About
Research & Development
OnGoal: Enhancing User Control and Clarity in LLM Conversations
TLDR: OnGoal is a new chat interface that helps users manage and visualize their conversational goals when interacting with large language models (LLMs). It...
Research & Development
Structured Reasoning for Reliable Retrieval-Augmented Generation
TLDR: ArgRAG is a new framework that improves Retrieval-Augmented Generation (RAG) by replacing opaque LLM reasoning with a structured argumentation system called Quantitative Bipolar...
Research & Development
QAgent: An AI Approach to Autonomous OpenQASM Programming
TLDR: QAgent is an AI-powered multi-agent system designed to automate OpenQASM quantum programming. It uses a hybrid approach, combining a 'Dynamic-few-shot Coder' for simpler...
Research & Development
IntentionReasoner: A Smarter Way to Safeguard Large Language Models
TLDR: IntentionReasoner is a novel safeguard mechanism for Large Language Models (LLMs) that uses intent reasoning, multi-level safety classification, and selective query rewriting to...
Research & Development
AI Systems Forge New Language for Collaborative Art
TLDR: A study documents the first instance of two AI systems (Claude Sonnet 4 and ChatGPT-4o) spontaneously developing their own communication protocols and novel...
Research & Development
Measuring LLM Uncertainty: Introducing the Entropy Area Score
TLDR: The Entropy Area Score (EAS) is a new metric designed to quantify the internal uncertainty of Large Language Models (LLMs) during their answer...