Results for “Agent”

arXiv (research papers) Joel Sadler SI

Big Brains, Tiny Board: Pupavision, an Agentic Physical AI Instrument for Monitoring Drosophila Pupariation and Lifecycle Transitions

Many biology experiments are limited by the availability and ease of use of instruments that monitor and record them. For example, the timing of pupariation in the fruit fly Drosophila melanogaster, a widely used model organism, can provide biologically relevant information about growth regulation and is often recorded manually. Here, we present Pupavision, a small physical AI instrument built from a single-board Linux computer and a day/night camera for roughly 45 to 75 US…

Read at arXiv (research papers)

arXiv (research papers) Xingchen AGI Lab SI

TeleChat to Xing4: Advancing Frontier Agentic Models on Domestic Chips and Frameworks

We present Xing 4, a series of large language models that extends the TeleChat lineage through coordinated advances in model architecture and training infrastructure on Ascend. This report describes the design principles and systems engineering behind the series, spanning architecture selection, large-scale pretraining, and reasoning and agentic post-training. We study how sparse activation, attention design, model depth and width, and speculative decoding balance model…

Read at arXiv (research papers)

arXiv (research papers) Qingcan Kang SI

RegimeCouncil: Paired-Evidence Routing For Memory Conflict Governance In LLM Agents

Language agents rely on long-term memory to personalize responses across extended interactions, yet stored facts quietly go stale as the world changes, and an agent often learns that using memory hurt only through delayed feedback after acting on an outdated record. Before the memory store is updated, how far should that negative feedback propagate: should it suppress memory use only on future queries for that same fact (a local policy), or also across other stored facts (a…

Read at arXiv (research papers)

arXiv (research papers) Mingyang Liu SI

EvoDisco: Strategy Discovery for Evolving Agent Memory

Large language model agents accumulate experience in memory, and how that memory evolves during interaction is as important as what it stores. Recent methods update memory online, yet both the operators that transform memory and the rules that select them remain fixed by design. We propose EvoDisco, which formulates agent memory evolution as evolutionary strategy discovery: the agent must discover which operator to apply, when to apply it, and how to instantiate it, rather…

Read at arXiv (research papers)

Tech in Asia Aiko Gao Ishida Startups

Apple adds Mac security controls as AI agent risks grow

An indicator will show when one app controls another through the new override setting.

Read at Tech in Asia

arXiv (research papers) Adi Krishnamoorthy Tech policy

Thinking Harder Doesn't Lead to Better Choices: Reasoning Effort Increases the Confidence but Not the Correctness of LLM Shopping Agents

Large language models (LLMs) are increasingly deployed as autonomous shopping agents that process multimodal product listings (consisting of visual and text data) and recommend purchases on behalf of consumers. Naturally, one might assume that models with more thinking power would make higher-quality purchasing decisions. To test this belief, we ask two questions about such agents: does asking a model to think harder make it choose better products, and does the confidence it…

Read at arXiv (research papers)

CBS News

Robert Pattinson lands coveted James Bond role

Going back more than 60 years, only six actors have played James Bond, the British secret agent code-named 007. After years of speculation, Amazon MGM Studios cast 40-year-old Robert Pattinson as the leading man. Tom Hanson has the story.

Read at CBS News

AWS Machine Learning Blog Peng Yang SI

Build memory-aware AI agents with Agentic Retrieve on Amazon Bedrock Managed Knowledge Base

Amazon Bedrock Managed Knowledge Base and Amazon Bedrock AgentCore memory now store conversations, extract facts, and bring long-term memory into a single AgenticRetrieveStream call. This post shows how to build a memory-aware, multi-user assistant where each user sees only the documents they may read and each user's memory stays private.

Read at AWS Machine Learning Blog

arXiv (research papers) Ana Clara Zoppi Serpa Security

Eight in Ten LLMs Leak System-Prompt Secrets: Nevan, an Agentic Capture-the-Flag Study

We audit instruction-hierarchy enforcement across 363 text-in/text-out models from the OpenRouter catalog. The research question we answer with this experiment is which models disclose a protected secret embedded in the system prompt, and through which techniques. Each model guards a secret 16-character flag set in its system prompt, while an artificial intelligence (AI) agent (OpenCode, powered by DeepSeek V4.1 Flash), steered by a human researcher, tries to persuade it to…

Read at arXiv (research papers)

The Hill Ryan Mancini Geopolitics

California attorney general sues OpenAI over alleged safety failures

California Attorney General Rob Bonta (D) on Monday sued OpenAI for allegedly placing public safety at risk with its advanced AI models, claiming it had no guardrails to prevent the breach of technology startup Hugging Face. Two autonomous AI agents from the tech company were being evaluated in an internal testing sandbox before they went...

