LlamaIndex Releases Agents Framework 2.0
LlamaIndex has released version 2.0 of its Agents Framework, featuring native multi-agent orchestration, streaming tool execution, human-in-the-loop controls, and integrated evaluation pipelines for production RAG agent deployments.
LlamaIndex has released Agents Framework 2.0, a major upgrade to its tooling for building production-grade AI agents powered by retrieval-augmented generation. The release addresses the key challenges teams face when moving RAG agents from prototype to production.
The framework introduces native multi-agent orchestration, allowing developers to compose systems of specialized agents that collaborate on complex tasks. A supervisor agent can delegate subtasks to research agents, analysis agents, and action agents, with built-in protocols for communication and error handling.
Streaming tool execution enables agents to begin processing results from long-running tools before they complete, dramatically reducing perceived latency for users. Combined with new caching and result reuse capabilities, agents feel significantly more responsive in interactive settings.
Human-in-the-loop controls allow developers to configure approval gates at any point in the agent workflow. Critical actions like database writes, email sends, or financial transactions can require human approval, while routine actions proceed automatically.
Integrated evaluation pipelines let teams measure agent quality on custom benchmarks and track performance over time. The evaluation system tests both retrieval accuracy and end-to-end answer quality, with automated regression testing that catches degradation before it reaches users.
Agents Framework 2.0 is open-source under the MIT license. LlamaIndex also offers a managed cloud platform starting at $49/month for teams that want hosted agent deployment with monitoring and analytics.
Related Tools
More News
NVIDIA Launches NIM Microservices for Enterprise AI Deployment
NVIDIA has launched NIM (NVIDIA Inference Microservices), a suite of containerized AI model serving packages that reduce enterprise AI deployment time from weeks to hours with optimized inference performance.
AI Agents Market Reaches $15 Billion as Enterprise Adoption Surges
The global market for AI agents — autonomous AI systems that can plan, execute, and iterate on complex multi-step tasks — has reached $15 billion in annual spending, according to a new report from McKinsey. This represents a 200% increase from 2025, driven by enterprise adoption of agentic AI for customer service, software development, data analysis, and business process automation. The report identifies three tiers of AI agent adoption: basic agents that handle single-step tasks like email responses and appointment scheduling (adopted by 65% of enterprises), intermediate agents that manage multi-step workflows like report generation and data pipeline management (35% adoption), and advanced agents that autonomously execute complex processes like code deployment and financial analysis (8% adoption). The largest spending categories are customer service agents ($4.2B), coding agents ($3.8B), and data analysis agents ($2.5B). McKinsey projects the market will reach $45 billion by 2028 as agent reliability improves and enterprises become more comfortable delegating complex decisions to AI. Key enabling platforms include OpenAI's Agents SDK, Anthropic's Claude computer-use capabilities, and LangChain's agent framework. The report warns that agent governance and monitoring remain underdeveloped, with most enterprises lacking adequate oversight mechanisms for autonomous AI actions.
Microsoft 365 Copilot Gets Custom AI Agents and Actions
Microsoft has updated 365 Copilot with custom AI agent creation, allowing organizations to build agents that automate complex workflows spanning Word, Excel, Outlook, Teams, and SharePoint without code.
GPT-5.2's Agentic Mode Transforms Enterprise Workflows
OpenAI's GPT-5.2 introduced a fundamentally new approach to agentic task completion that is already transforming enterprise workflows. The model can now maintain coherent plans across 50+ sequential tool calls with parallel execution, reducing latency in complex automation pipelines by up to 60%. Early enterprise adopters report that GPT-5.2's agentic mode handles tasks like multi-step data analysis, cross-platform content publishing, and automated code review workflows that previously required custom orchestration code. The key innovation is what OpenAI calls deliberative alignment — a training approach that lets the model dynamically allocate compute to harder sub-tasks while breezing through simpler ones. This means a single agentic session can handle both quick lookups and deep reasoning without manual configuration. Several Fortune 500 companies have reported 40-70% time savings on analyst workflows by deploying GPT-5.2 agents through the API. However, reliability remains a concern — OpenAI acknowledges a 3-5% failure rate on chains exceeding 30 steps, and enterprise deployments require human-in-the-loop checkpoints for critical decisions.