About
Research & Development
Personalized Math Learning: A Multi-Agent AI Approach
TLDR: A new multi-agent AI tutoring platform for math education is introduced, moving beyond reactive assistance to offer structured, personalized, and tool-assisted learning. It...
Research & Development
Unmasking AI Lies: Evaluating Deception Detection Tools
TLDR: This research paper introduces a new methodology to benchmark "deception probes," which are tools designed to detect when AI assistants are lying. By...
Research & Development
Smart AI for Smarter Peer Learning: Mimicking Errors for Better Outcomes
TLDR: A study proposes an AI-based peer learning environment where a Learning Companion AI Agent (LCAA) intentionally imitates a user's grammatical mistakes. This method,...
Research & Development
Deep Evaluation for LLM Agents: Introducing MCPEval
TLDR: MCPEval is an open-source, automated evaluation framework for AI agents powered by Large Language Models (LLMs). It uses the Model Context Protocol (MCP)...
Research & Development
Advancing Emotional Support Conversations with Fine-Tuned Large Language Models
TLDR: This research paper details an innovative approach to Emotional Support Conversation (ESC) using large language models (LLMs). The authors, Shiquan Wang, Ruiyu Fang,...
Research & Development
A New Framework for Evaluating AI’s Adaptive Intelligence Through Novel Games
TLDR: A new research paper proposes evaluating AI's ability to rapidly adapt and learn "world models" in genuinely new situations using "novel games." Unlike...