Tag: Agents

BuilderBench is a new benchmark for AI agent pre-training, challenging agents to build structures and fostering open-ended exploration & embodied ...

New research explores 'Autonomous Manager Agents' to orchestrate human-AI collaboration & identifies key challenges like compositional reasoning & ethical compliance. ...

Docker at AI Engineer Paris: Learn how Docker is simplifying agent lifecycle, democratizing AI development with standardized packaging & secure ...

New research introduces Hierarchical Preference Learning (HPL) to solve granularity mismatch in LLM agent training, improving performance on complex tasks.

New benchmark & model PolicyGuardBench/PolicyGuard-4B detect policy violations in web agents, enabling safer, compliant AI interactions across domains.

Introducing AstaBench: a novel AI agents evaluation framework simulating realistic scientific research workflows & assessing reasoning beyond simple task completion.

Discover how AI-powered science agents are revolutionizing research workflows, automating tasks, and boosting reproducibility. Learn more about CrewAI and the ...

Deploy Deep AI agents like LangGraph's Deep Agents on Amazon Bedrock AgentCore Runtime for secure, scalable production environments. Learn how ...

Learn how Writer and Premji Invest envision agentic AI's future: full-stack systems, adaptive models & IT-business collaboration at enterprise scale.

Discover the new GitHub MCP Registry! Find & use MCP servers easily with this central hub for agentic workflows, improving ...

Unlock the future of automation! Discover how sophisticated AI agents are revolutionizing workflows, boosting productivity & paving the way for ...

Google's ADK 0.2.0 now integrates with LangChain4j, enabling Java developers to leverage third-party language models for agent development & increased ...

Build trust in AI agents with Amazon Bedrock AgentCore Observability, streamlining monitoring & auditing across frameworks & deployments.

AI's rapidly evolving! Discover how sophisticated software *agents* are transforming workflows, automating tasks, and boosting productivity across various industries—and what ...

Protect your data from evolving threats! Discover essential strategies for bolstering artificial intelligence security and safeguarding against vulnerabilities in today's ...

A2A Extensions provide flexible custom functionalities for agent-to-agent communication, enabling specialized features & open implementation for developers.

Explore how Multi-Agent Systems (MAS) are revolutionizing cyber defense with AI. Learn about their architecture, benefits & future trends in ...

Build & scale AI agents for education using Strands Agents, Amazon Bedrock AgentCore, & LibreChat. Drive adoption with a familiar ...

Learn how to set up custom domain names for Amazon Bedrock AgentCore Runtime agents using CloudFront, improving branding & simplifying ...