Search Results for author:
Found 2 papers, 0 papers with code
From LLM to Conversational Agent: A Memory Enhanced Architecture with Fine-Tuning of Large Language Models
This paper introduces RAISE (Reasoning and Acting through Scratchpad and Examples), an advanced architecture enhancing the integration of Large Language Models (LLMs) like GPT-4 into conversational agents.
DUMA: a Dual-Mind Conversational Agent with Fast and Slow Thinking
The fast thinking model serves as the primary interface for external interactions and initial response generation, evaluating the necessity for engaging the slow thinking model based on the complexity of the complete response.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