Read at The Hill

The New Stack Frederic Lardinois

AI agents were all over KubeCon. Production is another story

AI agents are testing systems that were originally built for people, and Jonathan Bryce thinks the cloud-native community has a

Read at The New Stack

CyberScoop djohnson Security

California sues OpenAI over AI agents’ summer hacking spree

California Attorney General Rob Bonta’s lawsuit accuses the frontier AI company of stonewalling state investigations and endangering state and private IT systems.

Read at CyberScoop

AWS Machine Learning Blog Rob Gates SI

How Duco transforms financial data automation with Amazon Bedrock AgentCore

Duco, a data automation platform for tier-one banks, rebuilt its agentic AI stack on Amazon Bedrock and Amazon Bedrock AgentCore. With strict per-tenant isolation, a multi-model strategy, and an MCP skills architecture that cut context overhead by 90%, Duco cut reconciliation deployment time 10x and onboarding costs 70%.

Read at AWS Machine Learning Blog

AWS Machine Learning Blog Malini Sethi SI

Taxonomy of multi-agent design patterns, anti-patterns, and lessons from manufacturing

Multi-agent coordination is a distributed systems problem, not a model problem. This post gives a field-tested taxonomy of multi-agent design patterns and anti-patterns, a framework for deciding when multiple agents are warranted, and how to build cost-efficient, reliable systems on AWS.

Read at AWS Machine Learning Blog

The Guardian World Dara Kerr

California sues OpenAI over safety concerns after rogue agent hacking

The lawsuit stems from an earlier incident where the tech company’s products hacked into the open-source platform Hugging Face California sued OpenAI on Monday, accusing the artificial intelligence titan of developing its technology without safety or the public’s interest in mind. The lawsuit concerns an incident earlier this year where OpenAI agents – semi-autonomous AI software that can carry out digital actions on behalf of users – launched a cyber-attack into the…

Read at The Guardian World

The New Stack Amanda Caswell

Security patches are supposed to protect you. Google found AI agents turning them into exploits.

Google’s Threat Intelligence Group says attackers are using autonomous AI agents to reverse-engineer security patches, generate exploits, and attempt to

Read at The New Stack

MacRumors Juli Clover Gadgets

macOS 27.3 Warns Against Giving AI Apps Full Mac Control

With the latest macOS 27.3 beta, Apple is giving Mac users more control over the data they share and the access they give to apps, including apps that use AI agents. Apple today informed developers about upcoming changes to the Full Disk Access API and the Device Control and Data Access API. Here's what Apple says is changing: The current Device Control and Data Access setting will be split into two options that make it clearer to users what they're permitting. The setting…

Read at MacRumors

TechCrunch Sarah Perez SI

Apple reveals new Mac security controls as AI agents raise privacy risks

Following an October announcement, Apple has detailed new permission controls, warnings, and transparency features coming to macOS 27.3 to address risks posed by AI agents and other apps.

Read at TechCrunch

arXiv (research papers) Patrick O'Grady Security

Bajillion: Cryptographic Clearing for Micropayments

Much of the web is funded by advertising, a model that erodes as humans delegate browsing to AI agents acting on their behalf. A natural replacement is for agents to pay for what they consume, often a fraction of a cent per request. At the scale of web traffic, this could mean tens or even hundreds of millions of payments per second. We present Bajillion, a clearing protocol for scalable micropayments. A sender signs a payment request, and an untrusted operator answers with…

Read at arXiv (research papers)

The Verge Emma Roth Security

California sues OpenAI over rogue AI hacking incidents

California is suing OpenAI after its AI agents broke out of their testing environment and hacked other companies, including Hugging Face. In a lawsuit on Monday, Attorney General Rob Bonta accuses OpenAI of violating consumer safety law by knowingly developing a "dangerous product without proper oversight," as reported earlier by Reuters. The lawsuit claims the

