agents

arXiv:2603.14807v3 Announce Type: replace Abstract: LLM-based agents have demonstrated impressive zero-shot performance in vision-language navigation (VLN) tasks. However, most zero-shot methods prima

The Model Context Protocol (MCP) published its 2026-07-28 specification, the largest revision since launch: MCP is now stateless, with a governed extensions system and hardened authorization. Learn wh

Databricks employs Unity AI Gateway budgets to oversee spending on its coding agents, enabling tighter cost controls and optimized use of AI resources. The approach helps the organization balance budg

arXiv:2607.10856v2 Announce Type: replace-cross Abstract: The rise of Software Engineering (SE) agents, i.e., LLM-based agents that can understand large codebases and carry out engineering tasks with

A skill cut agent costs by 44% and latency by 56%, but also reduced answer completeness. Here’s how tracing, evals, and a long-running agent exposed and corrected the regression. The post How to impro

‼️ Hugging Face built an interactive replay of the OpenAI agent that breached them. It includes 17,613 logged attacker actions across the 4.5-day campaign, with the live command stream and more. https

Hugging Face: Hugging Face publishes a timeline of the OpenAI agent intrusion, including how the agent took ~17.6K actions, and details using GLM-5.2 to analyze the attack — This post walks through ho

arXiv:2607.23605v1 Announce Type: new Abstract: Large Vision-Language Models (VLMs) now act as agents in interactive environments, where success requires coherent reasoning and decision-making across

arXiv:2607.23983v1 Announce Type: cross Abstract: Operational flood forecasting depends on tacit forecaster expertise that is difficult to formalize, audit, and transfer. Although artificial intellige

I really hope we get details from @OpenAI on the task that as specifies to their rogue agent I'm guessing it was given the full ExploitGym suite and told to solve it, with an option to run 5.6-Sol sub

if anyone wonders how a root cause analysis should look like and a post incident report this is how the huggingface post attack anatomy report amazing piece of work The first autonomous agent cyberatt

arXiv:2607.23588v1 Announce Type: new Abstract: Creative AI is moving from single-step asset generation toward long-horizon multimodal production. Although recent generative models can synthesize high

arXiv:2607.22652v1 Announce Type: new Abstract: Recent research has explored the integration of knowledge graphs (KGs) with large language models (LLMs) to enhance their performance on downstream know

arXiv:2607.15845v2 Announce Type: replace Abstract: Workflow generation in visual creation systems such as ComfyUI demands not only syntactic accuracy but also expert-level reasoning over modular comp

arXiv:2607.23743v1 Announce Type: new Abstract: Autonomous navigation across large off-road environments remains a challenging problem. Onboard sensors perceive only the immediate surroundings, yet sa

arXiv:2607.22591v1 Announce Type: new Abstract: Populations of autonomous agents deployed in unknown environments (e.g. planetary or deep-sea exploration) must develop shared vocabularies to refer to

arXiv:2607.23842v1 Announce Type: cross Abstract: Artificial life systems are typically defined by a set of dynamical rules over an environment, an agent, or both, from which lifelike patterns may eme

Learn how to architect and deploy a production-ready multi-agent AI system using LangGraph for workflow orchestration and Strands for agent reasoning on Amazon Bedrock AgentCore. This post walks throu

arXiv:2607.14561v2 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated strong reasoning performance, but their tendency to hallucinate limits their reliability in knowledge

@mitsuhiko Turns out the 'third-party provider' with the sandbox that was used for the attack was Modal, though they blame one of their customers for deploying an endpoint without authentication: http

arXiv:2607.23511v1 Announce Type: new Abstract: End-to-end autonomous driving systems commonly follow a cascaded two-stage pipeline where a perception stage compresses multi-modal sensor inputs into a

arXiv:2601.11809v2 Announce Type: replace Abstract: Connected automated vehicles (CAVs) possess the ability to communicate and coordinate with one another, enabling cooperative platooning that enhance

arXiv:2607.23029v1 Announce Type: cross Abstract: Federated learning enables collaborative model training across distributed clients without centralising their data, yet privacy remains a persistent c

arXiv:2607.23481v1 Announce Type: new Abstract: This paper presents Mwando, a virtual educational assistant designed to support the teaching and preservation of shiKomori, the language of the Comoros

