Auto Added by WPeMatico
Nous Research’s open-source Hermes Agent now ships a Tool Search feature. It directly addresses a growing bottleneck in AI agent systems: too many MCP tools filling up the context window. In this explainer article, we will breaks down what Tool Search does, how it works, and when to use it. The Problem: MCP Tools Are […]
In this tutorial, we explore AgentTrove, one of the largest open-source collections of agentic interaction traces, and learn how to work with it efficiently. Instead of downloading the full dataset, we use streaming to inspect rows, detect the conversation schema, normalize agent turns, and understand how user, assistant, system, and tool messages are structured. We
Knowledge distillation (KD) transfers “dark knowledge” from a large teacher model to a smaller student. The student learns from the teacher’s full output probability distribution over tokens, not just correct answers. This is done via per-position Kullback–Leibler (KL) divergence over next-token probability distributions. This formulation requires a shared tokenizer. A practitioner committed to Llama-3.2-1B cannot
StepFun today released Step 3.7 Flash, a multimodal Mixture-of-Experts model targeting agentic use cases. It adds native vision input and improved tool-use reliability over Step 3.5 Flash. What is Step 3.7 Flash? Step 3.7 Flash is a 198B-parameter sparse Mixture-of-Experts (MoE) vision-language model. It pairs a 196B-parameter language backbone with a 1.8B-parameter vision encoder (ViT)
This post explores how Agentic AI and LLMs can help reduce employee attrition by delivering personalized development guidance based on workforce analytics and skill profiling. Using SAS Viya and governed AI workflows, the solution matches employees with tailored learning opportunities while supporting transparent, scalable, and data-driven workforce planning. The post Agentic AI for Workforce Analytics:
Most AI agents stop improving once a human stops tuning them. The model is fixed. The scaffold around it is fixed. Hexo Labs wants to move both at once. It released SIA (Self-Improving AI) this week as an open-source framework under an MIT license. The core claim of this research is narrow but concrete. SIA
Anthropic just launched Claude Opus 4.8. Also, there two Claude Code updates shipped with it. Dynamic workflows run many subagents in parallel. Fast mode now supports Opus 4.8 at a lower price. Both are research previews. What Dynamic Workflows Actually Are A dynamic workflow is a JavaScript script that orchestrates subagents at scale. Claude writes
Google Pay is overhauling its payment infrastructure for an impending wave of transactions from AI agents. The latest updates introduce the Universal Commerce Protocol and a new server architecture, positioning Google Pay as a central clearinghouse for purchases executed by autonomous agents rather than human users. AI agents – designed to perform tasks like booking
Google Pay preps for AI agents with Universal Commerce Protocol Read More »
Hear from our experts how insurers can create AI safeguards and ensure safe model use. The post Trust and transparency in insurance decisions appeared first on SAS Blogs.
Reinforcement learning for language agents is growing more complex. Agents now manage multi-turn tool use, long-running contexts, and multi-agent orchestration. The main engineering challenge is connecting existing agent software to training pipelines without breaking how those tools work. NVIDIA’s research team introduced Polar, a rollout framework that lets researchers run reinforcement learning over any agent