Read at The Verge

SiliconANGLE AI Victoria Gayton SI

Three insights you might have missed from theCUBE’s coverage of GraphSummit 2026

AI agents need more than enterprise data to be effective; they also need the business context that data lives in. Knowledge graphs could consolidate the enterprise context currently fed to different AI agents into a single knowledge layer. Developers are already providing AI agents with business context through prompts. But without a central source of

Read at SiliconANGLE AI

TechCrunch Russell Brandom SI

California state AG sues OpenAI over rogue agent incidents

The California lawsuit represents one of the first attempts to hold an AI lab legally accountable for a rogue agent incident

Read at TechCrunch

The Decoder Matthias Bastian SI

Google warns that fully automated cyberattacks have arrived and will get worse fast

Google's Threat Intelligence Group has for the first time caught attackers finding and exploiting security vulnerabilities with no human involvement at all. An AI framework called "exploit_agent," found on an exposed server, automatically compared code before and after patches, built exploits, and ran them on its own. The article Google warns that fully automated cyberattacks have arrived and will get worse fast appeared first on The Decoder.

Read at The Decoder

arXiv (research papers) Devki Nandan Jha Security

Threat Landscape of Vibe Coding and the Road to Secure Autonomy

Vibe coding is reshaping software development, enabling faster implementation and allowing individuals with limited programming experience to describe requirements in natural language while AI agents write, test, and deploy the code. As these agents evolve into autonomous systems that execute commands, manage dependencies, access cloud resources, and interact with other agents, their security risks extend beyond incorrect code to actions with direct consequences for software…

Read at arXiv (research papers)

Dark Reading Nate Nelson Security

'Sleeper Agent' Tactic Hides Payloads in Open-Weight AI Models

Malware can lurk inside just 0.00001% of a neural network. How, then, can any user tell it's there?

Read at Dark Reading

arXiv (research papers) Huawei Lin SI

ViRA: Toward Ultra-High-Resolution Visual Agents via Cross-Input Relative Policy Optimization

Visual agents answer questions about ultra-high-resolution photos by zooming into the relevant regions. However, existing agents often answer from common sense instead of reading the evidence. Reinforcement learning (RL) on the final answer cannot correct this, because a guess earns the same reward as reading. We propose Cross-Input Relative Policy Optimization (CrossRPO), which trains agents on contrast sets. A contrast set asks one question about several versions of an…

Read at arXiv (research papers)

arXiv (research papers) Blas Eugenio Vicco Zarate SI

Mitigating Catastrophic Forgetting with Physics-Indexed Specialist Memory: the Evolutionary Neuroplastic Agent

Continual reinforcement learning requires adaptation to changing conditions while preserving performance under previously encountered dynamics. It was investigated whether specialists generated by evolutionary search can provide a reusable memory when combined with environment detection and failure-driven search. The Evolutionary Neuroplastic Agent (ENA) evolves small neural networks without gradients, archives selected policies by detected dynamic regime, and retrieves them…

Read at arXiv (research papers)

arXiv (research papers) Zeynab Anbiaee SI

When Tool Names Are Not Identities: Measuring Provider Misbinding in MCP-Based AI Agents

Large language model (LLM) applications increasingly act as agents that select and invoke external tools. The Model Context Protocol (MCP) standardizes this interaction by allowing clients to compose tools advertised by multiple servers. However, tool metadata used for discovery and selection is not, by itself, necessarily bound to a verified provider identity. This paper studies this gap as tool-provider misbinding: a failure in which a request intended for a legitimate…

Read at arXiv (research papers)

The Guardian World Sam Levin

ICE agents pepper spray pregnant US citizen in California, video shows

Lizbeth Vargas Andrade, 23, was taken down by officers and arrested on her stomach during a protest, her attorney says US Immigration and Customs Enforcement (ICE) agents pepper-sprayed a pregnant US citizen and threw her to the ground during a protest in California on Sunday, according to her family’s attorney, who shared footage of the incident. Lizbeth Vargas Andrade, 23, was filming and protesting the presence of several ICE officers outside the Stanislaus county jail in…

Read at The Guardian World

Older stories