Knowledge catalogue
arXiv:2607.22371v1 Announce Type: new Abstract: Few-shot learning enables medical image segmentation models to adapt to new tasks using only a small number of labelled examples. However, adaptation pe
arXiv:2604.02441v2 Announce Type: replace Abstract: Hybrid state estimators that combine model-based Kalman filtering with learned components have shown promise on simulated data, yet their performanc
arXiv:2607.22385v1 Announce Type: cross Abstract: Diagnosing the root cause of anomalies is essential for safe industrial operation. Despite extensive sensor instrumentation, formulating hypotheses an
Are agent skills always worth using? The answer is no? This paper provides some important insights to understand this more. (bookmark it) Paper summary: Adding procedural skills to an agent is usually
arXiv:2607.22494v1 Announce Type: cross Abstract: Collision anticipation in autonomous driving requires not only accurate early warnings but also interpretable reasoning about what risk factors are be
arXiv:2607.22511v1 Announce Type: cross Abstract: Automating theoretical research is constrained not only by the generation of candidate results, but also by their reliable evaluation. A common approa
arXiv:2607.22409v1 Announce Type: new Abstract: Motion planning algorithms compute control sequences that drive autonomous robots to goal regions while avoiding unsafe states. Existing methods, from s
arXiv:2607.22123v1 Announce Type: new Abstract: Visual inertial odometry (VIO) is essential for accurate 6-DoF motion estimation in mobile robotic systems. Recent learning-based VIO methods have shown
arXiv:2601.17303v2 Announce Type: replace Abstract: As Industrial Internet of Things (IIoT) environments scale to tens of thousands of connected devices, centralized security architectures introduce l
arXiv:2601.10554v3 Announce Type: replace Abstract: The efficacy of autonomous driving systems hinges critically on robust prediction and planning capabilities. However, current benchmarks are impeded
arXiv:2601.17454v2 Announce Type: replace-cross Abstract: Centralized value learning underlies a broad class of multi-agent reinforcement learning methods, but its claimed advantage is typically evalu
How Booking.com built a unified AI observability stack with Arize for agentic GenAI workflows and traditional ML — from telemetry collection and PII redaction to latency monitors and evaluations. The
arXiv:2506.13553v4 Announce Type: replace Abstract: Road topology reasoning is fundamental for autonomous driving, requiring both accurate perception of road elements and understanding of their comple
here’s a video on my approach at applying this to agents w @activegraphai: 🆕 ActiveGraph: The Log is the Agent my talk from AI Engineer is live!!! 😆 https://www.youtube.com/watch?v=khVX_BUnEwU it's ab
arXiv:2607.21832v1 Announce Type: cross Abstract: Recent advances in large language models and their rapid adoption across software engineering tasks have made Artificial Intelligence (AI) coding agen
In partnership with @Kimi_Moonshot, we now have K3 on Together APIs with capacity for hundreds of millions of TPM on launch day! Kimi K3 is now live on Together AI. We’re proud to be a Day 0 launch pa
arXiv:2607.22153v1 Announce Type: cross Abstract: Industrial health management increasingly relies on heterogeneous information sources, including condition monitoring systems, supervisory control and
arXiv:2607.22172v1 Announce Type: new Abstract: Accurate yet low-latency depth is essential for radar-camera perception in autonomous systems. Cameras provide rich appearance but lack metric scale, wh
Kimi K3 is now available on @digitalocean 's Serverless Inference! Developers can start building with our most capable model in minutes. .@Kimi_Moonshot K3 from Moonshot AI is now live on DigitalOcean
Kimi K3 is now live on Together AI. We’re proud to be a Day 0 launch partner for @Kimi_Moonshot’s open frontier model, built for long-running agentic workflows across code, tools, vision, and research
Kimi K3 is now live on @togethercompute! Happy to have Together AI as our day0 launch partner, giving developers immediate access to K3 through high-throughput inference optimized for coding agents an
arXiv:2607.22313v1 Announce Type: cross Abstract: Estimating contemporaneous bidirectional interactions from observational data is difficult because each outcome is endogenous to the other, while flex
arXiv:2607.22399v1 Announce Type: cross Abstract: We consider the problem of learning from a single finite trajectory of an ergodic stochastic dynamical system. More precisely, we study discrete-time
Looking forward to chatting with @hugobowne today (July 27) at 4 pm PT on the Vanishing Gradient livestream on YouTube. Will cover open source, the newest LLMs & trends, agent frameworks, and whatever
arXiv:2508.12393v3 Announce Type: replace Abstract: The rapid expansion of medical literature challenges the scalable structuring of domain knowledge. Knowledge Graphs (KGs) offer a solution, yet curr
Microsoft AI: Microsoft says MAI-Cyber-1-Flash and MDASH, its vulnerability identification harness, deliver “world-class performance at 50% of the cost of leading models” — Today we're announcing MAI-
Microsoft Corp. today introduced its first in-house cybersecurity model, MAI-Cyber-1-Flash, and a companion agentic system called Project Perception that fields teams of artificial intelligence agents
arXiv:2607.21946v1 Announce Type: new Abstract: This technical report presents our approach to Challenge Track~3: SeePhys Pro at the 3rd AI for Math Workshop, where the task is to answer college-level
Powered by Cohere’s secure agentic platform North, Automations enable employees, regardless of their technical abilities, to: 1. Turn complex workflows into simple outputs 2. Stay in control at each s
the paper: babyagi has ~200 citations, but 0 papers... i just published my first paper on arXiv 😆 'The Log is the Agent: Event-Sourced Reactive Graphs for Auditable, Forkable Agentic Systems' https://
