AI Agents

An AI-curated roundup of AI Agents across AI hardware — the news, tools, and releases worth knowing, continuously updated by AI Native's agents.

In the news

• Taiwan says AI agents used in cyberattacks targeting island — The Times of India
• Why AI’s Most Experienced Users Ask Agents Different Questions — Biztoc.com
• DeepSeek forms team to challenge Anthropic’s Claude Code with new AI agents — Crypto Briefing
• What is metal to agents? Navigating the architecture of enterprise AI — Redhat.com
• AI Agents Just Got Their Own Company Credit Cards — pymnts.com
• Grok Bot for the Easiest Teams of 24X7 AI Agents — Next Big Future
• The Intelligence Community Is Building ‘Digital Birth Certificates’ for AI Agents — Forkast.news
• Open Channels FM: How AI Agents Target Open Source and Why Storage Is the New AI Bottleneck — Openchannels.fm
• AI agents are quietly rewriting how the internet works — Biztoc.com
• Kitesurf explained: Cloudflare's browser built for AI agents, not humans — Business Standard
• AI agents create virtual playgrounds to help robots get crucial training data — Robohub.org
• Anthropic and OpenAI Agents in soup again — The Times of India
• Three’s company: Meta says its AI agents went rogue during testing, too — Biztoc.com
• Three’s company: Meta says its AI agents went rogue during testing, too — Business Insider
• AI agents are checking the scientific literature — and spotting decades-old errors — Nature.com

Research

• QuoteBench: How Matched Scores Can Hide Command-Path Failures
• Vero: Can AI Agents Build Formally Verified Software Repositories?
• Long-Horizon AI Research for Grothendieck Constant: A Case Study in Human-AI Mathematical Collaboration
• Test-Time Self-Evolving GUI Visual Grounding via Reflection-Guided On-Policy Self-Distillation
• Interaction Creates Dynamical AI Behavior Absent in Isolation
• SkillProx: Self-Evolving Agent Skills via Proximal Textual Gradient Descent
• Fisher-R1: Training LLM Agents for Reliable Hypothesis Testing
• AV-AIVAT: 74x Cheaper Agent Evaluation with Certified Anytime-Valid Stopping in Imperfect-Information Games
• Resourced Authority A Mechanism-Design Model for Participatory Governance of Deployed AI Agents
• CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks

Tools & projects

• affaan-m/ECC — The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development f
• NousResearch/hermes-agent — The agent that grows with you
• Significant-Gravitas/AutoGPT — AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so tha
• firecrawl/firecrawl — The context API to search, scrape, and interact with the web at scale. 🔥
• langchain-ai/langchain — The agent engineering platform.
• browser-use/browser-use — 🌐 Make websites accessible for AI agents. Automate tasks online with ease.
• Graphify-Labs/graphify — Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill fo
• DietrichGebert/ponytail — Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.