Study examines tool discovery architectures for LLM agents

Research investigates whether LLM agents should plan or retrieve first when discovering APIs from large registries, addressing context window limitations in tool-augmented systems.

Read the full story at Apple Machine Learning Research ↗

Timeline · 1 report

2026-10-15 00:00 · Apple Machine Learning Research
Plan or Retrieve First? A Scale Study of Tool Discovery Architectures

More stories

Meta releases 816B Muse Spark Open; NVIDIA launches Nemotron 3.5 models — AWS Machine Learning Blog
Meta and Apple Partner to Bring Open-Weight Muse AI Model to Macs — Wall Street Journal Technology
Apple details local and distributed LLM inference using MLX and RDMA on Mac Studio — Apple Machine Learning Research
Apple Research Proposes Selection-Based Structured Reasoning for Multimodal Agents — Apple Machine Learning Research
Apple releases HomeView smart display with Siri AI — Mashable AI
Apple Research Proposes Method for Detecting Code-Switching in Speech Models — Apple Machine Learning Research
Apple Research Explores Tri-Modal Masked Diffusion Models — Apple Machine Learning Research
Apple unveils new smart home devices that showcase upgraded Siri AI — The Guardian AI

Get the daily brief of stories like this at 6:30 every morning →