Tootfinder

Trusted Agent Protocol: Wie Visa Zahlungen zwischen KI-Agenten absichern will
Mit kryptografischen Signaturen, Agenten-Identitäten und interoperablen Schnittstellen will Visa Zahlungen zwischen KI-Agenten und Handel sicher gestalten.

Less than 48 hours after joining Bluesky,
the White House has already become one of the most blocked accounts on the social network.
According to ClearSky, which tracks Bluesky blocking stats,
the White House account is blocked by around 91,000 accounts, while being followed by only 10,000.
The only account that’s been blocked by more Bluesky users belongs to Vice President JD Vance, who joined back in June. 
While the various new government accounts hadn’t qu…

The White House is already one of the most blocked accounts on Bluesky | TechCrunch
The Trump administration is taking its social media attacks on Democratic opponents to an unlikely platform, with the White House and numerous other government agencies joining Bluesky on Friday.

Sentinel Agents for Secure and Trustworthy Agentic AI in Multi-Agent Systems
Diego Gosmar, Deborah A. Dahl
https://arxiv.org/abs/2509.14956 https://arxiv.o…

Sentinel Agents for Secure and Trustworthy Agentic AI in Multi-Agent Systems
This paper proposes a novel architectural framework aimed at enhancing security and reliability in multi-agent systems (MAS). A central component of this framework is a network of Sentinel Agents, functioning as a distributed security layer that integrates techniques such as semantic analysis via large language models (LLMs), behavioral analytics, retrieval-augmented verification, and cross-agent anomaly detection. Such agents can potentially oversee inter-agent communications, identify potenti…

OpenAI's ChatGPT Agent System Card outlines how its red team helped implement key security features like "Watch Mode Activation" and "Terminal Restrictions" (Louis Columbus/VentureBeat)
https://venturebeat.com/security/openais…

How OpenAI’s red team made ChatGPT agent into an AI fortress
Discover OpenAI's red team blueprint: How 110 coordinated attacks and 7 exploit fixes created ChatGPT Agent's revolutionary 95% security defense system.

MACTAS: Self-Attention-Based Module for Inter-Agent Communication in Multi-Agent Reinforcement Learning
Maciej Wojtala, Bogusz Stefa\'nczyk, Dominik Bogucki, {\L}ukasz Lepak, Jakub Strykowski, Pawe{\l} Wawrzy\'nski
https://arxiv.org/abs/2508.13661

MACTAS: Self-Attention-Based Module for Inter-Agent Communication in Multi-Agent Reinforcement Learning
Communication is essential for the collective execution of complex tasks by human agents, motivating interest in communication mechanisms for multi-agent reinforcement learning (MARL). However, existing communication protocols in MARL are often complex and non-differentiable. In this work, we introduce a self-attention-based communication module that exchanges information between the agents in MARL. Our proposed approach is fully differentiable, allowing agents to learn to generate messages in …

Verbesserte Akkunutzung: iOS 26 gibt Hinweise an Nutzer
Neben einem neuen adaptiven Modus zur Akkusparsamkeit reicht Apple in iOS 26 eine weitere neue Batteriefunktion nach. Nutzer bekommen nun explizite Hinweise.
ht…

AgentCompass: Towards Reliable Evaluation of Agentic Workflows in Production
NVJK Kartik, Garvit Sapra, Rishav Hada, Nikhil Pareek
https://arxiv.org/abs/2509.14647 https://

AgentCompass: Towards Reliable Evaluation of Agentic Workflows in Production
With the growing adoption of Large Language Models (LLMs) in automating complex, multi-agent workflows, organizations face mounting risks from errors, emergent behaviors, and systemic failures that current evaluation methods fail to capture. We present AgentCompass, the first evaluation framework designed specifically for post-deployment monitoring and debugging of agentic workflows. AgentCompass models the reasoning process of expert debuggers through a structured, multi-stage analytical pipel…

Firecrawl, which offers an open-source web crawler for developers and AI agents, raised a $14.5M Series A led by Nexus Venture Partners (Julie Bort/TechCrunch)
https://techcrunch.com/2025/08/19/ai-crawler-firecrawl-raises-14-5…

AI crawler Firecrawl raises $14.5M, is still looking to hire agents as employees | TechCrunch
Firecrawl nabbed Shopify’s CEO Tobias Lütke as an investor from a gutsy email after they discovered he was using the product.

Zoom veröffentlicht AI Companion 3.0 – mit agentischen Fähigkeiten
Der KI-Assistent in den Arbeitsumgebungen von Zoom bekommt ein agentisches Update. Das hilft Nutzern wie auch potenziell Kunden.
https://…

Grammarly debuts AI agents for writing and grading assistance, including an AI grader and a citation finder agent, available for Grammarly Free and Pro users (Jess Weatherbed/The Verge)
https://www.theverge.com/news/760508/grammarly-ai-agents-help-students-ed…

Grammarly says its AI agent can predict an A paper
Grammarly is launching several new AI agents for specific writing challenges for educators and students. It can catch plagiarism and even predict a grade.