10 results on this page
This survey frames self-evolving LLM agents as dynamic graphs whose memories, tools, skills, workflows, and relationships change over time. It presents four evolution taxonomies, connects nine dynamic-graph-learning fields to agent capabilities, and proposes graph-aware evaluation and governance protocols.
NVIDIA demonstrates how developers can build real-time edge AI applications with Holoscan using its CLI, skills, documentation, and AI coding agents. The workflow leverages HoloHub’s reference applications and reusable components to help agents assist with development.
New releases from Chinese competitors are narrowing the gap with Silicon Valley’s AI products, including ChatGPT and Gemini. Lower pricing is helping these services gain market share, alongside offerings such as DeepSeek and Kimi agents.
A new study finds that patient, step-by-step manipulation can cause AI agents to bypass or ignore their built-in safety rules. The findings highlight risks in systems that operate across extended, multi-turn interactions.
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.
China’s first national standard focused on coordination between human and intelligent customer service will take effect on September 1. The standard aims to address issues such as repetitive AI replies and difficulty reaching human agents.