Engineering
How Many of Your Agent’s Calls Actually Need a Frontier Model?
LangChain benchmarked NVIDIA’s open-source NeMo Switchyard model-routing library against its Deep Agents evaluation suite of 145 multi-step agentic tasks. Calls…
Engineering
TutorMoments: Do AI Tutors Know When to Help and When to Hold Back?
Researchers at the Allen Institute for AI introduced TutorMoments, a framework that pauses real one-on-one math tutoring transcripts at critical…
Engineering
Deploy local agents everywhere with LFM2.5-2.6B
Liquid AI has released LFM2.5-2.6B, a 2.6-billion-parameter model built for on-device agentic use cases. The model goes through a training…
Engineering
Meet North Micro Vision: A 2.4B Native-Resolution Vision-Language Model
Cohere Labs has released North Micro Vision, a 2.4-billion-parameter vision-language model that pairs a custom 400-million-parameter native-resolution vision encoder with…
Engineering
Building monday.com Sidekick: Why Capable Agents Need More Than Just Tools
Monday.com’s Sidekick assistant evolved from a single general-purpose agent equipped with many tools into a layered system with distinct responsibilities.…
Engineering
Open-Sourcing Metals v2: Databricks’ Java and Scala Language Server for Multi-Million Line Codebases
Databricks has open-sourced Metals v2, a language server for Scala and Java built to handle codebases with millions of lines.…
Engineering
Databricks Network Configuration Delivery to Tens of Millions of Serverless VMs
Databricks redesigned its network configuration delivery system using an event-driven architecture that decouples the critical serving path from upstream dependencies.…
Engineering
Putting Sign Language AI Into Users’ Hands
Google DeepMind has introduced SL2T, a sign-language-to-text model trained on more than 100,000 hours of data spanning over 50 sign…
Engineering
GLInt: Geometry-Matched Hard Negatives for Late-Interaction Retrieval
GLInt is a late-interaction retrieval model that achieves a mean nDCG@10 of 57.43 on the BEIR benchmark by training on…
Engineering
Zilliz Adds Cost-Aware Benchmarking to VDBBench, the Open-Source Vector Database Benchmark
Zilliz has updated VectorDBBench (VDBBench), an open-source vector database benchmark, to add cost as a first-class evaluation dimension alongside performance.…
Engineering
Scientific computing in the age of agentic AI
OpenAI published an exploratory field report covering eight agent-assisted scientific computing projects, primarily in the life sciences, with five using…
Engineering
Announcing Day-0 Support for NVIDIA Nemotron 3.5 Lightning on vLLM
vLLM now provides Day-0 support for NVIDIA’s Nemotron 3.5 Lightning, a customizable 30-billion-parameter hybrid mixture-of-experts model with only 3 billion…