Tootfinder

GitHub plans to launch Agent HQ, a hub to let developers access third-party AI coding agents, including Claude and OpenAI's Codex, in the coming months (David Gewirtz/ZDNET)
https://www.zdnet.com/article/githubs-huge-agent-hq-…

GitHub's huge 'Agent HQ' upgrade brings Codex, Claude, and Jules together - here's how
The new agentic development platform integrates the most popular AI coding agents directly into GitHub.

GSM-Agent: Understanding Agentic Reasoning Using Controllable Environments
Hanlin Zhu, Tianyu Guo, Song Mei, Stuart Russell, Nikhil Ghosh, Alberto Bietti, Jiantao Jiao
https://arxiv.org/abs/2509.21998 …

GSM-Agent: Understanding Agentic Reasoning Using Controllable Environments
As LLMs are increasingly deployed as agents, agentic reasoning - the ability to combine tool use, especially search, and reasoning - becomes a critical skill. However, it is hard to disentangle agentic reasoning when evaluated in complex environments and tasks. Current agent benchmarks often mix agentic reasoning with challenging math reasoning, expert-level knowledge, and other advanced capabilities. To fill this gap, we build a novel benchmark, GSM-Agent, where an LLM agent is required to sol…

LLM Agent Meets Agentic AI: Can LLM Agents Simulate Customers to Evaluate Agentic-AI-based Shopping Assistants?
Lu Sun, Shihan Fu, Bingsheng Yao, Yuxuan Lu, Wenbo Li, Hansu Gu, Jiri Gesi, Jing Huang, Chen Luo, Dakuo Wang
https://arxiv.org/abs/2509.21501

LLM Agent Meets Agentic AI: Can LLM Agents Simulate Customers to Evaluate Agentic-AI-based Shopping Assistants?
Agentic AI is emerging, capable of executing tasks through natural language, such as Copilot for coding or Amazon Rufus for shopping. Evaluating these systems is challenging, as their rapid evolution outpaces traditional human evaluation. Researchers have proposed LLM Agents to simulate participants as digital twins, but it remains unclear to what extent a digital twin can represent a specific customer in multi-turn interaction with an agentic AI system. In this paper, we recruited 40 human par…

Right, folks, so there is an account on mastodon.social (@8124@mastodon.social) that has been libelling me and others, defaming us as antisemites for the longest time.
They just sent the posts attached.
They have been reported to mastodon.social and I have raised my concerns with them and yet no action has been taken against that account even though the account has been suspended on at least three major Mastodon servers and limited on at least four others.
It is not limited…

Palo Alto Networks launches Cortex AgentiX, AI agents that can be deployed across various security vendor platforms to automate cybersecurity actions (Samantha Subin/CNBC)
https://www.cnbc.com/2025/10/28/palo-alto-networks-debuts-new-tk-agent-to-fight-…

Palo Alto Networks debuts automated AI agents to fight cyberattacks
Palo Alto Networks launched new AI agents on Tuesday that allow customers to automate certain cybersecurity actions.

DeepTravel: An End-to-End Agentic Reinforcement Learning Framework for Autonomous Travel Planning Agents
Yansong Ning, Rui Liu, Jun Wang, Kai Chen, Wei Li, Jun Fang, Kan Zheng, Naiqiang Tan, Hao Liu
https://arxiv.org/abs/2509.21842

DeepTravel: An End-to-End Agentic Reinforcement Learning Framework for Autonomous Travel Planning Agents
Travel planning (TP) agent has recently worked as an emerging building block to interact with external tools and resources for travel itinerary generation, ensuring enjoyable user experience. Despite its benefits, existing studies rely on hand craft prompt and fixed agent workflow, hindering more flexible and autonomous TP agent. This paper proposes DeepTravel, an end to end agentic reinforcement learning framework for building autonomous travel planning agent, capable of autonomously planning,…

Microsoft launches Agent Mode in Excel and Word, using GPT-5 to generate complex spreadsheets and documents, saying it is "bringing vibe working" to 365 Copilot (Tom Warren/The Verge)
https://www.theverge.com/news/787076/microsoft-offi…

Microsoft launches ‘vibe working’ in Excel and Word
Microsoft is launching new AI tools in its Office apps. A new Agent Mode comes to Word and Excel, alongside an Office Agent in Copilot chat.

Adobe unveils Project Moonlight, an AI agent on its Firefly platform designed to act as a creative director for social media campaigns via text prompts (The Verge)
https://www.theverge.com/news/807457/adobe-ai-agent-project-moonlight

Adobe’s AI social media admin is here with ‘Project Moonlight’
Adobe announced Project Moonlight, an AI agent that uses other Adobe AI tools to create social media posts that match your tone and style.

Do LLM Agents Know How to Ground, Recover, and Assess? A Benchmark for Epistemic Competence in Information-Seeking Agents
Jiaqi Shao, Yuxiang Lin, Munish Prasad Lohani, Yufeng Miao, Bing Luo
https://arxiv.org/abs/2509.22391

Do LLM Agents Know How to Ground, Recover, and Assess? A Benchmark for Epistemic Competence in Information-Seeking Agents
Recent work has explored training Large Language Model (LLM) search agents with reinforcement learning (RL) for open-domain question answering (QA). However, most evaluations focus solely on final answer accuracy, overlooking how these agents reason with and act on external evidence. We introduce SeekBench, the first benchmark for evaluating the \textit{epistemic competence} of LLM search agents through step-level analysis of their response traces. SeekBench comprises 190 expert-annotated trace…

London-based Paid, which helps AI agent providers monetize and track costs, raised a $21.6M seed led by Lightspeed, a source says at a $100M valuation (Julie Bort/TechCrunch)
https://techcrunch.com/2025/09/28/paid-the…

Paid, the AI agent 'results-based billing' startup from Manny Medina, raises huge $21M seed | TechCrunch
Paid offers an interesting contribution to the AI agentic world: a platform for so-called "results-based" billing.