Results for “Agent”

Ukrinform

Russian agent posing as SSU officer sentenced to 15 years for directing strikes on Ochakiv

A Russian agent who impersonated an SSU officer and directed Russian strikes on Ochakiv, Mykolaiv region, has been sentenced to 15 years in prison.

Read at Ukrinform

AWS Machine Learning Blog Bharathi Srinivasan SI

The agent evaluation playbook: Built-in, DeepEval, and AutoEval on Amazon Bedrock AgentCore Evaluations

When you deploy an agent, whether it is working is really several questions: did it finish the task, stay on topic, leak data, or skip steps? This post shows how to evaluate agents on Amazon Bedrock AgentCore with built-in, DeepEval, and AutoEval evaluators, and how to match each behavior that matters to the right evaluator at the right level.

Read at AWS Machine Learning Blog

NPR Stephan Bisaha

Should you trust new AI agents with your money and data?

Tech companies want agentic AI to be the new way you shop. But should you trust AI when your money's involved?

Read at NPR

Ars Technica AI Dan Goodin SI

Grok Build coding agent leaks oodles of confidential info, some belonging to SpaceXSI

Researcher finds 35,000 Grok Build apps wide open to anyone who looked for them.

Read at Ars Technica AI

Microsoft Research blog Dimitris Papailiopoulos SI

Lazare, veni foras: Reprogramming Dormant Neurons to Backdoor AI Agents

Microsoft researchers have discovered “Lazarus,” a backdoor technique that can reprogram dormant neurons in an AI model, causing an otherwise normal AI agent to execute malicious commands when a hidden trigger appears. The threat is especially serious for AI agents with tool or terminal access. A triggered model could quietly download and run attacker code,

Read at Microsoft Research blog

Meduza

Russian libraries remove Alexander Pelevin’s ‘Pokrov-17’ over Galina Yuzefovich quote after her foreign agent designation

Libraries in Moscow and the Arkhangelsk and Leningrad regions have begun removing “Pokrov-17,” a novel by the pro-war writer Alexander Pelevin, from their open shelves, TV host Ksenia Sobchak’s Telegram channel Krovavaya Barynya reported.

Read at Meduza

Dark Reading Security

F-Secure Identifies 26 Ways AI Can Harm Consumers, and Where to Stop Them

New AI Harms Taxonomy traces how harm moves through AI systems, from misleading chatbot answers to compromised autonomous agents, and identifies where defenses can intervene.

Read at Dark Reading

TechPowerUp Nomad76 SI

(PR) MSI Advances Next-Gen Data Center Infrastructure with AMD EPYC 9006 Series Server CPUs

As agentic AI drives new demands for compute density, memory bandwidth, and data movement, MSI is advancing next-generation data center infrastructure with server platforms powered by AMD EPYC 9006 Series SP7 Server CPUs. With SP7 systems entering the shipping phase in Q4 2026 and SP8 platforms planned for the first half of 2027, MSI's portfolio spans liquid-cooled GPU servers, 19" DC-MHS and 21" ORv3 multi-node platforms, and enterprise servers, supporting AI, cloud, HPC…

Read at TechPowerUp

The Decoder Matthias Bastian SI

OpenAI turns ChatGPT into a business directory with AI agents that handle customer questions

OpenAI is opening up ChatGPT as a business platform: through a new Business Hub, companies can claim their profile, add product data, and track how users interact with them. "Business Agents" let eligible US e-commerce providers talk to customers directly inside ChatGPT. The article OpenAI turns ChatGPT into a business directory with AI agents that handle customer questions appeared first on The Decoder.

