TAU-bench

Papers using TAU-bench (5)

Self-Challenging Language Model Agents2025 · 1 citesMulti-Turn Reinforcement Learning for Tool-Calling Agents with Iterative Reward Calibration2026CM2: Reinforcement Learning with Checklist Rewards for Multi-Turn and Multi-Step Agentic Tool Use2026Generalizable End-to-End Tool-Use RL with Synthetic CodeGym2025Robust Tool Use via Fission-GRPO: Learning to Recover from Execution Errors2026