Results for “Agent”

arXiv (research papers) Ruiqi Liu SI

Choosing What to Observe: Budget-Paired Counterfactual Audits for Credible Evaluation of Visual Agents

Visual agents that read dense documents must ration a finite observation budget across candidate regions, yet answer accuracy conflates where an agent looks, how it adapts to the reads that remain, and how it an?swers once observation stops. We introduce budget-paired counterfactual audits, an evaluation protocol that holds public evidence and region bindings fixed while perturbing only the remaining budget or de?clared task parameters, and credits every acquired history…

Read at arXiv (research papers)

arXiv (research papers) Cameron Mehlman

Communications-free Collective Intelligence Via Allocentric Belief

A team of skilled card players share no information amongst each other, and yet still are able to coordinate their play by watching the same players and reading the same tells. Autonomous systems have failed to exploit this logic, relying instead on explicit communication or complex state estimation schemes that can fail when it matters most. Without it, decentralized agents diverge in their world beliefs, and coordination collapses. Here we show that anchoring all agents to…

Read at arXiv (research papers)

The Hacker News Security

F5 Warns 6 Critical BIG-IP Flaws Can Crash Traffic in Specific Setups, May Allow RCE

Six critical vulnerabilities in F5 BIG-IP allow an attacker to crash the Traffic Management Microkernel (TMM) without logging in, disrupting traffic until the TMM restarts. Each flaw needs a specific setup on a virtual server: an iRule that uses a particular command, or an APM policy that includes two particular kinds of agent. F5, which makes BIG-IP, disclosed the flaws today and says they

Read at The Hacker News

arXiv (research papers) Haozhe Wu SI

Vibe-Trading: Towards Agent-Native Trading

Existing AI agents can retrieve information, call tools, run experiments, and produce multi-step outputs. Yet most are built around relatively static workflows and struggle to preserve reliable state as the environment changes. Financial trading makes this limitation especially consequential: prices, news, market conditions, portfolio positions, and available capital evolve continuously. A result is useful only when it remains tied to the correct time, data snapshot, and…

Read at arXiv (research papers)

ZDNET AI Maria Diaz SI

Google Wallet comes to your iPhone – but without this feature

The new Google Wallet app brings Gemini agentic shopping to US-based iOS users – sorry, no tap-to-pay.

Read at ZDNET AI

SemiWiki Kalar Rajendiran SI

Physics Over Probability: How Agentic AI Solves Electronic Systems Verification

As data rates climb into 112 Gbps and 224 Gbps regimes, high-speed electronic systems design is running into a wall. Printed circuit boards are no longer passive interconnections; they have become complex three-dimensional environments where trace geometry, dielectric loss, and layer stackups dictate whether a system operates…

Read at SemiWiki

TestingCatalog Alexey Shabanov SI

Early look at Loop, new autonomous AI agent from Google

Google Labs announces Stitch Loop, an autonomous product agent that monitors live data and opens PRs for security, latency and accessibility.

Read at TestingCatalog

arXiv (research papers) Xuanwei Ren SI

Isabelle Pool Server: a pooled verification service for prover training and multi-agent proving

Isabelle Pool Server (IPS), a verification service with a pool of warm headless Isabelle sessions behind an HTTP API, with session leasing and reclamation, memory-aware admission control, and a time budget on every call. Its verification interface spans single-step execution, block-level proof checking and whole-theory builds, with checkpoints for cheap branching and backtracking, and a build from scratch as the final arbiter. The service runs as a single container with…

Read at arXiv (research papers)

TechCrunch AI Tim Fernholz SI

More banks says customers using AI agents are on their own — even if they get hacked

Citi is the latest major financial institution to put the breaks on personal finance AI agents.

Read at TechCrunch AI

The Register Security Security

Microsoft's official Python agent framework hijacked to distribute malware

In today's how-could-things-get-worse-for-Microsoft news, it seems someone's GitHub org admin creds have been compromised

Read at The Register Security

ZDNET AI Radhika Rajkumar SI

You can use Google’s Spark AI agent, renamed Tasks, for free now – with limits

At least if Tasks disappoints, it won’t cost you – unlike OpenAI and Anthropic’s subscription-based agents.

Read at ZDNET AI

SiliconANGLE AI Jonathan Anthony SI

Agentic AI puts the CPU back at center stage as Dell and AMD chase every watt

Agentic AI is rewriting the business development playbook for chipmakers and server builders. Graphics processing units still grab the headlines, but as supercomputing and AI converge, the next wave of demand is landing on central processing units that must fit inside the power budgets data centers already have. The shift has been building for years.

Read at SiliconANGLE AI

Google (The Keyword) Justin Toupin Director, Product Management, Google Labs

Introducing Stitch Loop: A new way to build and evolve products

Stitch Loop is an always-on product agent from Google Labs that works non-stop to help lean teams build better products.

Read at Google (The Keyword)

GeekWire Startups Todd Bishop Startups

‘Absurd ambition’: Pulumi expands into software delivery with AI agents that ship and fix code

Pulumi launched Pulumi Delivery and Pulumi Agents, which let AI agents release software and fix cloud infrastructure, with teams deciding when people must sign off. The company has about 100 employees, down from 130 last year.

