Research Assistant Review We've covered a few major LangGraph themes: * Memory * Human-in-the-loop * Controllability Now, we'll bring these ideas together to tackle one of AI's most popular applications: research automation. Research is often laborious work offloaded to analysts. AI has considerable potential to assist with this. However, research demands customization: raw LLM outputs are often poorly suited for real-world decision-making workflows. Customized, AI-based research and report generation workflows are a promising way to address this. Goal Our goal is to build a lightweight, multi-agent system around chat models that customizes the research process. Source Selection * Users can choose any set of input sources for their research. Planning * Users provide a topic, and the system generates a team of AI analysts, each focusing on one sub-topic. * Human-in-the-loop will be used to refine these sub-topics before research begins. LLM Utilization * Each analyst will conduct in-depth interviews with an expert AI using the selected sources. * The interview will be a multi-turn conversation to extract detailed insights as shown in the STORM paper. * These interviews will be captured in a using sub-graphs with their internal state. Research Process * Experts will gather information to answer analyst questions in parallel. * And all interviews will be conducted simultaneously through map-reduce. Output Format * The gathered insights from each interview will be synthesized int
Autonomy
Semi-autonomous
Sandbox-aware
No declared sandbox guidance
Network access
Unspecified
Filesystem access
Unspecified
Permissions declared
Not declared
Pattern
Multi-agent crew
Models
gpt-4oclaude-3-5-sonnetgpt-3.5-turbo