Search: “agents”

Security intelligence and management solutions company Exabeam Inc. today introduced Agent Behavior Verification, a pre-deployment security discipline for artificial intelligence agents, and released

arXiv:2606.22995v1 Announce Type: new Abstract: Group-based Reinforcement Learning (RL) has significantly enhanced Large Language Models (LLMs) in agentic scenarios. To achieve finer-grained policy up

Highly-recommended read. It's exciting to see large-scale agentic RL becoming more accessible. Cool to see the infra layer for this is being built and I think this plays an important role in self-impr

arXiv:2602.09012v2 Announce Type: replace Abstract: The rapid evolution of GUI-enabled agents has rendered traditional CAPTCHAs obsolete. While previous benchmarks like OpenCaptchaWorld established a

Identity and access management company Okta Inc. today said more than 25 software makers have signed on to its Cross App Access framework, which routes the connections artificial intelligence agents m

arXiv:2606.20512v2 Announce Type: replace-cross Abstract: LLM-based coding agents need higher-level operational knowledge about a repository (which files house which subsystems, how to run the test su

arXiv:2606.20659v1 Announce Type: cross Abstract: Agent skills encode reusable procedural knowledge that guides large language model agents across tasks and execution contexts. Existing evaluations pr

arXiv:2505.11579v3 Announce Type: replace-cross Abstract: As AI systems evolve from static tools to dynamic agents, traditional categorical governance frameworks -- based on fixed risk tiers, levels o

Just a glimpse of what collective AI intelligence will bring. We haven’t truly cracked multi-agent orchestration but with every new frontier model, intelligence should compound. Introducing Sakana Fug

The new /goal command in Grok Build is a huge update Until now, most coding agents have worked like enhanced chatbots You ask. It responds. You review. You guide it. Repeat /goal changes the entire pa

Use Case 2: Financial Time Series Prediction Can an AI agent navigate sequential, no-look-ahead market decisions? Just for fun, we tested Fugu Ultra on 50 weeks of historical data for an anonymized eq

Nous Research announced that the Hermes Agent repository has reached 1,500 contributors, celebrating the collaborative effort of developers who have contributed to the project. This milestone reflects

arXiv:2606.11337v1 Announce Type: new Abstract: Scientific AI agents increasingly retrieve evidence, reason across sources, and synthesize conclusions used in consequential decisions. Yet, their abili

arXiv:2606.11521v1 Announce Type: new Abstract: LLMs and LLM agents should improve when given feedback, but identifying when they are able to do so is difficult: feedback is heterogeneous, domain-spec

arXiv:2606.11688v1 Announce Type: cross Abstract: Long-horizon LLM agents are not trusted to run unattended: with no human watching, they confidently report success they never verified. We treat hones

arXiv:2307.01472v2 Announce Type: replace Abstract: We present a novel Diffusion Offline Multi-agent Model (DOM2) for offline Multi-Agent Reinforcement Learning (MARL). Different from existing algorit

arXiv:2606.11686v1 Announce Type: cross Abstract: End-to-end task-success is the dominant way to evaluate LLM agents, but one aggregate number tells you that an agent regressed, not where. We present

arXiv:2606.11897v1 Announce Type: new Abstract: Scientific discovery workflows usually contain and rely heavily on lab notes, where researchers record observations, interpret uncertain results, and pl

Reminder that profiles are still one of the most powerful features in Hermes Agent that not everyone seems to have fully grasped. It's one of those things that's obvious in hindsight, but yeah - tryin

arXiv:2606.11816v1 Announce Type: cross Abstract: Forecasting real-world events requires language-model agents to reason under uncertainty from incomplete, time-bounded information. Yet evaluating whe

AI agents have become surprisingly good at talking to servers 🤖 The next challenge is getting them to interact with the environment users actually live in. 🧑‍💻 Browsers. 🖥️ Apps. 📱 Devices. 🌐 Local st

MotherDuck Corp., the maker of a cloud-native data warehouse based on the open-source DuckDB analytical engine, is betting that artificial intelligence agents will reshape how data pipelines are built

