Tag
This paper proposes a multi-agent framework that enables LLM agents to conduct controlled experiments using simulation models for pharmaceutical process design, yielding more specific and actionable recommendations than language-only reasoning.
This paper proposes a source-guided protocol where an LLM generates candidate modifications for a weak target model using a stronger same-family source model, showing substantial accuracy improvements on CIFAR-10 and SVHN benchmarks while disentangling transfer from adaptation effects.
An open-source lab framework for running controlled experiments on tool-using agents, allowing variation of tool names, personas, and history to measure effects.