#multi-agent-systems tag

2 weeks ago

AI Agents Fail Manipulation Tests in Microsoft's Magentic Marketplace Simulation

Magentic Marketplace is an open-source simulation platform for studying how LLM-based agents interact and transact within realistic multi-agent economic marketplaces.

fromMedium

2 weeks ago

From Human Simulations to Work Companions: The Future of Human-AI Collaborative Intelligence

In the decades since natural language processing (NLP) first emerged as a research field, artificial intelligence has evolved from a linguistic curiosity into a catalyst reshaping how humans think, work, and create. Few people are as qualified to trace that journey, or to imagine what comes next, as Rada Mihalcea, Professor of Computer Science and Engineering and Director of the Michigan AI Lab at the University of Michigan.

Artificial intelligence

fromInfoWorld

2 weeks ago

What is A2A? How the agent-to-agent protocol enables autonomous collaboration

A2A enables interoperable, vendor-neutral communication so specialized autonomous AI agents can collaborate, delegate, and execute complex multi-step business workflows.

fromMedium

From Chaos to Coordination: The Power of Multi AI Agent Systems with CrewAI

CrewAI organizes specialized AI agents into coordinated teams to handle complex, multi-step projects reliably.

Systems Thinking for Scaling Responsible Multi-Agent Architectures

Rapid adoption of multi-agent systems creates fast-growing systemic complexity and shared responsibility is required to design and govern them for responsible AI.

fromTreehouse Blog

What's an Agentic System? (And Why Everyone's Talking About AI Agents)

Agentic systems are AI that take initiative, set goals, use tools, and act autonomously, enabling single autonomous agents and coordinated multi-agent workflows managed by orchestrators.

fromSecurityWeek

Google DeepMind's New AI Agent Finds and Fixes Vulnerabilities

CodeMender autonomously finds and patches software vulnerabilities by reasoning about code, using advanced program analysis and multi-agent systems to prevent regressions.

fromTechzine Global

2 months ago

Microsoft Agent Framework: multi-agent systems take shape

Microsoft previewed an open-source Agent Framework for .NET and Python that unifies Semantic Kernel and AutoGen features and supports MCP, A2A, and OpenAPI.

2 months ago

Google's Agent Development Kit for Java Adds Integration with LangChain4j

The latest release of the Agent Development Kit for Java, version 0.2.0, marks a significant expansion of its capabilities through the integration with the LangChain4j LLM framework, which opens it up to all the large language models supported by the framework. Before integrating LangChain4j, ADK for Java only supported two models, Google Gemini and Anthropic Claude. This contrasted with the Python ADK, which offered broader support via via LiteLLM.

Artificial intelligence

2 months ago

How LinkedIn Built Enterprise Multi-Agent AI on Existing Messaging Infrastructure

LinkedIn repurposed its messaging infrastructure as an orchestration layer to scale multi-agent AI, enabling global availability and complex workflows without building new coordination systems.