AI Agents & Automation

arXiv:2511.06458v2 Announce Type: replace-cross Abstract: Acoustic Environment Matching (AEM) is the task of transferring clean audio into a target acoustic env

arXiv:2511.12882v3 Announce Type: replace-cross Abstract: Embodied world models aim to predict and interact with the physical world through visual observations

arXiv:2512.19576v4 Announce Type: replace-cross Abstract: Attitude control is essential for many satellite missions. Classical controllers, however, are time-co

arXiv:2601.19066v2 Announce Type: replace-cross Abstract: Bug Reproduction Tests (BRTs) have been used in many Automated Program Repair (APR) systems, primarily

arXiv:2602.10149v3 Announce Type: replace-cross Abstract: Third-Party Risk Assessment (TPRA) relies on large repositories of cybersecurity compliance questions

arXiv:2602.14157v2 Announce Type: replace-cross Abstract: Text-driven image and video editing can be naturally cast as inpainting problems, where masked regions

arXiv:2603.10062v2 Announce Type: replace-cross Abstract: As LLM agents evolve into collaborative multi-agent systems, their memory requirements grow rapidly in

arXiv:2603.14841v2 Announce Type: replace-cross Abstract: Road crashes remain a leading cause of preventable fatalities. Existing prediction models predominantl

arXiv:2603.20340v2 Announce Type: replace-cross Abstract: Self-generated skills for web agents are often unstable and can even hurt performance relative to dire

Gradient Labs uses GPT-4.1 and GPT-5.4 mini and nano to power AI agents that automate banking support workflows with low latency and high reliability.

Paul Duvall recently discussed his library of engineering patterns for AI assisted development and practices that ground high quality delivery. Related discussi

The Brussels-founded, Y Combinator-backed startup counts Orange among its early enterprise customers, which deployed a customer onboarding agent in four weeks.

After Anthropic released Claude Code's 2.1.88 update, users quickly discovered that it contained a package with a source map file containing its TypeScript code

ChatGPT is now accessible from your CarPlay dashboard if you have iOS 26.4 or newer and the latest version of the ChatGPT app, 9to5Mac reports. Apple's recently

I'm excited to announce that AWS Security Agent on-demand penetration testing and AWS DevOps Agent are now generally available, representing a new class of AI c

I used coding agents to build agents that automated part of my job. Here's what I learned about working better with coding agents. The post Agent-driven develop

Traditional frameworks designed for static deployments cannot address the dynamic interactions that define agentic workloads. AI Risk Intelligence (AIRI), from

Box CEO Aaron Levie says reimagining enterprise workflows for AI agents is one of the most valuable skills in the economy right now. Venture capital is starting

Bluesky's new Attie, a natural-language agent, makes the case that social media does not have to be locked inside a few giant platforms.

CERAWeek — dubbed the Davos of energy — is where policymakers, producers, technologists and financiers gather to discuss how the world powers itself next. NVIDI

The company turns footage from robots into structured, searchable datasets with a deep learning model.

In agentic AI systems , when an agent's execution pipeline is intentionally halted, we have what is known as a state-managed interruption .

New York-based startup Crosby’s AI agents and lawyers work together to review contracts quickly, billed by the page, for the likes of Cursor and Runway. CEO Rya

At QCon London 2026, Matthew Skelton argued that AI success depends on organisational maturity. He highlighted bounded agency, security, and stewardship as key

arXiv:2603.26765v1 Announce Type: new Abstract: The efficiency of game engines and policy optimization algorithms is crucial for training reinforcement learning

arXiv:2603.27195v1 Announce Type: new Abstract: Designing microstructures that satisfy coupled cross-physics objectives is a fundamental challenge in material s

arXiv:2603.27303v1 Announce Type: new Abstract: Protein scientific discovery is bottlenecked by the manual orchestration of information and algorithms, while ge

arXiv:2603.27304v1 Announce Type: new Abstract: General-purpose technologies reshape economies less by improving individual tools than by enabling new ways to o

arXiv:2603.27341v1 Announce Type: new Abstract: Recent Artificial Intelligence (AI) models have matched or exceeded human experts in several benchmarks of biome

arXiv:2603.27438v1 Announce Type: new Abstract: We propose a stylized model of human-AI collaboration that isolates a mechanism we call the novelty bottleneck:

arXiv:2603.27476v1 Announce Type: new Abstract: AI-powered people search platforms are increasingly used in recruiting, sales prospecting, and professional netw

arXiv:2603.27597v1 Announce Type: new Abstract: Recent work on artificial consciousness shifts evaluation from behaviour to internal architecture, deriving indi

arXiv:2603.27611v1 Announce Type: new Abstract: When a cognitive system modifies its own functioning, what exactly does it modify: a low-level rule, a control r

arXiv:2603.27738v1 Announce Type: new Abstract: Artificial intelligence (AI) has achieved breakthroughs comparable to traditional numerical models in data-drive

arXiv:2603.27765v1 Announce Type: new Abstract: Recommendation ranking is fundamentally an influence allocation problem: a sorting formula distributes ranking i

arXiv:2603.27857v1 Announce Type: new Abstract: Smart shipping operations increasingly depend on collaborative AI, yet the underlying data are generated across

arXiv:2603.27910v1 Announce Type: new Abstract: AI agents that interact with users across multiple sessions require persistent long-term memory to maintain cohe

arXiv:2603.27922v1 Announce Type: new Abstract: In the context of algorithms for problem solving, procedural knowledge -- the know-how of algorithm design and o

arXiv:2603.28010v1 Announce Type: new Abstract: Heterogeneous Multi-Embodied Agent Systems involve coordinating multiple embodied agents with diverse capabiliti

arXiv:2603.28015v1 Announce Type: new Abstract: Deep learning models for drug-like molecules and proteins overwhelmingly reuse transformer architectures designe

arXiv:2603.28046v1 Announce Type: new Abstract: Dogfight is a tactical behavior of cooperation between fighters. Inspired by this, this paper proposes a novel m

arXiv:2603.28063v1 Announce Type: new Abstract: We prove that under five minimal axioms -- multi-dimensional quality, finite evaluation, effective optimization,

arXiv:2603.28336v1 Announce Type: new Abstract: Systematic literature reviews in the social sciences overwhelmingly follow arborescent logics -- hierarchical ke

arXiv:2603.28407v1 Announce Type: new Abstract: Recent progress in deep research systems has been impressive, but evaluation still lags behind real user needs.

arXiv:2603.28589v1 Announce Type: new Abstract: Autonomous systems that generate scientific hypotheses, conduct experiments, and draft manuscripts have recently

arXiv:2603.28716v1 Announce Type: new Abstract: Agentic reinforcement learning (RL) can benefit substantially from reusable experience, yet existing skill-based

arXiv:2603.25240v1 Announce Type: cross Abstract: Modeling cellular states and predicting their responses to perturbations are central challenges in computation

arXiv:2603.26679v1 Announce Type: cross Abstract: Large-enrollment university courses face persistent challenges in providing timely and scalable instructional