ResearchBenchmarksUser Simulation Quality Assessment on Session-level Human Evaluation Set adversarial (test)Follow86Win RateUserLM-R142.3253.666576.34Jan 14, 2026Evaluation ResultsMethodMethodLinksWin RateTie RateLoss RateUserLM-R1Opponent=Gemini-2.5-FlashOpponent=Gemini-2.5-Flash2026.01862212UserLM-R1Opponent=UserLM-R1 (w/...Opponent=UserLM-R1 (w/o RL)2026.01553233UserLM-R1Opponent=DeepSeek-R1Opponent=DeepSeek-R12026.01442848