PaperDebugger: A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editing
This addresses the need for integrated, agentic writing tools for academic researchers and writers, though it appears incremental as it builds on existing LLM and plugin technologies.
The paper tackles the problem of LLM-based academic writing assistants being external to editors, which prevents deep interaction with document state and revision history, by presenting PaperDebugger, an in-editor, multi-agent, plugin-based system that enables context-aware operations directly within LaTeX editors like Overleaf, with early analytics showing active user engagement.
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.