发表机构
Lehigh University; University of Illinois Chicago; University of Pennsylvania; University of Maryland; University of Notre Dame; University of British Columbia（利哈伊大学; 伊利诺伊大学芝加哥分校; 宾夕法尼亚大学; 马里兰大学; 圣母大学; 不列颠哥伦比亚大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出开源AI科学家工作空间Dr. Claw，以人在回路编排层整合现有编码智能体，提升研究完整性并保留可审计过程轨迹，通过对比实验验证其优势。
AI 中文摘要
命令行编码智能体（如Claude Code、Gemini CLI）已具备读写文件、维持长会话的能力，但端到端研究仍分散在聊天工具、IDE、终端和写作环境中，且保障可审计性的决策极少被保留。我们提出Dr. Claw，这是一个开源工作空间，它将现有编码智能体执行器包装成可控且可审计的人在回路工作流，而非引入另一个自主智能体。持久状态对象、可复用技能库和多执行器协调机制，将人类决策与AI执行关联，把规划、执行和写作转化为可追踪、可恢复的闭环。我们通过交互式三视图场景和故障恢复演练演示Dr. Claw，并将其与使用相同后端执行器的纯命令行智能体对比，以此将整个编排层（任务图、状态对象和技能库）与其包装的智能体进行比较。在执行器固定的情况下，Dr. Claw在研究完整性上得分更高，同时保留了可审计、可恢复的过程轨迹。演示访问：代码仓库为this https URL，基于AGPL-3.0许可发布，包含GPL-3.0上游组件。
英文摘要
Command-line coding agents (e.g., Claude Code, Gemini CLI) can already read and write files and sustain long sessions, yet end-to-end research still fragments across chat tools, IDEs, terminals, and writing environments, and the decisions that make it auditable are rarely preserved. We present Dr. Claw, an open-source workspace that wraps existing coding-agent executors in a controllable and auditable human-in-the-loop workflow rather than introducing another autonomous agent. Persistent state objects, a reusable skill library, and multi-executor coordination link human decisions to AI execution, turning planning, execution, and writing into one traceable, recoverable loop. We demonstrate Dr. Claw through an interactive three-view scenario and a failure-recovery walkthrough, and evaluate it against a bare command-line agent sharing the same backend executor, so the comparison contrasts the whole orchestration layer (task graph, state objects, and skill library) with the agent it wraps. Holding the executor fixed, Dr. Claw scores higher on research completeness while persisting an auditable, recoverable process trail. Demo access: repository https://github.com/OpenLAIR/dr-claw, released under AGPL-3.0 with GPL-3.0 upstream components.
CommentsAccepted to EMNLP 2026 System Demonstrations. Code: https://github.com/OpenLAIR/dr-claw
