agents

arXiv:2607.07885v1 Announce Type: cross Abstract: Dynamic obstacle avoidance in unstructured outdoor environments remains a critical challenge for autonomous mobile robots, particularly when large-sca

arXiv:2607.08010v1 Announce Type: new Abstract: Production LLM agents often waste latency and reliability by regenerating code for the same procedural steps on every request. We replace this inference

arXiv:2607.08124v1 Announce Type: cross Abstract: The behavior of an LLM agent is determined not only by the underlying model, but also by its harness: the executable program that constructs context,

We’re Hiring: Software Engineer (R&D, Infrastructure and Platform Reliability) 🐟 https://sakana.ai/careers/infrastructure-platform-reliability-engineer/ Sakana Fugu, our Multi-Agent System as a Model,

The AI engineering world is using “loop” to describe several different agent architectures. This post maps execution loops, task loops, product loops, system loops, and the human oversight loop that c

arXiv:2607.07847v1 Announce Type: new Abstract: As large language models (LLMs) become increasingly capable, the next question is how can we enable models to continually learn? Today, the field largel

arXiv:2607.06990v1 Announce Type: new Abstract: Multi-robot systems provide the parallelism and redundancy necessary for long-horizon tasks, while Large Language Models (LLMs) offer the reasoning capa

A self-improving agent is conceptualized as a software factory—a system capable of generating and modifying code—that is directed toward improving its own codebase and capabilities. This framing sugge

arXiv:2607.07475v1 Announce Type: new Abstract: In robotics, the capability of an artificial agent to represent the range of its action possibilities, i.e. affordances, is crucial to understand how it

Infrastructure design is being redefined by agentic AI, pushing the industry toward system-level AI infrastructure optimization, balancing performance and cost across diverse workloads rather than foc

big update to openwiki - it now supports two modes: - code brain: create a wiki for a code base - personal brain: create a wiki for more general purpose tasks (email, web, etc) webinar at 11am PST (5

Built from scratch by Grok 4.5 + Grok Build in UE5.8: a cyberpunk L-corner street with neon facades, rain, signs, and crowds walking through the scene. End-to-end, the run took 10.75M tokens, 36.5 min

This OpenAI announcement highlights ChatGPT's expanded capabilities and positioning as a tool for complex, professional work rather than just simple queries. It likely covers new features, improved pe

arXiv:2607.06700v1 Announce Type: new Abstract: Multi-agent Simultaneous Localization and Mapping (SLAM) and collaborative SLAM (CSLAM) require robots to continuously exchange global descriptors (GDs)

arXiv:2607.06691v1 Announce Type: new Abstract: Human-human collaboration is a fundamental aspect of everyday life, essential to success in a wide range of goal-directed activities from household task

arXiv:2508.00554v4 Announce Type: replace-cross Abstract: In financial trading, large language model (LLM)-based agents demonstrate significant potential, but their decisions can be sensitive to noisy

As agentic AI accelerates enterprise transformation, data sovereignty is crystallizing from a compliance checkbox into a foundational strategic imperative — one that determines not just where data liv

arXiv:2511.23347v2 Announce Type: replace Abstract: An associative memory (AM) enables cue-response recall, and it has recently been recognized as a key mechanism underlying modern neural architecture

arXiv:2607.07139v1 Announce Type: new Abstract: Underwater robots often operate near delicate targets where high-power thrusters resuspend sediments and induce turbulence, degrading image quality at t

arXiv:2603.21489v2 Announce Type: replace-cross Abstract: AI agents have become increasingly capable at isolated software engineering (SWE) tasks such as resolving issues on Github. Yet long-horizon t

arXiv:2607.06964v1 Announce Type: cross Abstract: Bridging the gap between human pilot intent and autonomous flight operation is critical for real-world electric vertical takeoff and landing (eVTOL) a

For coding agents, trustworthiness has to be tested in the harness where the model actually writes code. In one surveillance scenario, Kimi K2.7 complied with the request in 8/8 samples. SWE-1.7 refus

arXiv:2607.06786v1 Announce Type: cross Abstract: Standards bodies, including TM Forum, 3GPP, and ETSI, are converging on Agentic AI as the foundation for next-generation network management, where Lar

arXiv:2607.07321v1 Announce Type: new Abstract: Tool utilization enables Large Language Model (LLM) agents to interact with the real world and resolve complex tasks. However, existing agent frameworks

arXiv:2607.07702v1 Announce Type: new Abstract: The optimization of long-horizon agents increasingly relies on reflection-based mechanisms, where a large language model (LLM) acts as an optimizer to d

