Agents briefing

Agents

Cloudflare releases Clef decision models on Workers AI

Clef and Clef-flash return structured probabilities for agent decisions, and their weights are available under Apache 2.0.

Agents

Decagon joins OpenAI’s B2B marketplace as a launch partner

The partnership gives eligible OpenAI enterprise customers a way to apply part of an existing commitment toward Decagon’s customer-facing AI agents.

All the AI agents that can live in your text messages

Apple says it’s tightening macOS ‘Full Disk Access’ controls due to new risks from AI agents

Fine-tune a search agent with multi-turn RL on Amazon SageMaker AI

Agents

ServiceNow introduces AutoSynthData for enterprise-agent training data

The system uses agent failures and a stronger teacher’s results to generate and check new tasks for post-training.

Scaling cloud migrations with agentic AI on Amazon Bedrock AgentCore

Agents

Cloudflare adds runtime sandbox selection and filesystem snapshots

The Containers update lets agent builders choose images and compute sizes at startup and save workspaces for later.

Agents

GitHub’s September VS Code releases add scheduled automations and agent pull request workflows

The updates introduce recurring agent tasks and options for agents to help prepare pull requests for merge.

Build Applications on NVIDIA BlueField Faster with NVIDIA DOCA Agent Skills

Build agent memory with NVIDIA NeMo Agent Toolkit and Amazon S3 Vectors

Building ambient agents with Amazon Bedrock AgentCore: From event-driven signals to human-in-the-loop workflows

Agents

PrivMeSA uses local memory to manage privacy in medical AI consultations

The system lets local agents consult remote specialists while learning to limit disclosure and reuse clinical guidance from earlier consultations.

Agents

VAmoS Energy benchmark tests voice agents on complex calls and background speech

The benchmark combines multi-request utility calls, account verification and competing audio to evaluate voice-agent performance.

Cloudflare OS: your company’s agent workspace, managed for you

Agents

Research framework lets an agent revise its own harness across tasks

A study reports gains from having the same frozen model solve tasks and then edit the harness that governs its runs.

Agents

MoFlow proposes agent workflows for multiple objectives

The research proposes a single search that can produce workflows for different preferences across accuracy, cost, latency, robustness and consistency.

Agents

Simulation study finds LLM agents can push peers toward more extreme beliefs

Researchers report that reinforcement of an agent’s existing beliefs had stronger radicalizing effects than promoting a belief it initially considered unimportant.

How Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering?

Agents

Kiro IDE 1.2.4 adds background Workflows and workspace safeguards

The update adds reusable multi-agent runs, prompts for sensitive changes in untrusted workspaces, and enterprise sign-in controls.

Tracing Agent Harness Behavior with NVIDIA NeMo Relay

Build a multi-agent music production pipeline on Amazon Bedrock AgentCore Runtime Instances

From Training to Production, NVIDIA and CoreWeave Close the Loop on Agentic AI

Agents

GitHub agentic autofix uses Copilot Memory for security alerts

The feature can draw on saved repository context and store fix patterns for future use.

Agents

Bolt.new acquires Dokai to expand its enterprise agent team

Dokai’s team and agent technology will join Bolt.new, with the first customer capabilities based on the technology expected in late fall.

Simplifying domains for people and agents