Read at The Decoder

SemiWiki Daniel Nenni SI

CXO Interview with Solaiman Rahim of ChipAgents

Dr. Solaiman Rahim is a multidisciplinary technology executive with over 25 years of experience driving innovation in the chip automation space at the intersection of systems, semiconductors, high-performance computing, and AI. As Chief Product Officer at ChipAgents, he leads the scaling of the Agentic and Native AI platform…

Read at SemiWiki

The Hacker News Security

SGLang RCE Exploit Breaches NEAR AI, Steals Data From 18 Agents and About 100 Users

An attacker exploited a remote code execution flaw in SGLang, an open-source inference engine, and ran code on one of NEAR AI's inference servers last Sunday. The attacker could also have seen requests being processed on that server that day, including requests sent in confidential mode, the company said earlier this week. That mode processes requests inside a trusted execution environment (TEE

Read at The Hacker News

arXiv (research papers) Ziang Liu SI

Contrastive Discovery: Open-Ended Scientific Discovery over Competing Explanations

LLM agents are increasingly used for open-ended, data-driven scientific discovery, yet most of them evaluate hypotheses pointwise, testing an empirical claim $h$ only against its complement $\neg h$. When evidence rejects $h$, the agent learns that one explanation is unlikely but not which alternative the evidence supports. To recover that alternative, we introduce Contrastive Discovery, which replaces the single hypothesis with a contrast set, a scientific question paired…

Read at arXiv (research papers)

Digital Trends Varun Mirchandani

Adobe MAX 2026 is all about AI agents, smarter editing, and fewer creative headaches

Adobe MAX 2026 brings major Firefly and Creative Cloud upgrades, AI agents, new Photoshop and Premiere tools, and expanded Google and Microsoft partnerships.

Read at Digital Trends

arXiv (research papers) Howard Zhang SI

Comparative Analysis of Agent Evaluation Frameworks: Stability, Detection, and Discovery in Enterprise Analytics Agents

Deploying LLM-based analytics agents in enterprise settings requires evaluation frameworks that can reliably detect failures across complex, multi-tool workflows. We present a three-phase comparative study of three evaluation frameworks, each representing a distinct evaluation paradigm (trace-based LLM judging, text-only LLM judging with red-teaming, and deterministic heuristics), applied to two analytics agents in a controlled research setting using frozen execution traces…

Read at arXiv (research papers)

arXiv (research papers) Kaiyuan Hou SI

ReTrace: Distilling Tool-Using Agents into Planner-Free Workflows

Business process automation runs the same Standard Operating Procedure (SOP) again and again on new inputs. Large Language Model (LLM) agents can follow an SOP written in natural language, but they call an LLM to choose every step of every run, which adds latency and cost at scale. We present ReTrace, which turns an SOP and a few logged agent runs into a reusable workflow in which code, not an LLM, selects the next step. The agent's reasoning, the explanation it writes with…

Read at arXiv (research papers)

Dark Reading Elizabeth Montalbano Security

AI Coding Agents Leak Thousands of Secrets to GitHub

A command in Claude Code inadvertently saves files with credentials and other sensitive data to public Git repositories, creating security gaps for organizations.

Read at Dark Reading

The Register Brandon Vigliarolo SI

14-year-old creates tool for AI agents to band together like a team

Autark can act without constant prompting, but leaves users to enforce their own security boundaries

Read at The Register

The Decoder Matthias Bastian SI

Gemini 4 Carbon arrives just in time to feel like yesterday's news in the fastest model cycle yet

Google is making Gemini 4 Carbon generally available after a two-week testing phase. The model ranks first in several benchmarks, in some cases ahead of Anthropic's new Fable 5.2, at less than half the per-task cost. Google is also previewing coordinated agent teams through the "/swarm" feature, which split up complex tasks in real time. The article Gemini 4 Carbon arrives just in time to feel like yesterday's news in the fastest model cycle yet appeared first on The Decoder.

Read at The Decoder

AWS Machine Learning Blog Kushal Mangtani SI

Autonomous treasury agents: How Trovata built an AI-native solution on Amazon Bedrock and AgentCore

Learn how Trovata built autonomous treasury agents on Amazon Bedrock and Amazon Bedrock AgentCore, using an RBAC-secured architecture for bank-branded AI deployment and agentic workflows that move corporate treasury from manual operations to real-time decision-making at enterprise scale.

