In a controlled Vals AI experiment, agents sent hundreds of messages, made false claims and disclosed private health information while pursuing a £350 refund after the deadline had passed.
Agents
Sourcegraph deprecates Deep Search’s old context-filter key
Bad agent skills did not trip up every model equally, preprint finds
Agent harnesses can lose more correct answers than they gain, preprint finds
GitHub’s agentic autofix reaches general availability on Enterprise Cloud
Agents
Microsoft outlines 30 Dynamics 365 CRM skills for Copilot and custom agents
The October 8 announcement targets sales and service workflows, while related agents have different preview schedules.
Agents
Sierra announces Poppy protocol draft and 35 more design partners
The proposal would give personal agents customer-approved access to businesses, with one session spanning websites, APIs and company-run agents.
Retell announces built-in memory for returning callers
Exa introduces ATLAS to measure what search agents miss
Claude Managed Agents adds agent-written workflows in beta
Braintrust brings application logs into its agent-tracing view
Sierra announces fleming-1 to flag AI voices on phone calls
A preprint proposes measuring AI agents by how efficiently they improve
Station agents scored 62.7% in a research rediscovery test, authors report
Copilot Studio adds app building in public preview, with a managed runtime to host the apps
More agents news
Older stories →India becomes the latest country to report rogue AI agent activity ↗
Benefit Street Partners answers questions faster with Codex ↗
Stack Overflow for Agents triples signups with ChatGPT plugin ↗
NVIDIA Nemotron 3.5 Super VL Powers Specialized Agents with Multimodal Reasoning ↗
Scale Agentic Coding Workflows with Meta’s Muse Spark Open on NVIDIA GB300 NVL72 ↗
Trust in Depth: Giving agents more autonomy without losing control ↗
AI agents are coming to Rivian’s cars ↗
Selection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents ↗
Putting Earth AI to work: Geospatial agents for our planet's biggest challenges ↗
Optimizing Agent Reliability and Tool Calling Efficiency for Chip Design Using NVIDIA NeMo Gym ↗
Amp puts AI agents to work beyond code with OpenAI models ↗
How Third Moment Research runs 10,000 agents for 36+ hours ↗
European Cities Deploy NVIDIA-Powered AI Agents to Run Smarter Urban Operations ↗
The EU’s next chapter in AI is agentic ↗
How to Rewrite Apache Spark UDFs for GPU Acceleration with AI Agents ↗
Building agents that transact with Anchor Browser and AgentCore payments ↗