OpenAI shuts down Sora while Meta gets shut out in court
When an 82-year-old Kentucky woman was offered $26 million from an AI company that wanted to build a data center on her land, she said no. Sure, that same company can try to rezone 2,000 acres nearby anyway, but as AI infrastructure stretches further into the real world, the real world is starting t...
LlamaAgents Builder: From Prompt to Deployed AI Agent in Minutes
Creating an AI agent for tasks like analyzing and processing documents autonomously used to require hours of near-endless configuration, code orchestration, and deployment battles.
Meta Releases TRIBE v2: A Brain Encoding Model That Predicts fMRI Responses Across Video, Audio, and Text Stimuli
Neuroscience has long been a field of divide and conquer. Researchers typically map specific cognitive functions to isolated brain regions—like motion to area V5 or faces to the fusiform gyrus—using models tailored to narrow experimental paradigms. While this has provided deep insights, the resultin...
ARC-AGI-3: A New Challenge for Frontier Agentic Intelligence
arXiv:2603.24621v1 Announce Type: new
Abstract: We introduce ARC-AGI-3, an interactive benchmark for studying agentic intelligence through novel, abstract, turn-based environments in which agents must explore, infer goals, build internal models of environment dynamics, and plan effective action seq...
When Is Collective Intelligence a Lottery? Multi-Agent Scaling Laws for Memetic Drift in LLMs
arXiv:2603.24676v1 Announce Type: new
Abstract: Multi-agent systems powered by large language models (LLMs) are increasingly deployed in settings that shape consequential decisions, both directly and indirectly. Yet it remains unclear whether their outcomes reflect collective reasoning, systematic ...
AutoSAM: an Agentic Framework for Automating Input File Generation for the SAM Code with Multi-Modal Retrieval-Augmented Generation
arXiv:2603.24736v1 Announce Type: new
Abstract: In the design and safety analysis of advanced reactor systems, constructing input files for system-level thermal-hydraulics codes such as the System Analysis Module (SAM) remains a labor-intensive task. Analysts must extract and reconcile design data ...
Trust as Monitoring: Evolutionary Dynamics of User Trust and AI Developer Behaviour
arXiv:2603.24742v1 Announce Type: new
Abstract: AI safety is an increasingly urgent concern as the capabilities and adoption of AI systems grow. Existing evolutionary models of AI governance have primarily examined incentives for safe development and effective regulation, typically representing use...
Formal Semantics for Agentic Tool Protocols: A Process Calculus Approach
arXiv:2603.24747v1 Announce Type: new
Abstract: The emergence of large language model agents capable of invoking external tools has created urgent need for formal verification of agent protocols. Two paradigms dominate this space: Schema-Guided Dialogue (SGD), a research framework for zero-shot API...
Google Releases Gemini 3.1 Flash Live: A Real-Time Multimodal Voice Model for Low-Latency Audio, Video, and Tool Use for AI Agents
Google has released Gemini 3.1 Flash Live in preview for developers through the Gemini Live API in Google AI Studio. This model targets low-latency, more natural, and more reliable real-time voice interactions, serving as Google’s ‘highest-quality audio and speech model to date.’ By natively process...
Athena: Intermediate Representations for Iterative Scaffolded App Generation with an LLM
It is challenging to generate the code for a complete user interface using a Large Language Model (LLM). User interfaces are complex and their implementations often consist of multiple, inter-related files that together specify the contents of each screen, the navigation flows between the screens, a...
To Infinity and Beyond: Tool-Use Unlocks Length Generalization in State Space Models
State Space Models (SSMs) have become the leading alternative to Transformers for sequence modeling. Their primary advantage is efficiency in long-context and long-form generation, enabled by fixed-size memory and linear scaling of computational complexity. We begin this work by showing a simple the...
A Coding Implementation to Run Qwen3.5 Reasoning Models Distilled with Claude-Style Thinking Using GGUF and 4-Bit Quantization
In this tutorial, we work directly with Qwen3.5 models distilled with Claude-style reasoning and set up a Colab pipeline that lets us switch between a 27B GGUF variant and a lightweight 2B 4-bit version with a single flag. We start by validating GPU availability, then conditionally install either ll...
How Kensho built a multi-agent framework with LangGraph to solve trusted financial data retrieval
Discover how Kensho, S&P Global’s AI innovation engine, leveraged LangGraph to create its Grounding framework–a unified agentic access layer solving fragmented financial data retrieval at enterprise scale.
AsgardBench: A benchmark for visually grounded interactive planning
Imagine a robot tasked with cleaning a kitchen. It needs to observe its environment, decide what to do, and adjust when things don’t go as expected, for example, when the mug it was tasked to wash is already clean, or the sink is full of other items. This is the domain of embodied AI: systems […]
Th...
GroundedPlanBench: Spatially grounded long-horizon task planning for robot manipulation
Vision-language models (VLMs) use images and text to plan robot actions, but they still struggle to decide what actions to take and where to take them. Most systems split these decisions into two steps: a VLM generates a plan in natural language, and a separate model translates it into executable ac...
Getting Started with Smolagents: Build Your First Code Agent in 15 Minutes
Build an AI weather agent in 40 lines of Python using Hugging Face's smolagents library. Learn to create tools, connect LLMs, and run autonomous tasks.
Transform your headphones into a live personal translator on iOS.
Google Translate’s Live translate with headphones is officially arriving on iOS! And we're expanding the capability for both iOS and Android users to even more countries…
When multi-agent AI systems fail, who takes the blame?
All AI systems can fail, but now we can trace exactly who’s responsible. Implicit Execution Tracing (IET) embeds invisible signatures in AI outputs, making multi-agent systems accountable, auditable, and tamper-proof.
💡TLDR: The best agent evals directly measure an agent behavior we care about. Here's how we source data, create metrics, and run well-scoped, targeted experiments over time to make agents more accurate and reliable.Evals shape agent behaviorWe’ve been curating evaluations to measure and