BFCL Multi-Turn

The 'BFCL multi-turn' dataset/benchmark contains a suite of tasks designed to evaluate emergent delegation in long-horizon agentic workflows.

Papers using BFCL Multi-Turn (3)

DecisionBench: A Benchmark for Emergent Delegation in Long-Horizon Agentic Workflows2026Unlocking Implicit Experience: Synthesizing Tool-Use Trajectories from Text2026Robust Tool Use via Fission-GRPO: Learning to Recover from Execution Errors2026