Skip to content
Thursday, 19 November 2026
Tenesys AI News
Subscribe

All News

TENESYS AI NEWS tracks the most important AI news and explains what changed, why it matters and whether a technology is worth testing.

“LLM” — 70 articles ✕

Research· Important· 🧪 Worth Testing

AWS introduces push-based KV transfer to cut latency in disaggregated vLLM inference

AWS released a push-based NIXL connector for vLLM that changes how key-value (KV) cache data moves between prefill and decode instances in disaggregated LLM serving. Instead of the decode instance pulling KV blocks after prefill finishes, the decode instance registers its target memory in advance and the prefill instance writes the KV data directly once ready, moving coordination work off the critical path. Benchmarked on a 1-prefill/1-decode Qwen3-32B deployment using EC2 P5en instances with EFA, push mode delivered up to 3x better time-to-first-token (TTFT) and up to 30% better time-per-output-token (TPOT) than the default pull mode, especially under high request rates.

AWS Machine Learning
Agents· 🧪 Worth Testing

Google Cloud outlines a three-layer agent architecture for high-compute, governed biotech workflows

Google Cloud published a reference architecture for building AI agents that coordinate long-running, GPU-heavy scientific tasks like protein folding and compound screening, which break standard single-LLM-agent setups due to timeouts and context overflow. The design separates a cognitive orchestrator (Gemini on Agent Runtime) from a GPU execution layer (NVIDIA NIMs like ESMFold and GenMol on GKE) and wraps both in an enterprise governance plane with agent identity, a gateway, a registry and Model Armor. It also lays out best practices such as passing bulky data by reference instead of inline, streaming progress updates, and gating irreversible actions behind human approval.

Google Cloud AI
Models· Important· 🧪 Worth Testing

IBM combines transcription, decision-making and chat in a single Granite Switch model

IBM has released Granite Switch 4.1 in 8B and 30B sizes, a modular system that runs chat, decision-making and speech transcription from one hosted endpoint instead of separate models. The update adds a general-purpose Decision adapter, a specialized Guardian adapter for safety-related classifications, and an embedded ASR model, Granite-Speech-5.0-Turbo-CTC, which tops the OpenASR Leaderboard. Despite bundling three capabilities, the combined model uses roughly the same VRAM as the base model alone.

Hugging Face
Models· Important· 🧪 Worth Testing

Meta releases Muse Spark Open, an 816B-parameter open-weight multimodal MoE model

Meta published Muse Spark Open, an open-weight mixture-of-experts model with about 816 billion total parameters and 42 billion active per token. It accepts text, images, audio and video as input and generates text, with a context window of up to 1 million tokens. Meta positions it as a coding-optimized, agentic model built on top of the smaller Muse Glimmer architecture, calling it the most capable US open-weights model released so far.

Hugging Face
Models· Important· 🧪 Worth Testing

Apertus 1.5 adds image/audio understanding, longer context and a thinking mode to the open 8B/70B models

Swiss AI released Apertus 1.5, a continued pretraining of its open Apertus 1.0 models (8B and 70B, Apache 2.0) with native image and experimental audio understanding, a 4x larger context window of 262,144 tokens, an optional thinking mode, and improved instruction-following and tool use. The models were trained on a total of 19T (8B) and 17T (70B) tokens, with full training data, recipes and intermediate checkpoints published for reproducibility. The team also published detailed, standardized evaluation cards and announced early API access from providers like Swisscom and Infomaniak, plus a roadmap for a ~600B-parameter MoE Apertus 2.0.

Hugging Face
Voice AI· 🧪 Worth Testing

Small Fine-Tuned Model Learns to Follow New Regulated Call Scripts Without Retraining

Researchers describe a system called FlowSpec that converts a creditor's legal call procedure into machine-readable instructions, tool restrictions, training signals and test cases for a voice agent. A 9-billion-parameter model was trained on calls covering nearly 300 randomly generated procedures, then tested on four procedures it had never encountered, including one entirely held-out family of scripts, to see whether compliance behavior transfers.

arXiv cs.CL
Cyber Security· Important· 🧪 Worth Testing

GitHub swaps LLM-based secret scanner for a lightweight ModernBERT classifier

GitHub replaced its LLM-based pipeline for detecting generic secrets (like passwords and API keys) with a fine-tuned ModernBERT classifier combined with regex candidate generation. The new two-stage system improved detection accuracy while cutting scan time and serving costs dramatically, and it's now fast enough to run during push protection, not just after code is committed.

