just-in-time

JIT-Agent is an open-source 27B model that dynamically generates task-specific harnesses for AI agents, outperforming hand-built systems with improved token efficiency.

JIT-Agent is a trainable model that synthesizes adaptive agent harnesses for off-the-shelf LLMs, improving performance across diverse models and tasks.

Garry Tan argues that we are entering a golden age for just-in-time software development, implying a shift towards more efficient and responsive software creation.

This paper presents a framework that uses domain-specific expert knowledge to ground large language models for providing Just-in-Time adaptive feedback to students based on their written reasoning, achieving over 80% improvement in student performance in a large university course.