How do we teach AI agents to reliably find and click the exact on screen element we mean when we give them a simple instruction? A team of researchers from ML Foundations has introduced Gelato-30B-A3B, a state of the art grounding model for graphical user interfaces that is designed to plug into computer use agents…
Kosmos, built by Edison Scientific, is an autonomous discovery system that runs long research campaigns on a single goal. Given a dataset and an open ended natural language objective, it performs repeated cycles of data analysis, literature search, and hypothesis generation, then synthesizes the results into a fully cited scientific report. A typical run lasts…
Reliable multi-agent systems are mostly a memory design problem. Once agents call tools, collaborate, and run long workflows, you need explicit mechanisms for what gets stored, how it is retrieved, and how the system behaves when memory is wrong or missing. This article compares 6 memory system patterns commonly used in agent stacks, grouped into…
In this tutorial, we explore how neural memory agents can learn continuously without forgetting past experiences. We design a memory-augmented neural network that integrates a Differentiable Neural Computer (DNC) with experience replay and meta-learning to adapt quickly to new tasks while retaining prior knowledge. By implementing this approach in PyTorch, we demonstrate how content-based memory…
Every time you prompt an LLM, it doesn’t generate a complete answer all at once — it builds the response one word (or token) at a time. At each step, the model predicts the probability of what the next token could be based on everything written so far. But knowing probabilities alone isn’t enough —…
How can speech editing become as direct and controllable as simply rewriting a line of text? StepFun AI has open sourced Step-Audio-EditX, a 3B parameter LLM based audio model that turns expressive speech editing into a token level text like operation, instead of a waveform level signal processing task. https://arxiv.org/pdf/2511.03601 Why developers care about controllable…
In this tutorial, we explore how to build an Agentic Voice AI Assistant capable of understanding, reasoning, and responding through natural speech in real time. We begin by setting up a self-contained voice intelligence pipeline that integrates speech recognition, intent detection, multi-step reasoning, and text-to-speech synthesis. Along the way, we design an agent that listens…
How can we build AI systems that keep learning new information over time without forgetting what they learned before or retraining from scratch? Google Researchers has introduced Nested Learning, a machine learning approach that treats a model as a collection of smaller nested optimization problems, instead of a single network trained by one outer loop….
Agents that use the Model Context Protocol MCP have a scaling problem. Every tool definition and every intermediate result is pushed through the context window, which means large workflows burn tokens and hit latency and cost limits fast. Anthropic’s new ‘code execution with MCP’ pattern restructures this pipeline by turning MCP tools into code level…
Tabular data is still where many important models run in production. Finance, healthcare, energy and industry teams work with tables of rows and columns, not images or long text. Prior Labs now extends this space with TabPFN-2.5, a new tabular foundation model that scales in context learning to 50,000 samples and 2,000 features while keeping…
