BFCL v-4 Multi-Turn
Emerging2papers using it
2026first seen
The 'BFCL v4 Multi-Turn' dataset/benchmark contains multi-turn execution scenarios used to evaluate the error recovery capabilities of language models in tool use.
The 'BFCL v4 Multi-Turn' dataset/benchmark contains multi-turn execution scenarios used to evaluate the error recovery capabilities of language models in tool use.