About
Research & Development
SATQuest: A New Approach to Evaluating and Enhancing AI’s Logical Reasoning
TLDR: SATQuest is a novel verifier designed to systematically evaluate and improve Large Language Models' (LLMs) logical reasoning. It generates diverse, Satisfiability-based problems across...
Research & Development
AI Explanations: A New Frontier in Teaching Humans Active Learning
TLDR: A new method called LENS (Logic Programming Explanation via Neural Summarisation) uses AI to automatically generate natural language explanations for machine-learned logic programs,...
Research & Development
The Future of Data: Redesigning Systems for LLM Agents
TLDR: This research paper proposes a new architecture for data systems to efficiently support Large Language Model (LLM) agents, which are expected to become...
Research & Development
VERLTOOL: A New Standard for Training Tool-Augmented AI Agents
TLDR: VERLTOOL is a new open-source framework designed to improve how large language models (LLMs) learn to use external tools. It addresses common issues...
Research & Development
Unpacking How Language Models Simulate Reality: A Coin Toss Perspective
TLDR: This paper introduces "causal abstractive simulation," a formal framework to assess if a language model (LM) can simulate another system, using a fair...
Research & Development
AnchorRAG: A Multi-Agent Framework for Enhanced Open-World Question Answering with Knowledge Graphs
TLDR: AnchorRAG is a novel multi-agent collaboration framework designed to improve Retrieval-Augmented Generation (RAG) for Large Language Models (LLMs) in open-world question answering using...