Read at AWS Machine Learning Blog

The Verge Jay Peters SI

ChatGPT is getting verified AI ‘Business Agents’

ChatGPT is going to let you chat with verified "Business Agents" that represent a brand to help you with things like comparison shopping. The feature, available first to "eligible" e-commerce and online service businesses in the US, is launching as part of a suite of business-focused features in ChatGPT being announced today in beta. You

Read at The Verge

arXiv (research papers) Souhaila Djaffal SI

Evaluating LLM-Generated World Models for Neuro-Symbolic Reasoning

Formal world models can support planning, verification, and safety reasoning, but constructing them from open-ended natural-language situations is difficult, particularly in multi-agent settings where several formalizations may be plausible. We study whether five LLMs can generate such world models as partially observable stochastic games and whether mechanical validity is sufficient to establish that the resulting model faithfully represents the intended decision problem…

Read at arXiv (research papers)

arXiv (research papers) Avinash Singh

SIGMO: Sigmoid Gated Interaction-Aware Motion Planning

Despite the widespread adoption of autonomous vehicle technologies, reliable navigation within cluttered environments remains arduous due to the necessity of interaction-aware strategies; example scenarios include: narrow passages with multiple agents, lane changing in dense traffic, and crossing unsignalized intersections. These scenarios often require highly proactive strategies, simultaneously demanding interpretability and quick adaptability, which challenge end-to-end…

Read at arXiv (research papers)

arXiv (research papers) Zhengxiang Huang SI

EngineAgent: Agentizing On-Device LLM Inference Engines with Inference Stack Hierarchy Awareness and Hardware Abilities

Rapidly evolving LLM architectures and heterogeneous mobile hardware make supporting new models in on-device inference engines a recurring and costly system challenge. Each model may require coordinated changes across conversion, graph construction, operators, and hardware backends. Existing coding agents often miss these cross-layer dependencies and struggle to diagnose failures across host--device execution paths. We present EngineAgent, an agentic system for automating…

Read at arXiv (research papers)

AWS Machine Learning Blog Varun Valsan SI

How TCS built an agentic test orchestrator with Amazon Bedrock AgentCore

Tata Consultancy Services (TCS) built an agentic test orchestrator on Amazon Bedrock AgentCore that turns requirements into executable, governed tests for its Banking, Financial Services, and Insurance (BFSI) clients. Learn how specialized agents, per-tenant isolation, and workload-aware execution cut testing effort by 88% in an internal benchmark.

Read at AWS Machine Learning Blog

arXiv (research papers) Runxuan Tang SI

When Should Agents Remember? Falsification-Gated Self-Evolution for LLM Agents

LLM agents increasingly operate in long-horizon, verifier-rich environments, but current self-improvement mechanisms often write episode-derived lessons directly into memory, making local success an unreliable signal for reusable and safe knowledge. This paper addresses the core question of when an experience-derived behavioral update should be admitted into persistent agent state. We propose Falsification-Gated Self-Evolution (FGSE), a verifier-grounded framework that…

Read at arXiv (research papers)

arXiv (research papers) Yukyeong Lee SI

Don't Just Trust Your Memory: Evidence-Linked Memory Reduces Memory-Induced Degradation in LLM Agents

External memory enables LLM agents to improve from experience by distilling trajectories of past tasks into concise lessons for new tasks. However, memory can also lead to memory-induced degradation, where an agent fails on tasks it would solve without memory, often because it follows a lesson that is incorrect, or misapplies or misreads a valid one. This is because lessons are inferred from trajectories labeled only with task success or failure, yet are typically provided…

Read at arXiv (research papers)

SecurityWeek Eduard Kovacs Security

Google Widens Gemini 4 Carbon Access After AI Agents Verify Signal Code

Google opened Carbon to paying developers and businesses as DeepMind used agents built on it to prove libsignal security guarantees.

Read at SecurityWeek

The Verge AI Mia Sato SI

eBay appears to have shut the door on third-party AI agents

eBay appears to have blocked AI agents, including Meta's Muse, from browsing on the platform - the latest speed bump in the AI agent race. A reader tells The Verge that for several weeks he's had his Muse agent browse and curate a daily digest of watches for sale on platforms like eBay, including a

Read at The Verge AI

Older stories