BFCLv-3

BFCLv-3 is a benchmark dataset used to evaluate the effectiveness of large language model agents in generating and refining tool calls through simulated feedback.

Papers using BFCLv-3 (13)

D-CORE: Incentivizing Task Decomposition in Large Reasoning Models for Complex Tool Use2026Pushing the Limits of LLM Tool Calling via Experiential Knowledge Integration and Activation2026MAVEN: Improving Generalization in Agentic Tool Calling2026TopoCurate:Modeling Interaction Topology for Tool-Use Agent Training2026ToolWeave: Structured Synthesis of Complex Multi-Turn Tool-Calling Dialogues2026HINT-SD: Targeted Hindsight Self-Distillation for Long-Horizon Agents2026EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL2026Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning2026MagicAgent: Towards Generalized Agent Planning2026Gecko: A Simulation Environment with Stateful Feedback for Refining Agent Tool Calls2026On Generalization in Agentic Tool Calling: CoreThink Agentic Reasoner and MAVEN Dataset2025Small Language Models For Agentic Systems: A Survey Of Architectures, Capabilities, And Deployment Trade Offs2025ToolSample: Dual Dynamic Sampling Methods with Curriculum Learning for RL-based Tool Learning2025