Berkeley Function Calling Leaderboard v-3
Emerging9papers using it
2024first seen
The 'Berkeley Function Calling Leaderboard v-3' is a benchmark dataset that contains 200 tasks used to evaluate the performance of function-calling language agents, particularly in relation to the effects of chain-of-thought reasoning on their accuracy.
Papers using Berkeley Function Calling Leaderboard v-3 (9)
- ToolACE: Winning the Points of LLM Function CallingReasoning through Exploration: A Reinforcement Learning Framework for Robust Function CallingOn the Robustness of Agentic Function CallingBrief Is Better: Non-Monotonic Chain-of-Thought Budget Effects in Function-Calling Language AgentsAwakening the Sleeping Agent: Lean-Specific Agentic Data Reactivates General Tool Use in Goedel ProverDon't Just Fine-tune the Agent, Tune the EnvironmentTinyllm: Evaluation And Optimization Of Small Language Models For Agentic Tasks On Edge DevicesxLAM: A Family of Large Action Models to Empower AI Agent SystemsAsynchronous LLM Function Calling