InfoQ Homepage Large language models Content on InfoQ
-
Google Researchers Propose Bayesian Teaching Method for Large Language Models
Google Research has proposed a training method that teaches large language models to approximate Bayesian reasoning by learning from the predictions of an optimal Bayesian system. The approach focuses on improving how models update beliefs as they receive new information during multi-step interactions.
-
DoorDash Builds LLM Conversation Simulator to Test Customer Support Chatbots at Scale
DoorDash engineers built a simulation and evaluation flywheel to test large language model customer support chatbots at scale. The system generates multi-turn synthetic conversations using historical transcripts and backend mocks, evaluates outcomes with an LLM-as-judge framework, and enables rapid iteration on prompts, context, and system design before production deployment.
-
AWS Launches Strands Labs for Experimental AI Agent Projects
Amazon Web Services has introduced Strands Labs, a new GitHub organization created to host experimental projects related to agent-based AI development.
-
Scaling Human Judgment: How Dropbox Uses LLMs to Improve Labeling for RAG Systems
To improve the relevance of responses produced by Dropbox Dash, Dropbox engineers began using LLMs to augment human labelling, which plays a crucial role in identifying the documents that should be used to generate the responses. Their approach offers useful insights for any system built on retrieval-augmented generation (RAG).
-
Google Publishes Scaling Principles for Agentic Architectures
Researchers from Google and MIT published a paper describing a predictive framework for scaling multi-agent systems. The framework shows that there is a tool-coordination trade-off and it can be used to select an optimal agentic architecture for a given task.
-
OpenAI Codex-Spark Achieves Ultra-Fast Coding Speeds on Cerebras Hardware
In a major shift in its hardware strategy, OpenAI launched GPT-5.3-Codex-Spark, its first production AI model deployed on Cerebras wafer-scale chips rather than traditional Nvidia GPUs. The new model offers delivers improved throughput and low-latency, enabling a real-time, interactive coding experience, says the company.
-
Apple Researchers Introduce Ferret-UI Lite, an On-Device AI Model for Seeing and Controlling UIs
Apple's Ferret-UI Lite is a 3B-parameter model optimized for mobile and desktop screens, designed to interpret screen images, understand UI elements such as icons and text, and interact with apps by, e.g., reading messages, checking health data, and more.
-
Rivet Launches the Sandbox Agent SDK to Solve Agent API Fragmentation
Rivet Sandbox Agent SDK provides a universal API for coding agents, allowing developers to work with different agent runtimes like Claude Code, Codex, OpenCode, and Amp without rewriting their integration for each one. It addresses the fragmentation across agent APIs, session handling, and streaming formats that has historically made agent integrations complex and difficult to maintain.
-
OpenAI Launches Frontier, a Platform to Build, Deploy, and Manage AI Agents across the Enterprise
OpenAI Frontier is an enterprise platform for building, deploying, and managing AI agents, designed to make AI agents reliable, scalable, and integrated into real company systems and workflows.
-
Hugging Face Introduces Community Evals for Transparent Model Benchmarking
Hugging Face has launched Community Evals, a feature that enables benchmark datasets on the Hub to host their own leaderboards and automatically collect evaluation results from model repositories.
-
GitHub Agentic Workflows Unleash AI-Driven Repository Automation
Recently launched in technical preview, GitHub Agentic Workflows introduce a way to automate complex, repetitive repository tasks using coding agents that understand context and intent, GitHub says. This enables workflows such as automatic issue triage and labeling, documentation updates, CI troubleshooting, test improvements, and reporting.
-
How Dropbox Built a Scalable Context Engine for Enterprise Knowledge Search
Dropbox engineers have detailed how the company built the context engine behind Dropbox Dash, revealing a shift toward index-based retrieval, knowledge graph-derived context, and continuous evaluation to support enterprise AI at scale.
-
Google Explores Scaling Principles for Multi-Agent Coordination
Google Research tried to answer the question of how to design agent systems for optimal performance by running a controlled evaluation of 180 agent configurations. From this, the team derived what they call the "first quantitative scaling principles for AI agent systems", showing that multi-agent coordination does not reliably improve results and can even reduce performance.
-
GitHub Copilot SDK Lets Developers Integrate Copilot CLI's Engine into Apps
Now available in technical preview on GitHub, the GitHub Copilot SDK lets developers embed the same engine that powers GitHub Copilot CLI into their own apps, making it easier to build agentic workflows.
-
Windsurf Introduces Arena Mode to Compare AI Models During Development
Windsurf has introduced Arena Mode inside its IDE allowing developers to compare large language models side by side while working on real coding tasks. The feature is designed to let users evaluate models directly within their existing development context, rather than relying on public benchmarks or external evaluation websites.