Tag: Released

Introducing AgentFlow: A Revolutionary Framework for AI Agents AgentFlow is an innovative framework for developing trainable AI agents, structured around four key modules: Planner, Executor, Verifier, and Generator. By implementing an advanced policy optimization method named Flow-GRPO, AgentFlow enhances the performance of agents in multi-turn, tool-integrated reasoning. What is AgentFlow? AgentFlow formalizes tool-using agents into […]

Liquid AI Unveils LFM2-Audio-1.5B: A Breakthrough in Audio-Language Models Liquid AI has recently launched LFM2-Audio-1.5B, an innovative audio-language foundation model designed to seamlessly understand and generate both speech and text. This model is tailored for low-latency, real-time applications on resource-constrained devices, further enhancing the LFM2 family by integrating audio capabilities while maintaining a compact footprint. […]

Delinea’s New Model Context Protocol Server: Enhancing AI-Agent Security Delinea has unveiled an innovative Model Context Protocol (MCP) server designed to enhance AI-agent access to credentials securely. This system aims to maintain the integrity of sensitive data while ensuring comprehensive audit trails. What’s New? The Delinea MCP server is now available on GitHub, offering a […]

ShinkaEvolve: Revolutionizing Program Evolution with AI Sakana AI has unveiled ShinkaEvolve, a groundbreaking open-source framework designed to leverage large language models (LLMs) as mutation operators in a unique evolutionary loop. This innovative approach not only accelerates the evolution of programs for scientific and engineering challenges but also significantly reduces the number of evaluations needed for […]

Meta Releases MobileLLM-R1: A Game Changer in Edge Reasoning Meta has recently unveiled its new lightweight AI model, MobileLLM-R1, which is designed for efficient edge deployment. This family of reasoning models ranges from 140M to 950M parameters and aims to provide superior performance in mathematical, coding, and scientific tasks without the hefty resource requirements of […]

Streamline LLM Performance with BentoML’s New llm-optimizer BentoML has introduced llm-optimizer, an innovative open-source framework aimed at optimizing the benchmarking and performance tuning of self-hosted large language models (LLMs). This tool addresses the complexities associated with LLM deployment, making it easier to achieve the best configurations for latency, throughput, and cost. Why is Tuning LLM […]