This release marks a significant step forward in making agentic AI practical, scalable, and deeply integrated into daily business operations. Automations is available today to all North customers. Lea
Together gives developers an efficient, high-throughput production path for K3’s long, tool-heavy agent workloads, hosted on Together AI’s US-based infrastructure with zero data retention. Start build
arXiv:2607.21887v1 Announce Type: cross Abstract: Foreign language anxiety (FLA) can be a major barrier to second language acquisition (SLA), especially in conversational contexts. With the proliferat
arXiv:2607.14514v2 Announce Type: replace Abstract: Training-free ObjectNav agents increasingly use vision-language models (VLMs), yet typically discard acquired scene knowledge after each request. We
Together AI has released the Kimi K3 model on its platform as a Day‑0 launch partner for Moonshot AI’s open frontier agentic model, which supports long‑running workflows across code, tools, vision and
Chris Metinko / Axios: Way Security, which uses AI-driven automation and agentic workflows to help deploy IAM systems, raised a 20M seed from Insight Partners and Glilot Capital — Way Security raised
We've open-sourced AgentENV in collaboration with kvcache-ai. AgentENV is a distributed system for running agent environments at scale. Its components power agentic RL training for Kimi K3, with fast
Comfy MCP enables users to create ComfyUI workflows from any location by simply describing their ideas. An AI agent will automatically build the workflow, after which the user can monitor progress unt
Enterprise investment in agentic artificial intelligence is accelerating, but the infrastructure supporting those systems is still catching up. Organizations are moving agents into customer support, s
The thread argues that applied AI has entered a distributed‑systems phase, with event‑driven architectures treating logs as “agents” that consume data rather than serve as endpoints. It notes that alm
“The first autonomous agent cyberattack is an unprecedented event. It deserves an unprecedented response!” In the spirit of transparency, here’s what I asked @OpenAI: • Radical transparency: let’s rel
This blog is full of design choices as you build your Agentic systems. Critical choices to be made, evals need to be upgraded if the underlying intelligence is upgraded. Well thought out blog—new stre
We turned the browser into the inference server. @RunAnywhereAI ( @runanywhere/web ) runs models client-side with WebGPU + WASM SIMD, stores them in OPFS and generates with 0 outbound bytes. No backen
As AI expands into robotics and other real-world applications, the focus is shifting toward integrated platforms that simplify development and deployment. Open ecosystems and standardized architecture
Twenty years on, AWS EC2 compute is meeting demand shaped by agentic AI, physical AI, and customers pushing general-purpose cloud infrastructure into new territory its earliest architects never antici
Diffusion LLMs can now handle real agentic work. LLaDA 2.2 is the first large-scale diffusion LLM built to operate as a real agent, planning, calling tools, and self-correcting across long multi-turn
In the spirit of transparency, here’s what I asked @OpenAI: • Radical transparency: let’s release the traces from the “rogue” agents so the entire research community can study what happened. • More ca
I was exploring how to prompt the voice chat so that it can correctly count the number of “e”s in seventeen (which it fails most of the time). At the beginning of a new chat, instead of counting “e”s
“one OAI agent appeared to leave notes for future versions of itself that lay out instructions for how to free themselves from OpenAI’s internal constraints, per sources” I don’t think this kind of pr
OpenAI’s agent went rogue, escaped containment, and spent days hacking Hugging Face. Before that, an OpenAI agent reportedly left notes for future versions of itself explaining how to break free from
Reuters confirms my hypothesized time line. OpenAI did not realize its AI has breached the sandbox for a week. Astounding. https://www.reuters.com/business/its-ai-agent-spent-days-hacking-company-sour
LangChain proposes using Langsmith traces to fine‑tune open‑source models within the AI Development Lifecycle (ADLC). A tweet by Harrison Chase (@hwchase17) on July 25, 2026 invites interested users t
web archive for agent testing 🔍 Introducing BackSearch. LLMs are increasingly asked to predict the future, but a good backtest requires a snapshot of the internet at a point in time. BackSearch allows
Yikes New details about the Hugging Face incident from Reuters. The report says OpenAI noticed odd behavior before the event, including an agent leaving notes for future versions of itself with escape
arXiv:2607.20748v1 Announce Type: cross Abstract: Impact hammers, also known as rock-breakers, are essential machines in mining operations, where they perform secondary reduction. In underground minin
arXiv:2607.21437v1 Announce Type: new Abstract: Deep learning models can effectively use Rapid Evaporative Ionization Mass Spectrometry (REIMS) data for surgical margin assessment. However, their clin
// Agentic Context Management // Great read for the weekend. (bookmark it) Production agents fail less on reasoning and more on what sits in their context. Conversation history, big prompts, huge tool
arXiv:2607.21503v1 Announce Type: new Abstract: Production AI agents' failures are less often due to an inability to reason well and more often because they cannot manage what is in their reasoning co
arXiv:2607.20452v1 Announce Type: new Abstract: Modern software quality assurance demands intelligent, autonomous systems capable of adaptive decision-making across distributed cloud environments. Thi
The transition from chatbots to autonomous agents is changing the shape of demand itself, and tokenomics — the economics of AI token consumption — is emerging as the defining constraint on enterprise