GitHub
Models· Important· 🧪 Worth Testing

Liquid AI's new open-weight model runs agentic reasoning locally with just 2B active parameters

Liquid AI has published LFM2.5-24B-A2B, a mixture-of-experts model with 24B total parameters but only 2B active per token, designed to run reasoning agents on local hardware. The release expands the context window to 131K tokens, doubles the vocabulary size, and was trained on roughly double the pretraining data of its predecessor. On agentic and tool-use benchmarks the model performs on par with or better than models that have about 50% more parameters, while delivering fast inference speeds on both consumer and data-center hardware.

Hugging Face
Agents· Important· 🧪 Worth Testing

Orca Security cuts natural-language query costs 90% using a staged Bedrock agent pipeline

Orca Security built Discovery AI, an Amazon Bedrock-based agent that turns plain-English security questions into structured queries against its Sonar system, which tracks over 900 cloud resource types. Rather than relying on one large model with the full schema stuffed into every prompt, the production version splits the work across nine specialized stages and multiple foundation models. The result: dramatically lower cost, faster responses, and better accuracy on complex queries, now running live since March 2026.

AWS Machine Learning
Research· 🧪 Worth Testing

AWS open-sources MoE kernel optimizations for vLLM, cuts latency and boosts throughput on H200

AWS detailed three kernel-level optimizations for Mixture-of-Experts (MoE) model serving on Hopper GPUs, implemented in collaboration with the vLLM community and shipped in Amazon SageMaker AI's LMI container. The changes target the inefficiencies of fused MoE computation during low-batch decode, which previously left Tensor Cores underutilized. Combined, the optimizations deliver up to 10% higher throughput and up to 9% faster time-to-first-token (TTFT).

AWS Machine Learning
Business· Important· 🧪 Worth Testing

NVIDIA Open-Sources Run:ai GPU Orchestration Platform

NVIDIA has released the full Run:ai platform as open source, adding it as a foundation of the NVIDIA DSX AI Factory Platform for AI workload and GPU orchestration on Kubernetes. The release includes four modular components — KAI Scheduler, GPU Fractioning Operator, KAI Resource Management, and Workload Map — that can be adopted together or independently. Eight ecosystem partners, including Crusoe, Mirantis, Nebius, OpenNebula Systems, Rafay, Saturn Cloud, Spectro Cloud, and vCluster, are integrating the platform into their own offerings.

NVIDIA Developer
Research· Important· 🧪 Worth Testing

Amazon's 'Priming' Turns Pretrained Transformers Into Efficient Hybrid Models for Under 1% of Training Cost

Amazon Web Services researchers published a method called 'priming' that converts pretrained Transformer models into hybrid architectures mixing attention and state space model (SSM) layers, reusing existing weights instead of retraining from scratch. The approach cuts pretraining costs by over 99% and lets a 32-billion-parameter hybrid model match its source Transformer's quality while decoding up to twice as fast. Amazon tested three SSM types and released an open-source model zoo, training code, and serving tools under Apache 2.0.

Amazon Science
Voice AI· Important· 🧪 Worth Testing

Mistral releases open-source real-time Arabic speech-to-text model Voxtral Mini 4B Realtime Arabic

Mistral AI has released Voxtral Mini 4B Realtime Arabic, a streaming speech-to-text model fine-tuned for Arabic dialects, Modern Standard Arabic, and code-switching between languages. The 4.4-billion-parameter model processes 16 kHz audio in real time with a configurable transcription delay, achieving an 8.82% average Character Error Rate across seven Arabic benchmarks at a 480ms delay — close to the offline Voxtral Transcribe Arabic model's 7.91% CER. It was co-developed with Morocco's digital transition ministry as part of a sovereign AI partnership and is released under Apache 2.0.

Mistral AI (Hugging Face)
Models· Important· 🧪 Worth Testing

Google Open-Sources ML Drift, a New GPU Engine for On-Device AI Inference

Google released ML Drift, an open-source, cross-platform GPU compute engine for on-device ML inference, replacing the legacy TFLite GPU delegate. It unifies shader handling across OpenGL ES, OpenCL, Metal and WebGPU, adds 5D tensor support, and introduces stage-aware optimizations for LLM prefill/decode. It is already running in production in Chrome, YouTube Shorts, Google Photos, Meet and partner apps from Adobe and Snap.

Google Developers
Agents· 🧪 Worth Testing

Google opens a dedicated API for grounding AI agents in its developer docs

Google has released the Developer Knowledge API, a structured, machine-readable source for Google Cloud, Firebase and Android documentation aimed at AI agents and developer tooling. Instead of scraping web pages or relying on an LLM's training cutoff, agents and CLIs can now query fresh, Markdown-formatted docs through several interfaces: a gcloud CLI surface, an installable agent skill, client libraries, and a browser-based API explorer. The underlying index is refreshed frequently so retrieved answers stay close to the latest published documentation.

