BFCL v-4
Emerging3papers using it
2025first seen
The 'BFCL-V4' dataset/benchmark contains a collection of multi-turn user interactions designed to evaluate the performance of AI agents in reasoning and invoking external tools through reinforcement learning.
Papers using BFCL v-4 (3)
- CM2: Reinforcement Learning with Checklist Rewards for Multi-Turn and Multi-Step Agentic Tool UseTraining LLMs for Multi-Step Tool Orchestration with Constrained Data Synthesis and Graduated RewardsSmall Language Models For Agentic Systems: A Survey Of Architectures, Capabilities, And Deployment Trade Offs