Salesforce/xLAM-2-32b-fc-r

Salesforce/xLAM-2-32b-fc-r is a 32 billion parameter Large Action Model (LAM) developed by Salesforce, designed to translate user intentions into executable actions for AI agents. This model excels in multi-turn conversation and tool usage, trained using the APIGen-MT framework which generates high-quality data from simulated agent-human interactions. It achieves state-of-the-art performance on BFCL and τ-bench benchmarks, making it highly effective for automating workflows and enhancing decision-making in agentic systems.