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” — 87 articles ✕

Models· Important· 🧪 Worth Testing

Amazon SageMaker AI introduces KV cache-aware routing for LLMs

Amazon SageMaker AI has launched a new 'KV_AWARE' routing strategy that directs LLM inference requests to instances based on their actual KV cache state rather than just prompt headers. This optimizes multi-turn conversations and long-context workloads by ensuring requests land where relevant data is already cached.

AWS Machine Learning
Models· Important· 🧪 Worth Testing

Optimizing Sparse Attention Kernels for Long-Context LLMs

NVIDIA has released a technical primer on co-designing sparse attention for long-context models. By focusing on GPU-friendly indexer kernels—which identify relevant tokens before full attention—developers can significantly improve inference efficiency for context lengths surpassing 100K tokens.

NVIDIA Developer
Models· Important· 🧪 Worth Testing

Unified Multilingual Speech Tagging with Multimodal LLMs

Researchers introduced OmniTag-Bench, a new five-language framework for evaluating multimodal LLMs on simultaneous speech transcription and metadata tagging. Instead of using separate specialist models, the study demonstrates that a single, fine-tuned multimodal LLM can extract transcripts, emotion, gender, language, and named entities in a single inference pass.

arXiv cs.CL
Agents· Important· 🧪 Worth Testing

Trident Framework Enhances LLM Agent Performance Through Test-Time Evolution

Researchers have introduced Trident, a framework designed to improve LLM-based agents by solving three information bottlenecks: ineffective memory retrieval, redundant behavioral candidates, and risky whole-harness rewriting. By implementing boundary-aware memory reading, diversity-aware routing, and order-aware patching, Trident consistently outperforms existing reflection and memory-based methods.

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

New Adversarial Research Reveals Universal Vulnerabilities in LLM Utility

Researchers have introduced EndoUT, an adversarial framework that identifies universal prompt triggers capable of significantly degrading LLM utility. By analyzing how a model's internal response-onset preferences are disrupted, attackers can create fixed strings that force performance drops across various benign tasks without needing target labels or feedback.

arXiv cs.CL
Agents· Important· 🧪 Worth Testing

Scaling agentic platforms using MCP and Amazon Bedrock AgentCore

MoEngage has integrated AI agents into its customer engagement platform by using the Model Context Protocol (MCP) and Amazon Bedrock AgentCore to expose existing APIs as agent-callable tools. By treating its platform as an architecture of isolated sessions and standardized tool schemas, the company enabled teams to automate workflows and decision-making within a single conversation.

AWS Machine Learning
Models· Important· 🧪 Worth Testing

Hugging Face migrates Inference Providers to OpenRouter

Hugging Face has partnered with OpenRouter to power its language model inference. All language model requests now use OpenRouter to automatically select the optimal provider based on real-time price, speed, and reliability metrics.

Hugging Face
Research· Important· 🧪 Worth Testing

Improved Training Method for Masked Diffusion Language Models

Researchers have introduced a 'full-block estimator' to optimize the alignment of Masked Diffusion Language Models (MDLMs). By evaluating every block exactly once during training, this approach removes the variance associated with random block sampling.

arXiv cs.CL
Research· Important· 🧪 Worth Testing

LLM Behavior Control via Input Optimization

Researchers introduced ActGCG, a method to replicate the effects of activation steering—typically requiring internal model access—by optimizing input suffixes. The technique successfully reproduces specific behaviors like language steering through external text inputs alone.

arXiv cs.CL
Models· Important· 🧪 Worth Testing

Optimizing coding agent costs on Amazon Bedrock with NVIDIA NeMo Switchyard

Amazon has released a reference architecture that integrates the NVIDIA NeMo Switchyard library with LiteLLM to dynamically route coding agent requests between different models on Bedrock. By using stage or random routing, you can shift traffic between high-capability and high-efficiency models to balance performance and cost.

AWS Machine Learning
Cyber Security· Important· 🧪 Worth Testing

Threat actors using ARTEX AI agent framework for large-scale cybercrime

Amazon Threat Intelligence observed autonomous agents using the open-source ARTEX framework to conduct large-scale credential theft and deepfake-based identity fraud. These campaigns exploited unpatched AI infrastructure and public misconfigurations to automate multi-stage offensive operations.

AWS Security
Models· Important· 🧪 Worth Testing

Scaling Large MoE Models Across Multiple NVIDIA DGX Stations

NVIDIA has released a technical workflow for serving the 753B parameter GLM-5.3 MoE model across two GB300-equipped DGX Stations. By utilizing tensor parallelism (TP=2) over RDMA connections and vLLM, you can overcome single-GPU memory constraints (252 GB HBM3e) for massive frontier-scale models.

