AI Agents & Automation

arXiv:2604.03037v1 Announce Type: cross Abstract: Long-horizon robotic manipulation remains challenging for reinforcement learning (RL) because sparse rewards p

arXiv:2604.03094v1 Announce Type: cross Abstract: Accurate and automated sea ice classification is important for climate monitoring and maritime safety in the A

arXiv:2604.03104v1 Announce Type: cross Abstract: Cyber-attacks continue to grow in scale and sophistication, yet existing network intrusion detection approache

arXiv:2604.03131v1 Announce Type: cross Abstract: Tool-augmented AI agents substantially extend the practical capabilities of large language models, but they al

arXiv:2604.03203v1 Announce Type: cross Abstract: Three-dimensional medical image data and computer-aided decision making, particularly using deep learning, are

arXiv:2510.27176v5 Announce Type: replace Abstract: Can AI autonomously design mechanisms for computer systems on par with the creativity and reasoning of human

arXiv:2512.16300v2 Announce Type: replace Abstract: Existing image forgery detection (IFD) methods either exploit low-level, semantics-agnostic artifacts or rel

arXiv:2601.00290v2 Announce Type: replace Abstract: Clinical trials constitute a critical yet exceptionally challenging and costly stage of drug development (\$

arXiv:2601.13518v3 Announce Type: replace Abstract: While recent automated red-teaming methods show promise for systematically exposing model vulnerabilities, m

arXiv:2603.17714v2 Announce Type: replace Abstract: Autonomous driving technologies have achieved significant advances in recent years, yet their real-world dep

arXiv:2410.13891v3 Announce Type: replace-cross Abstract: Transferable Targeted Attacks (TTAs) face significant challenges due to severe overfitting to surrogat

arXiv:2505.17938v2 Announce Type: replace-cross Abstract: Routing problems are canonical combinatorial optimization tasks with wide-ranging applications in logi

arXiv:2507.04356v2 Announce Type: replace-cross Abstract: Research, innovation and practical capital investment have been increasing rapidly toward the realizat

arXiv:2509.17608v3 Announce Type: replace-cross Abstract: Social narratives help autistic children understand and navigate social situations through stories. To

arXiv:2509.19454v2 Announce Type: replace-cross Abstract: Training robust bimanual manipulation policies via imitation learning requires demonstration data with

arXiv:2509.25438v2 Announce Type: replace-cross Abstract: When there exists an unlearnable source of randomness (noisy-TV) in the environment, a naively intrins

arXiv:2510.19127v2 Announce Type: replace-cross Abstract: Controllable music generation remains a significant challenge, with existing methods often requiring m

arXiv:2512.00129v2 Announce Type: replace-cross Abstract: Deep learning models for breast cancer detection from mammographic images have significant reliability

arXiv:2512.08980v3 Announce Type: replace-cross Abstract: Recent VLM-based agents aim to replicate OpenAI O3's "thinking with images" via tool use, yet most ope

arXiv:2601.13508v2 Announce Type: replace-cross Abstract: Fully automating the scientific process is a transformative ambition in materials science, yet current

arXiv:2603.05917v2 Announce Type: replace-cross Abstract: Stock market prediction presents considerable challenges for investors, financial institutions, and po

arXiv:2603.16663v3 Announce Type: replace-cross Abstract: The AIED community envisions AI evolving "from tools to teammates," yet our understanding of AI teamma

In short: Microsoft has spent billions building Copilot into every corner of its product lineup, pitching it as an indispensable AI co-worker. Its own Terms of

Current Breach and Attack Simulation (BAS) tools just replay static scripts and generate PDFs. VANGUARD uses an LLM ReAct loop to autonomously hack targets, ada

Agentic AI is here. ANGTCY is building the Internet of Agents an open, standardized network where AI agents discover, communicate, and collaborate accelerating

I built a browser-based AI medical scribe as a way to explore whether the real question isn’t just “can AI write a good note?” but “can it be done in a way that

As synthetic candidates scale and deepfake interviews slip past recruiters, AI-powered HR platforms like Phenom are deploying AI agents to detect and expose fra

Glemad, an AI security and research company, today announced the...

I run 100+ AI agents across a Web3 codebase. This is the story of how I learned that prompts control objectives, not boundaries, and that the real engineering i

In this post, we show you how to configure AWS Network Firewall to restrict AgentCore resources to an allowlist of approved internet domains. This post focuses

Fortis Solutions, an enterprise technology partner with decades of experience across infrastructure, cybersecurity, and data systems, approaches artificial inte

In October 2025, Sam Altman posted a message on X that ended with a single, carefully placed promise. ChatGPT, he said, would soon allow verified adults to acce

Generalist Bets Wearable “Data Hands” Could Spark Robotics’ ChatGPT Moment

Adrian Cockcroft explains the transition from cloud-native to AI-native development. He shares his "director-level" approach to managing swarms of autonomous ag

Author(s): DrSwarnenduAI Originally published on Towards AI. 512,000 lines of TypeScript. A secret AI pet. An always-on daemon that dreams. A mode that hides fr

Author(s): Divy Yadav Originally published on Towards AI. The practical guide to monitoring, debugging, and governing AI agents before they become a liability Y

arXiv:2604.00137v1 Announce Type: new Abstract: Tool-integrated LLMs can retrieve, compute, and take real-world actions via external tools, but reliability rema

arXiv:2604.00284v1 Announce Type: new Abstract: We formally introduce a improvisational wordplay game called Connections to explore reasoning capabilities of AI

arXiv:2604.00319v1 Announce Type: new Abstract: We develop algorithms for collaborative control of AI agents and critics in a multi-actor, multi-critic federate

arXiv:2604.00356v1 Announce Type: new Abstract: Agentic applications based on large language models increasingly rely on multi-step interaction loops involving

arXiv:2604.00788v1 Announce Type: new Abstract: This technical report presents methods developed by the UK AI Security Institute for assessing whether advanced

arXiv:2604.00795v1 Announce Type: new Abstract: We propose the Preference Guided Iterated Pareto Referent Optimisation (PG-IPRO) for urban route planning for pe

arXiv:2604.00842v1 Announce Type: new Abstract: Proactive agents that anticipate user needs and autonomously execute tasks hold great promise as digital assista

arXiv:2604.01221v1 Announce Type: new Abstract: We present HippoCamp, a new benchmark designed to evaluate agents' capabilities on multimodal file management. U

arXiv:2603.05735v2 Announce Type: cross Abstract: We present an AI agentic measurement of the thrust distribution in $e^{+}e^{-}$ collisions at $\sqrt{s}=91.2$~

arXiv:2604.00043v1 Announce Type: cross Abstract: Non-Axiomatic Reasoning Systems (NARS) provide a framework for building adaptive agents that operate under ins

arXiv:2604.00057v1 Announce Type: cross Abstract: Soccer commentary plays a crucial role in enhancing the soccer game viewing experience for audiences. Previous

arXiv:2604.00073v1 Announce Type: cross Abstract: There has been growing interest in building agents that can interact with digital platforms to execute meaning