Search: “agents”

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:2606.20659v1 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

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: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

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 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

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: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:2606.09730v1 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:2606.07649v1 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: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

arXiv:2602.21889v2 Announce Type: replace Abstract: Predictions from ML models support human decision making in several fields, including high-stakes ones such as healthcare and the judiciary. Yet, we

A super useful feature I like that we have in Grok Build: we load your .envrc and pass it straight into the agent’s shell environment. Same API keys, PATH, sccache, remote caches, .etc — everything yo

arXiv:2606.06448v1 Announce Type: new Abstract: LLM agents are increasingly deployed on long-horizon tasks requiring sustained reasoning over extended interaction histories. Realizing this at scale re

This post describes the automatic features of a coding agent built on ActiveGraph, highlighting that developers receive both an execution trace and a visual graph representation without additional con

Open-source AI Agent Security resource , fully on the @LangChain 🦜 stack. It shows real attacks (prompt injection, Indirect prompt injection, tenant data exfiltration, memory poisoning) and the securi

The Hermes Agent Dashboard's skills hub integration search functionality has been enhanced to provide more comprehensive results and improved information delivery to users. This update, shared by Nous

arXiv:2512.05774v2 Announce Type: replace-cross Abstract: Long video understanding (LVU) is challenging because answering real-world queries often depends on sparse, temporally dispersed cues buried i

Cloudflare Inc. co-founder and Chief Executive Matthew Prince says that artificial intelligence agents now drive the bulk of the internet’s traffic, having surpassed human web activity for the first t

arXiv:2606.05669v1 Announce Type: new Abstract: Robotic Cellular Warehousing Systems (RCWS) give rise to multi-agent pickup and delivery (MAPD) processes in which robots sequentially collect multiple

Cursor's visual prompts feature helps bridge the understanding gap between user interface elements and AI agent perception by providing clearer visual cues and contextual information. This enhancement

Jeremy Howard discusses a significant increase in output capabilities driven by agentic AI systems, while noting that adoption rates remain completely flat across the board. The observation suggests a

arXiv:2606.04492v1 Announce Type: new Abstract: Cooperative Multi-Agent Reinforcement Learning (MARL) frequently suffers from severe reward sparsity and exploration bottlenecks. While episodic memory

arXiv:2603.24747v2 Announce Type: replace Abstract: The emergence of large language model agents capable of invoking external tools has created urgent need for formal verification of agent protocols.

arXiv:2606.05002v1 Announce Type: new Abstract: LLM-based multi-agent systems are increasingly used for strategic decision-making tasks. In such settings, performance depends not only on individual mo