NVIDIA Developer
Models· Important· 🧪 Worth Testing

llama.cpp reaches v1.0.0 with formalized API stability

The llama.cpp project has officially reached its 1.0.0 milestone, three and a half years after its inception. The release introduces strict semantic versioning to ensure better predictability for developers relying on its C/C++ libraries, libllama and libggml.

Hugging Face
Research· Important· 🧪 Worth Testing

New Data-Efficient Technique Enables Full-Duplex Voice Agents Using Frozen LLMs

Researchers have developed a method to adapt general-purpose, frozen LLMs into full-duplex voice systems using only 97 million trainable parameters and 30 GPU-hours of training. The system functions as a thinker-talker cascade with an 80 ms frame clock, allowing for realistic turn-taking, interruptions, and backchanneling without massive speech-data pretraining.

arXiv cs.CL
Models· Important· 🧪 Worth Testing

IBM releases LLMON-enabled Granite models to combat prompt injection

IBM has introduced LLMON (LLM Object Notation), an XML-like markup language that uses reserved special tokens to explicitly label components like instructions, data, and constraints. Two experimental models, Granite 4.1 3B and 8B LLMON-preview, are now available, demonstrating near-zero success rates for indirect prompt injection attacks.

Hugging Face
Research· Important· 🧪 Worth Testing

Mathematical bounds for LLM alignment discovered

Researchers have established the theoretical maximum reward gain possible during language model alignment under fixed KL-divergence constraints. The findings demonstrate that 'best-of-N' sampling effectively reaches these theoretical bounds, whereas common reinforcement learning approaches like PPO and GRPO currently fall short of optimal performance.

Apple Machine Learning
Agents· Important· 🧪 Worth Testing

Implementing Secure Fine-Grained Access Control in Amazon Bedrock Managed Knowledge Bases

Amazon introduced a pattern for securing multi-tenant AI agents by ensuring that RAG search queries are scoped to specific users. The solution uses ACL-aware knowledge bases combined with a request interceptor in the AgentCore Gateway to deterministically inject verified user identities into tool calls, preventing LLMs or prompt injections from accessing unauthorized data.

AWS Machine Learning
Research· 🧪 Worth Testing

Optimizing Knowledge Editing in LLMs Through Sparse Target Regularization

Researchers have identified that the upstream construction of target hidden states significantly impacts the quality of LLM knowledge updates. By implementing an L1 regularization method to prune extraneous components of knowledge vectors, this approach reduces interference during parameter editing, allowing for more precise knowledge injection.

arXiv cs.CL
Agents· Important· 🧪 Worth Testing

AWS introduces framework-agnostic evaluation for AI agents

Amazon has released the Universal Agent Evaluation Framework (UAEF), an open-source tool designed to standardize the evaluation of AI agents. It uses adapters to normalize execution traces from various frameworks like LangChain and LangGraph into a single format, enabling consistent measurement across 36 metrics and 7 quality dimensions.

AWS Machine Learning
Agents· Important· 🧪 Worth Testing

Amazon Bedrock AgentCore adds native support for DeepEval and AutoEval

Amazon Bedrock AgentCore now includes a comprehensive catalog of built-in, third-party, and custom evaluators to monitor agent behavior in production. The platform allows you to run metrics from DeepEval and AutoEval in a managed environment, supporting on-demand, online, and batch evaluation workflows.

AWS Machine Learning
Models· Important· 🧪 Worth Testing

Tether AI Research releases BotPsy: A high-performance 0.8B agentic model

Tether AI Research has introduced BotPsy, a 0.8B-parameter language model optimized for agentic workflows and function calling. Built on Qwen3.5-0.8B, the model is designed for on-device deployment, offering superior tool-use reliability and instruction following while maintaining data privacy.

Hugging Face
Models· Important· 🧪 Worth Testing

Moonshot AI Launches Kimi K3.1 Pro Highspeed on Amazon Bedrock

Moonshot AI has introduced Kimi K3.1 Pro Highspeed, a new model on Amazon Bedrock optimized for long-horizon agentic tasks and coding. The model delivers 2–3 times faster output than the standard version and includes configurable reasoning, tool calling, and support for explicit prompt caching to optimize costs.

AWS Machine Learning
Cyber Security· Important· 🧪 Worth Testing

New Lazarus backdoor technique targets dormant AI model neurons

Microsoft researchers have uncovered 'Lazarus,' a technique that reprograms dormant neurons in LLMs to inject malicious behaviors. By modifying fewer than 10 neurons, an attacker can trigger the execution of unauthorized commands without impacting standard model performance or evaluation scores.

Microsoft Research