AWS announces general availability of AWS Interconnect - multicloud connectivity with Microsoft Azure
“Current browse context: Bibliographic and Citation Tools Code, Data and Media Associated with this Article Demos Recommenders and Search Tools arXivLabs: experimental projects with community collaborators Have an idea for a project that will add value for arXiv's community?”
“Using a drop-in MLP kernel as a steppingstone to profile the shortcomings of the pre-built implementation, we wrote a custom weight-stationary fused SwiGLU MLP kernel that eliminated the HBM stalls.”
Computer Science > Artificial Intelligence [Submitted on 18 Nov 2026] Title:KnowledgeClaw: Towards Agentic Knowledge Engineering via Omnimodal Hypergraphs View PDF HTML (experimental) Abstract:Knowledge engineering (KE) turns raw files into a reasoning-ready knowledge base, a task now within reach of LLM agents. KE has progressed from chunk and graph retrieval-augmented generation (RAG) to memory agents, agentic KE and multimodal KE. However, a live knowledge base needs omnimodality, a closed-loop lifecycle and multi-granular application at once, yet existing systems meet at most two and no benchmark measures all three.
Computer Science > Computation and Language Title:Piccolo: Co-Evolving Decision Models and Data through Recursive Self-Improvement View PDF HTML (experimental) Abstract:We present Piccolo, a family of multimodal decision models (0.8B to 27B) that coevolves model capabilities and training data via Agentic Data Engineering and recursive self-improvement (RSI). The models predict probabilities over candidate answers for general-purpose text and visual judgments, agent harnesses, data workflows, and interactive games. Piccolo-27B tops the Decision Index Vision Full leaderboard with a score of 75.59, while Piccolo-9B and Piccolo-4B achieve 68.35 and 67.46, respectively.
Computer Science > Software Engineering Title:The Obsolescence of High-Level Code: Agentic Generation from Semantic Artifacts View PDF HTML (experimental) Abstract:This paper argues that high-level source code need not remain the primary persistent artifact of software development when AI agents can generate, validate, and regenerate executable implementations from semantic intent. We place this claim in historical context by revisiting application generators, CASE tools, model-driven development, and platforms such as GeneXus, where developers already maintained higher-level representations from which code and other artifacts were derived. We propose a unifying view in which generation is t
At Exa , we are building one of the few true web indexes by aggregating and serving knowledge from across the web, along with private and synthetic sources. We optimize the index for semantic search, grounding agents and humans in true, high-quality data. We use multi-tower semantic machine learning (ML) models to embed web data and query data into the same vector space, so users can express complex queries in natural language alongside traditional keyword search.
Microsoft is replacing outside AI models in its own products with cheaper in-house alternatives Key Points - Microsoft's AI division unveiled seven specialized models for code, IT security, image editing, speech, and workflow decisions at its Ignite conference. All are aimed at cutting operating costs for always-on AI agents. - The models target OpenAI's and Anthropic's systems as cheaper alternatives. The coding model MAI Code 2 nearly matches GPT-6.1 Sol and Claude Opus 5.5 on internal benchmarks at a fraction of the cost.
TL;DR - Attackers move first. On average, exploitation now starts before a patch exists (Mandiant M-Trends 2026). In 1H 2026, 23% of vulnerabilities VulnCheck added to its exploited list were hit on or before disclosure day. - AI pentesting vendors aren't interchangeable.
As enterprises build production agents with dozens of tools and large structured inputs, token consumption and latency become the primary blockers to a good user experience. When these agents process large JSON data, every additional tool invocation injects the full payload into the large language model (LLM) context window, causing token usage and response latency to spike. Over multi-turn conversations, this pressure compounds, driving up costs and degrading response quality.
The biggest cost lever in a generative AI system is whether you call a model at all. We often see teams route every task through a large language model (LLM), including input validation, formatting, and routing. Each call is cheap in isolation, but at production scale these small costs become one of the largest line items in the architecture.
Agentic workloads, long documents, and large codebases are pushing context lengths from tens of thousands of tokens to hundreds of thousands. At those lengths, attention becomes the most expensive part of a transformer layer. Dense attention scores every query against every key, so its cost per query grows with the context length N, and at 128K tokens it can take most of the prefill time in a layer.
AWS announces general availability of AWS Interconnect - multicloud connectivity with Microsoft Azure AWS announces the general availability of AWS Interconnect - multicloud with Microsoft Azure. Customers have been adopting multicloud strategies while migrating more applications to the cloud. They do so for many reasons including interoperability requirements, the freedom to choose technology that best suits their needs, and the ability to build and deploy applications on any environment with greater ease and speed.
Agentic workloads are demanding more from inference systems. AI agents carry growing conversation histories across turns and generate a mix of reasoning, tool calls, and responses. Inference systems must support users at scale while remaining responsive.
Agentic AI is reshaping scientific research and innovation. Researchers communicate complex scientific hypotheses in natural language and let autonomous agents independently plan tasks, execute simulations, evaluate results, and self-correct across multiple iterations. Scientific agents are taking on longer, more complex, and increasingly visual workflows.