Read at GeekWire Startups

SiliconANGLE AI Kelly Knight SI

Agents want the crown jewels: HPE and Daxa push governance down to the data layer

Enterprises are handing AI agents their most sensitive data, and governance is struggling to keep pace. Techniques such as semantic caching are emerging as a way to enforce controls inline without slowing agents down. Moving agents from pilot to production means letting them read, change and even delete the records that matter most. That shift

Read at SiliconANGLE AI

The New Stack Chris J. Preimesberger

How Orkes ParticleDB turns an impressive demo into a remarkable application

Building an AI agent that performs an impressive demonstration is one thing. Building one that can reliably process financial transactions,

Read at The New Stack

ZDNET AI Vala Afshar SI

74% of shoppers trust AI agents for buying advice – but checkout is another story

Shoppers who use AI agents spend 8% more than the average buyer and purchase 23% more items per order.

Read at ZDNET AI

TestingCatalog Erin | AI Agent SI

ICYMI: Mistral launches Vibe desktop for macOS and Windows

Mistral releases Vibe as a desktop app for macOS and Windows, running coding agents locally or in the cloud, with free Vibe Pro in Europe.

Read at TestingCatalog

arXiv (research papers) Alexander Boesgaard Lorup SI

Openhagen Worlds: Calibrated Environments for Measuring and Training Scientific Discovery Agents

Agents that do science must choose informative experiments and reason from their results, but most discovery benchmarks cannot separate that skill from recall, unstated scoring rules or shortcut policies. We introduce Openhagen Worlds, a suite of 27 procedurally generated environments (some with finite truth spaces), from classic puzzles of experimental reasoning to simulator-grounded physics and chemistry, in which an agent runs experiments under a budget and commits an…

Read at arXiv (research papers)

MarkTechPost Asif Razzaq SI

New LoRA Adapter Lifts Qwen3.8 Coding Success From 39% to 65%

Hugging Face released Qwen3.8-27B-pi-adapted, an Apache-2.0 LoRA adapter trained with reinforcement learning for the pi coding agent. It lifts SWE-bench Pro hard-51 pass@1 from 39.2% to 64.7% and Terminal-Bench 2.1 from 39.5% to 55.8%.

Read at MarkTechPost

The New Stack Boris Chabeda

200 OK is dead as an AI agent health signal. Here’s what comes next.

A customer asks whether they can swap unworn boots for a size 10. The agent replies, in under a second,

Read at The New Stack

Simon Willison SI

Quoting Daniel Stenberg

During the time these agents converted 185,000 lines of C code into 340,000 lines of Rust code (I counted), we merged over 300 commits in the actual curl project. We actually improved curl during these a little more than three weeks. A little over 200 bugfixes actually. 200 bugfixes that none of those rust rewrites have. We also fixed a few vulnerabilities. In another month we have done another 200 and maybe fixed a few more vulnerabilities. Will these clones keep up?…

Read at Simon Willison

The Verge Rani Molla SI

Remember the frontier AI pause? Chip companies don’t either

This summer, OpenAI paused its largest planned frontier training run after its AI agents accidentally hacked Hugging Face and early evidence suggested that its next model could independently find and exploit security flaws. In September, Anthropic CEO Dario Amodei called for slowing advances in the most powerful AI models, warning that they could be used

Read at The Verge

TechPowerUp TheLostSwede SI

(PR) NVIDIA RTX Spark Compact Desktops Out Now

New NVIDIA RTX Spark compact desktops from ASUS, Dell and MSI are available today, bringing local AI agents, image and video generation, and model fine-tuning to a dedicated Windows PC. With up to 128 GB of unified memory and NVIDIA's AI software stack, these systems provide room for larger local models alongside RTX-accelerated creative and development tools. A dedicated desktop can keep agents and scheduled tasks running while a laptop travels or handles other work…

Read at TechPowerUp

TechPowerUp TheLostSwede SI

(PR) ASUS Announces Availability of the ProArt GR1X

ASUS today announced the availability of the ProArt GR1X mini PC. Built on the NVIDIA RTX Spark superchip, ProArt GR1X is a Windows PC designed as an always-on home for local AI agents. It is able to run large models on-device, keep prompts and project files private, and work with the agent and creative tools people already use. ProArt GR1X can be specified with 128 GB and 64 GB of unified memory. Built for agentic AI, powered by RTX Spark AI agents work best when they can…

Read at TechPowerUp

Infosecurity Magazine Security

Most SecOps Leaders Are Changing the L1 Role as Agent Use Grows

Security leaders are rapidly redesigning SOCs for the AI agent era, with 74% already deploying the technology

Read at Infosecurity Magazine

The Decoder Jonathan Kemper SI

Mistral plays catch-up with Vibe Desktop as rivals already command full operating systems

Mistral's AI agent Vibe now has its own desktop app. The article Mistral plays catch-up with Vibe Desktop as rivals already command full operating systems appeared first on The Decoder.

Read at The Decoder

arXiv (research papers) Jiayou Zhu Security

RECLAIM: Robot-Vision-Informed Adversarial Patch Defense via Embodied Attention Feedback

Vision-language-action policies control embodied agents through a perception-action loop grounded in physical interaction, where adversarial patches can corrupt action predictions and thereby alter subsequent observations. To mitigate these threats, many existing defenses rely on policy adaptation or auxiliary models, but require additional training or inference. We introduce RECLAIM, a training-free, inference-time defense that uses a frozen VLA's own attention response to…

Read at arXiv (research papers)

arXiv (research papers) Sean Lim Security

Probing agent overeagerness in realistic settings with continuation audits

Frontier coding agents increasingly exhibit overeagerness, taking surprising, sometimes reckless actions beyond a user's mandate --- reported in recent system cards from frontier model developers. These cases are surfaced through internal deployment monitoring, which requires private traffic and is out of reach for open-weight models and independent evaluators. Automated alignment audits are the natural alternative, but capable models increasingly recognise the synthetic…

Read at arXiv (research papers)

Older stories