LLM News

Every LLM release, update, and milestone.

Filtered by:personalization✕ clear
research

FlyThinker: Researchers propose parallel reasoning during generation for personalized responses

Researchers introduce FlyThinker, a framework that runs reasoning and generation concurrently rather than sequentially, addressing limitations of existing "think-then-generate" approaches in long-form personalized text generation. The method uses a separate reasoning model that generates token-level guidance in parallel with the main generation model, enabling more adaptive reasoning without sacrificing computational efficiency.

research

First benchmark for personalized deep research agents reveals gaps in current AI systems

Researchers introduced PDR-Bench, the first benchmark specifically designed to evaluate personalization in Deep Research Agents (DRAs). The benchmark pairs 50 research tasks across 10 domains with 25 authentic user profiles, creating 250 realistic queries that expose current limitations in how AI systems adapt to individual user contexts.