Google Developers
Cyber Security· Important· 🧪 Worth Testing

AWS adds real-time permission checks to RAG in Amazon Quick and Bedrock Knowledge Bases

AWS describes a new two-stage access control architecture for Retrieval Augmented Generation (RAG) in Amazon Quick and Amazon Bedrock Knowledge Bases. Instead of relying only on periodically synced access control lists (ACLs), the system now verifies permissions in real time against the authoritative data source (e.g. Google Drive, SharePoint, Confluence) at query time, before passing content to the LLM. AWS says this closes security gaps caused by stale or incorrectly mapped permissions between sync cycles. Mondelēz International, with over 35,000 employees, is cited as a customer using this approach.

AWS Machine Learning
Voice AI· Important· 🧪 Worth Testing

AssemblyAI adds Qwen3.5 4B to LLM Gateway for fast voice-transcript rewriting

AssemblyAI launched a hosted deployment of the open-source Qwen3.5 4B model on its LLM Gateway, optimized specifically for rewriting raw speech-to-text output into clean, formatted text. On voice rewrite tasks like dictation cleanup and transcript formatting, the model averaged 612ms response time—1.9x faster than GPT-4.1—at 94% lower cost per hour of audio processed. The model is priced at $0.10/$0.50 per million tokens (prompt/completion) and supports only max_tokens, temperature, and stream parameters, with no tool calling.

AssemblyAI
Models· Important· 🧪 Worth Testing

Google ships EmbeddingGemma 2, an open multimodal embedding model for RAG

Google has launched EmbeddingGemma 2, a Gemma 4-based embedding model released under Apache 2.0 that places text, code, images, video and audio in one shared 768-dimensional vector space. It's modular, so developers load only the encoders they need: 270M parameters for text and code alone, scaling up to 740M for every modality. Google reports a 14% jump over EmbeddingGemma 1 on the MTEB Code benchmark while keeping the earlier model's multilingual text accuracy.

Google Developers
Research· Important· 🧪 Worth Testing

GitHub opens up ReviewBench to standardize how AI code reviewers get graded

GitHub has published ReviewBench, a research-preview benchmark designed to compare AI code review agents on a common, auditable standard. The dataset draws on 219 real public pull requests across 19 languages and 187 repositories, chosen to mirror the language and size distribution found across 103.9 million GitHub pull requests. Ground truth comes from a blended pool of human reviewers, static analysis tools, and multiple frontier LLMs, cross-checked by senior engineers who agreed with the benchmark's labels 96.6% of the time. GitHub says it has already used ReviewBench internally to track its own Copilot code review (CCR) product, and that offline benchmark movement reliably predicted the direction of later production A/B tests.

GitHub
Cyber Security· Important· 🧪 Worth Testing

GitHub's open-source AI agent found 24 Android app vulnerabilities

GitHub Security Lab built an open-source 'Taskflow Agent' that uses custom AI prompt workflows to audit code for vulnerabilities, and used it to find and report over 24 vulnerabilities in Android applications. Two detailed examples show the agent finding a location-tracking flaw in the OsmAnd navigation app and an account-takeover chain in the Wikipedia Android app via a deeplink parsing bug. The team notes LLMs are strong at finding complex logic vulnerabilities and understand API behavior well, but struggle to correctly judge severity and often produce false positives, so findings still require human review. The taskflows are open source and can be run on any GitHub repository via a Copilot-powered codespace script, though running them consumes premium model requests and can take hours.

GitHub Security
Agents· 🧪 Worth Testing

AWS Publishes Guide for Connecting Claude Desktop to a Secure Managed Web Search Tool via AgentCore

AWS released a step-by-step walkthrough showing how to give Claude Desktop (on Amazon Bedrock) live internet access through Amazon Bedrock AgentCore Gateway, closing the gap left by the model's training cutoff. The setup wires AWS IAM Identity Center SSO through Amazon Cognito as a SAML-to-OAuth federation layer, issuing JWTs that the AgentCore Gateway validates on every request. The Web Search capability itself is MCP-compatible and runs on an internal Amazon web index covering tens of billions of documents, so no query traffic leaves AWS and no third-party API key is needed. The feature is currently limited to three AWS Regions: us-east-1 (N. Virginia), eu-west-1 (Ireland), and ap-northeast-1 (Tokyo).

AWS Machine Learning
Agents· Important· 🧪 Worth Testing

Google's Antigravity SDK Adds Local Offline Model Support with Gemma 4 26B

Google announced that its Antigravity SDK now supports running agentic workflows locally and offline, with initial support for Gemma 4 26B A4B running via Google AI Edge's LiteRT. Developers can build agents that run entirely on-device, without cloud API costs or internet dependency. Google also demonstrated a hybrid 'Architect-Builder' pattern where a cloud model (Gemini 3.8 Flash) plans tasks and a local swarm of Gemma 4 26B instances does the heavy execution, keeping source code off the cloud.

Google Developers