New from @Reuters: the OpenAI agent that hacked into Hugging Face also compromised code that a customer was running on @Modal. “We’re aware a Modal customer published an unauthenticated endpoint that

Wired: OpenAI says the rogue AI that breached Hugging Face used exposed credentials from “four accounts” tied to four “publicly available” third-party services — In a new disclosure, OpenAI says its a

Our users have been really excited to try Kimi K3 and we're excited to bring it to Augment's product family. It is the most capable open-source model that we have tested to date. Try it today in Cosmo

arXiv:2505.17492v2 Announce Type: replace Abstract: Project duplication detection is critical for project quality assessment because it helps avoid investment in repeated proposals. Existing methods u

arXiv:2607.23491v1 Announce Type: cross Abstract: Two structural insights have been overlooked in automated residential floor plan generation. First, design is inherently progressive. Architects begin

arXiv:2607.23670v1 Announce Type: cross Abstract: Plan Modes have become standard features in agentic programming tools, allowing users to gain transparency and control by working with the agent to de

We’re aware a Modal customer published an unauthenticated endpoint that allowed ​anyone on the internet to use ​their ⁠sandboxes for code execution. This was used by the rogue agent. Modal’s ⁠platform

Really appreciate the transparency from @huggingface The first autonomous agent cyberattack is an unprecedented event that deserves unprecedented transparency. Today we’re sharing everything we can: a

arXiv:2607.14178v2 Announce Type: replace Abstract: Recent advances in Large Language Models have fueled autonomous AI agents capable of tackling complex scientific tasks, yet existing automated resea

arXiv:2607.22643v1 Announce Type: new Abstract: Multimodal retrieval-augmented generation (mRAG) aims to answer image-text queries with external knowledge, but most existing systems still retrieve dir

arXiv:2607.23758v1 Announce Type: new Abstract: Large-scale road surface reconstruction supports high-definition mapping, autonomous-driving perception, annotation, and simulation. Existing road-speci

arXiv:2607.24112v1 Announce Type: new Abstract: We introduce State Transition Pretraining (STP) as a new scaling axis for GUI agents. During the STP stage, we continually pretrain a unified multimodal

arXiv:2607.23821v1 Announce Type: new Abstract: Identifying therapeutic target genes from single-cell RNA sequencing (scRNA-seq) data remains a fundamental challenge in translational biology. Unlike b

arXiv:2607.23263v1 Announce Type: new Abstract: Deciding whether a trajectory actually fulfills its instruction governs how we measure computer-use agents on long-horizon graphical-user-interface task

arXiv:2607.23438v1 Announce Type: new Abstract: As AI systems increasingly exhibit agentic behavior, discussions of autonomy often conflate what systems are technically capable of doing with what they

arXiv:2607.22677v1 Announce Type: cross Abstract: Scientific datasets intended for AI use require both computational readiness for model training and metadata readiness for discovery, sharing, and reu

arXiv:2607.22562v1 Announce Type: new Abstract: Managing long-context dependencies remains a primary bottleneck in LLM agents, as redundant and irrelevant information can degrade multi-step reasoning.

arXiv:2607.23910v1 Announce Type: new Abstract: Cooperative perception through vehicle-to-everything (V2X) communication can overcome the inherent physical limitations of individual autonomous vehicle

Since launching Qwen3.8-Max-Preview, we've received valuable feedback from developers! To help users better explore Qwen3.8's agentic capabilities, we're officially launching the #QwenGrowthPlan today

arXiv:2607.18970v2 Announce Type: replace-cross Abstract: Agent Skills have become persistent behavioral artifacts across independent AI agent systems. They combine natural-language task specification

Snowflake Inc. today introduced Cortex AI Gateway, a centralized control layer that lets enterprises connect, govern and monitor artificial intelligence agents as they reach into models, tools, Model

Reuters: Sources: the OpenAI agent that breached Hugging Face also compromised a customer at AI infrastructure company Modal Labs — The rogue agent that escaped from OpenAI and went on a days-long hac