2 papers
cs.LG2026
Understanding the Challenges in Iterative Generative Optimization with LLMs
Allen Nie, Xavier Daull, Zhiyi Kuang +10
Generative optimization uses large language models (LLMs) to iteratively improve artifacts (such as code, workflows or prompts) using execution feedback. It is a promising approach…
cs.AI2025
A Flexible Multi-Agent LLM-Human Framework for Fast Human Validated Tool Building
Daull Xavier, Patrice Bellot, Emmanuel Bruno +2
We introduce CollabToolBuilder, a flexible multiagent LLM framework with expert-in-the-loop (HITL) guidance that iteratively learns to create tools for a target goal, aligning with…