ResearchBenchmarksCross-domain demo-to-code on Combination Factor Low-ComplexityFollow80Success Rate (SR)NESYCR2841.55568.5Mar 19, 2026Evaluation ResultsMethodMethodLinksSuccess Rate (SR)Goal Completion (GC)Policy Deviation (PD)NESYCR2026.038088.752.81Statler2026.0367.581.2530.12GPT4V-Robotics2026.03557015.76MoReVQA2026.035572.514.85Critic-V2026.0340605LLM-DM2026.0332.556.2582.05Demo2Code2026.033046.250