9
- GitHub
- 1.5K stars
01 In brief
Summary
PaperDebugger is an in-editor, multi-agent, plugin-based academic writing assistant that integrates directly into Overleaf via a Chrome extension, eliminating copy-paste workflows.
It addresses the challenge of external LLM assistants by providing bidirectional synchronization, version control, secure state management, and multi-agent scheduling.
The system uses a Kubernetes-native backend, a gRPC gateway, and a Model Context Protocol (MCP) toolchain (XtraMCP) for literature search, reference lookup, document scoring, and revision pipelines.
It supports two agent execution modes: prompt-template agents for low-latency tasks and workflow-based agents for complex tasks like deep research.
Specialized agents include Reviewer, Enhancer, Scoring, and Researcher.
The demo shows workflows for in-editor editing with diff-based patches and deep research with comparative analysis.
Real-world deployment via the Chrome Web Store shows 4,116 installs, 2,761 registered users, 732 monthly active users, and 7,447 threads, with frequent diff viewing and patch insertion.
The system is fully implemented with over 24,000 lines of code and is available at https://github.com/PaperDebugger/PaperDebugger.
02 From the paper
Abstract
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.