Technology & AI
AI agents learn your standards, up to 20.9% better
New preprint: AI agents learn individual standards through interaction, lifting task success up to 20.9% for professionals needing personal quality.
AI Agents
98 stories
Technology & AI
Environment evolution for terminal agents: 18-point gain
New arXiv preprint: terminal AI agents gain 14 to 18 benchmark points by training against progressively harder environments. Results are unverified.
Technology & AI
Vercel Labs agent-browser hits 41,800 GitHub stars
Vercel Labs' agent-browser, a Rust CLI that lets AI agents drive Chrome without Node.js or Playwright at runtime, is trending on GitHub with 41,800 stars.
Technology & AI
New technique cuts AI agent wait time up to 45%
SMC pairs a small drafter model with a large actor model to speculatively execute tool calls, reducing wall time by up to 45% on AppWorld.
Technology & AI
Prompt injection attack on AI agents jumps to 28% success
SIR, a self-improving prompt injection attack, raised its success rate from 0% to 28% on Gemini 3.5 Flash while the agent's legitimate task still
Technology & AI
AIMC dashboard flags recurring flaws in AI-generated science
AIMC, a visual analytics framework, lets researchers track quality, themes and weaknesses across papers produced by autonomous AI scientist FARS.
Technology & AI
DiaSentinel AI agents screen diabetes risk on-premise
DiaSentinel, a new arXiv preprint from a Taiwan hospital team, describes a fully on-premise multi-agent system for type 2 diabetes risk screening from
Technology & AI
AI coding agent defense cuts malware severity 83%
SkillShield bakes security skills into the system prompt, dropping malware severity from 3.37 to 0.58 across six models while refusing just 0.14% of benign
Technology & AI
StepGuard blocks AI agent attacks 77% before they run
StepGuard from Shanghai AI Lab checks AI agent tool calls before execution, cutting attack success 77% while losing just 2.8 points of utility.
Technology & AI
Vibe coding: security prompt halves AI app flaws
An arXiv preprint found adding security requirements to AI coding prompts cut confirmed flaws from 51 to 24 across six web apps, with zero critical issues.
Technology & AI
Google Gemini CLI hits 106,000 stars with free 1,000-request daily tier
Google's Gemini CLI offers 1,000 free AI requests daily in the terminal, with a 1M token context window and Gemini 3 models. Now 106,000 stars.
Technology & AI
NVIDIA Groq 3 LPX hits full production at 3,400 tokens/second
NVIDIA's Groq 3 LPX inference accelerator is now in full production, delivering a record 3,400 tokens/second for agentic AI workloads.