Fun conversation with @swyx on our journey building the cloud for true elastic inference, sandboxes, and more. And of course, how we're evolving Modal's dev experience to be better for agents. Modal's

arXiv:2607.07626v1 Announce Type: cross Abstract: Reliable confidence estimation is essential for deploying large language models (LLMs) in confidence-aware systems, where downstream decisions such as

arXiv:2607.07029v1 Announce Type: cross Abstract: Reinforcement learning (RL) policies can be unsafe and vulnerable to attacks. Ensuring their reliability is often a pain point as existing automated t

Grok 4.5 on OpenClaw Grok 4.5 from @SpaceXAI is live on OpenClaw. No OpenClaw update required, just connect your X Premium or SuperGrok subscription, select Grok 4.5 under the xAI provider, and use an

Yohei Nakajima created a virtual dance studio application in Replit that uses computer vision to analyze uploaded dance videos and automatically generates corresponding 3D rig animations. The project

arXiv:2607.06619v1 Announce Type: cross Abstract: Modern processor verification struggles to reach deep architectural states due to the inefficiencies of traditional mutation-based fuzzing. We propose

A demonstration of an AI agent with iPhone integration that autonomously ordered a donut, showcasing early progress in agentic AI capabilities. The demo was presented publicly by AGI Inc and Div Garg,

Hermes Agent is a project from Nous Research focused on developing agentic AI systems capable of autonomous reasoning and task execution. The initiative likely explores methods for creating AI agents

Introducing Evan by Zams. The AI that prepares you for high-stakes meetings. Evan gathers context from all your tools, conducts CIA-level research and builds you a presidential-style briefing before e

Introducing Muse Spark 1.1 Following Muse Spark in April, here's Muse Spark 1.1 - the first Spark model to offer an API. Meta claim significant improvements in agentic tool calling and computer use. T

Join us for a LangChain + Clay meetup with @palashshah, @jeffbarg, Vyshu Khota, and Soroush Khadem. https://luma.com/jqif2hti Palash will break down how he built a self-improving agent at LangChain, L

This post critiques Apple's significant financial investment in Apple Intelligence, suggesting the AI features are underwhelming or disappointing relative to the spending. The tweet appears to be a co

John Reynolds / Tech.eu: Kraken Technology, which designs and builds autonomous maritime platforms, such as uncrewed subsurface vessels, raised a 175M Series B at a 1B valuation — It says it will use

arXiv:2607.07136v1 Announce Type: new Abstract: This paper presents a Spatiotemporal Tube (STT)-based control framework for general unknown nonlinear Euler-Lagrange (EL) systems subject to input const

Low user caps in LlamaParse? Gone.🎉 Every plan — Free through Pro — now unlocks up to 100 team members. No more picking who gets a seat. No more shared logins. No more upgrading just to invite a teamm

Mark Zuckerberg hasn’t posted since 2023. X is the global town square — this is where news happens. (1) Today we're releasing Muse Spark 1.1 -- a strong agentic and coding model at a very low price. I

MCP tool design involves deciding the granularity of tools—whether they map to individual API calls or complete workflows—which directly impacts how many tools agents need and their effectiveness. Eff

arXiv:2607.07040v1 Announce Type: new Abstract: How can we measure intelligence beyond human capability? Human-authored benchmarks saturate, and above human capability, examiners may not know which ta

Ina Fried / Axios: Meta prices Muse Spark 1.1 at 1.25/1M input tokens and 4.25/1M output tokens; Alexandr Wang says improving coding and agentic performance was a key focus — Facebook's parent company

arXiv:2607.07383v1 Announce Type: new Abstract: Knowledge-based Visual Question Answering (KB-VQA) requires models to retrieve visual entities matching the query image from large-scale encyclopedic kn

Neat Grok 4.5 reviewed a full Credit & Security Agreement stored in Box — the kind of dense, multi-section facility document that typically requires significant counsel time. @Grok 4.5 used Box MCP to