New Benchmark ToolTurns Tests LLM Agents in Multi-Turn Tool-Use Dialogue
A new arXiv paper introduces ToolTurns, a benchmark evaluating tool-using language model agents in multi-turn conversational settings, addressing the gap left by benchmarks focused on isolated requests.
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-11-13 05:00 · arXiv cs.CL
ToolTurns: Benchmarking LLM Agents in Multi-Turn Dialogue