Reactive Machines

KV Cache Management: PagedAttention & RadixAttention

KV Cache Management: PagedAttention & RadixAttention

Modern LLMs rely on quantization, pruning, distillation, and faster attention kernels, but production performance often depends most on KV cache…
Introducing cross-Region inference for OpenAI GPT-5.6 models on Amazon Bedrock

Introducing cross-Region inference for OpenAI GPT-5.6 models on Amazon Bedrock

This post is co-written with Chris Dickens from OpenAI. Amazon Bedrock now offers OpenAI GPT-5.6 models on Amazon Bedrock in…
Authoring Dogwood policies from natural language in Amazon Bedrock AgentCore

Authoring Dogwood policies from natural language in Amazon Bedrock AgentCore

AI agents can automate complex workflows but might take actions that don’t align with your organization’s policies or regulatory constraints…
Scaling Laws for Mixture Pretraining Under Data Constraints

Scaling Laws for Mixture Pretraining Under Data Constraints

As language models scale, the amount of data they require grows – yet many target data sources, such as low-resource…
Progressive Refinement: An Iterative Pseudo-Labeling Approach for Mandarin-English Code-Switching ASR

Progressive Refinement: An Iterative Pseudo-Labeling Approach for Mandarin-English Code-Switching ASR

Self-training has been shown to be helpful in addressing data scarcity for many domains, including vision, speech, and language. Specifically,…
Domain and publish date filters for Web Search on AgentCore

Domain and publish date filters for Web Search on AgentCore

When an AI agent uses Web Search to ground its answers on behalf of a customer, the organization behind that…
How Fanatics Betting and Gaming built a multi-agent customer support system

How Fanatics Betting and Gaming built a multi-agent customer support system

Fanatics Betting and Gaming (FBG) built a multi-agent customer support system on AWS to solve a challenge unique to sports…
Examining Human-Like Behaviors in LLMs: A Multi-Dimensional Analysis of Model Behaviors, User Factors, and System Prompts

Examining Human-Like Behaviors in LLMs: A Multi-Dimensional Analysis of Model Behaviors, User Factors, and System Prompts

Large language models (LLMs) exhibit a wide range of human-like behaviors, from expressing thoughts and emotions, to engaging in relationship-building…
The P-Completeness of Inverted Index Traversal: On the Complexity of Evaluating Boolean Query DAGs

The P-Completeness of Inverted Index Traversal: On the Complexity of Evaluating Boolean Query DAGs

Modern AI agents increasingly rely on search infrastructure to execute complex, neuro-symbolic reasoning workflows. These workflows often compile into deeply…
Back to top button