-
AI agent research have attracted a lot of attention with the rapid development of Large Language Model (LLM) and Reasoning (RL or CoT Chain of Thought) technology. Generative AI Agents use LLM to plan, act and reflect on the memories from the environment as well as the interactions from other agents, just like the environment in Stanford's Generative Agents paper "Generative Agents: Interactive Simulacra of Human Behavior". The simulation environment usually consists of a environment (Such as A Small Town) and multiple AI Agents taking actions to make plans and achieve goals. Before making plans and taking actions, agents will retrieve related information from memories, which is a list of descriptions of the timestamp and exact events, such as "2023-02-03 Someone is watching a movie...". During multi-agents simulation, each agent will have its own timeline and their actions are usually asynchronous. In this blog, we will give a review of the tools of AI Agents Visualization, especially in the situation where there are multiple agents with asynchronous actions during the simulation.
22Follow -
Dialogue Agent Multimodal Visualization Tools for AI Systems: A Review. With the rapid development of generative AI technology, developing Chatbot Assistant, Dialogue and Agents have become frequent tasks for designer, developer, product manager, machine learning and AI practitioner. There are a lot data (usually in json format) exchange during different phases of prototyping, designing and developing modern AI systems, such as Chatbot Assistant, Agent, Dialogue, AI Image Generator, text to image, AI video generator, etc. There are potential needs to help visualize the data (json format or others) for AI system. In this blog, we will introduce you an online dialogue data visualization tool DeepNLP Dialogue Visualization to help visualize the agents and dialogue history with simply a json string data. And we will use the OpenAI Dialogue GPT model for a multi-turn dialogue developing for example.