About
Research & Development
Beyond Final Answers: TRAJECT-Bench Evaluates AI Agents’ Tool-Use Journeys
TLDR: TRAJECT-Bench is a new benchmark for evaluating how large language model (LLM) agents use external tools. Unlike previous benchmarks that focus only on...
Research & Development
ContextNav: An Agentic Approach to Better Multimodal In-Context Learning
TLDR: ContextNav is an agentic framework that enhances multimodal in-context learning (ICL) by intelligently managing and refining contextual examples. It integrates automated retrieval with...
Research & Development
COSMIR: A New Approach to Long-Context Reasoning for AI Models
TLDR: COSMIR (Chain Orchestrated Structured Memory for Iterative Reasoning) is a novel framework designed to improve how large language models (LLMs) reason over very...
Research & Development
Unlocking Advanced AI Research with a Dual-System Framework
TLDR: MARS is a novel multi-agent AI system that integrates fast, intuitive thinking (System 1) with deliberate reasoning (System 2) to enhance Large Language...
News & Current Events
NTT Docomo Business Collaborates with Pier’s to Advance AI Systems for Financial Sector
TLDR: NTT Docomo Business has partnered with Japanese firm Pier's to develop advanced AI systems for the financial sector. This collaboration will leverage generative...
News & Current Events
IIFL Fintech Fund Secures 5x Return on Partial FinBox Exit, Announces New AI-Focused Fund
TLDR: IIFL Fintech Fund has successfully executed a partial exit from its investment in FinBox, a credit infrastructure and embedded finance platform, achieving a...