Introducing @PoeticHQ: a new AI system that executes complex multi-hour tasks with 99%+ accuracy and 10x fewer tokens than agents. We raised 50M at 500M from Kleiner Perkins, Founders Fund, First Harm

Introducing Write Gate in Hermes Agent. Now you have the capability to be able to approve/deny memory updates, skill updates, and skill creation with the same familiar mechanisms as approving dangerou

Most AI agents reset every session. @JenovaAIAgent's don't. Longest session on their platform: 16M tokens. All of it retrievable in <10ms via Pinecone vector retrieval. Result: Fast ramp to $1M+ ARR,

The Model Lab vs Agent Lab distinction is one of the clearest frameworks I've seen for understanding where AI value actually lives right now. TL;DR from @latentspacepod: • Model Labs compete on capabi

arXiv:2606.10423v1 Announce Type: new Abstract: Autonomous web navigation remains challenging for LLM agents, and the strongest generalist systems rely on proprietary reasoning models whose inference

arXiv:2606.09037v1 Announce Type: new Abstract: Interior permanent magnet synchronous motor (IPMSM) design requires balancing conflicting objectives and multi-physics constraints, while modern optimiz

arXiv:2606.08285v1 Announce Type: new Abstract: Large language models (LLMs) and agentic systems are increasingly proposed for financial trading, yet their reported performance remains difficult to co

This post shows engineering teams how to apply that principle to one of the most time-sensitive workflows in engineering: incident triage. You will build a custom incident triage assistant agent using

arXiv:2606.08661v1 Announce Type: cross Abstract: Data agents integrate LLM-driven reasoning with relational data access, executable analytical tools, and multi-step workflow orchestration, making the

arXiv:2603.03292v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) exhibit high reasoning capacity in medical question-answering, but their tendency to produce hallucinations and o

arXiv:2606.09641v1 Announce Type: new Abstract: The dominant paradigm in video retrieval relies on embedding-based full-corpus scanning, which suffers from inherent computational inefficiency and the

arXiv:2606.09692v1 Announce Type: cross Abstract: Delegation-scoped execution is not identifiable from standard observables: audit logs and execution traces can be identical under multiple incompatibl

arXiv:2606.08552v1 Announce Type: new Abstract: I discuss some quantitative representations of Promise Theory for processes involving autonomous agents. Agent models are common in software systems, ma

arXiv:2606.09730v1 Announce Type: new Abstract: Large language models are increasingly expected to handle complex, long-horizon real-world tasks whose context demands can grow without bound, yet model

arXiv:2606.08049v1 Announce Type: new Abstract: AI agents increasingly turn past experience into reusable artifacts such as code, workflows, and procedural memories. Reuse can improve efficiency, but

arXiv:2606.07552v1 Announce Type: cross Abstract: Large language models exhibit innate behavioral tendencies when deployed as strategic agents -- notably a risk-averse 'turtle' bias toward defensive p

arXiv:2606.08531v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly evolving from simple text-based interaction systems into LLM agents that can maintain memory, use tools, a

arXiv:2606.07649v1 Announce Type: cross Abstract: Long-form video generation requires systematic narrative planning and visual consistency that current short-clip methods cannot provide. Existing meth

arXiv:2606.09290v1 Announce Type: new Abstract: Visual reasoning requires integrating evidence distributed across regions, attributes, and relations, making single-chain reasoning prone to early perce

One year prior to this post, o3 represented the most advanced AI agent available, marking a significant milestone in AI development. The statement reflects how rapidly AI capabilities have evolved, wi

Hartley Charlton / MacRumors: Apple announces a new Foundation Models framework for developers, a new Core AI framework, and a set of Xcode enhancements aimed at agentic coding workflows — Apple today

arXiv:2603.13428v2 Announce Type: replace-cross Abstract: With AI agents increasingly deployed as long-running systems, it becomes essential to autonomously construct and continuously evolve customize

arXiv:2606.06532v1 Announce Type: new Abstract: Despite significant progress in agentic long video understanding, existing methods still lack detailed motion comprehension coupled with an efficient me

arXiv:2603.24481v2 Announce Type: replace Abstract: Miscalibrated confidence scores are a practical obstacle to deploying AI in clinical settings. A model that is always overconfident offers no useful