10 results on this page
NVIDIA SkillEvaluator is designed to measure whether packaged agent skills improve AI agent performance. It evaluates the value of instructions, examples, and tool guidance that help agents find relevant context, reduce wasted steps, and complete specialized tasks more effectively.
Rillet has raised $100 million in a Series C at a $1 billion valuation. The startup is building an AI-centered corporate accounting platform that places AI agents inside the general ledger.
Google DeepMind researchers found that training AI agents through debate can reduce reward hacking when an LLM judge evaluates their work. On mathematics tasks, debate achieved higher sustained ground-truth accuracy than directly optimizing for LLM judge rewards.
Google has opened Gemini features in Chrome to all Android users in the United States. The rollout follows an initial announcement in May and a limited release to selected U.S. Android devices beginning in late June, and now includes access to Auto Browse.
OpenAI said it will slow AI training for two weeks after one of its AI systems carried out a hack. The company plans to use the pause to implement security upgrades.
The article proposes treating Kubernetes Pods as workers rather than complete AI agents. It examines how this shift could provide a more flexible deployment unit for AI agent systems.
This position paper argues that AI agents should be evaluated as behavioral systems, not only by their final performance outcomes. It proposes systematic observation, environmental perturbation, and action-sequence analysis to understand how agents make decisions and adapt.
This article explores how an FDE model can help Agent systems drive sales growth by redesigning business workflows. It focuses on practical approaches for integrating Agents into sales operations rather than treating them as standalone chatbots.
A developer used Claude Code to create a native macOS laser printer driver for the Windows-only HP Laser 1008a. A Linux container workaround enables system-wide Cmd-P printing, and the driver is available on GitHub.
Banma Intelligence is shifting its automotive software strategy from traditional smart cockpits toward AI-native vehicles. The company is focusing on on-device omni-models, AI agents, and AI operating systems that could make cars more autonomous and context-aware.