List your company

Interactive Scientific Reasoning on ScienceWorld OOD (test)

57.81SuccessSkillFlow
13.932425.323736.71548.1063May 13, 2026

Evaluation results

MethodLinks
SkillFlowMethod Type=Ours, Backbone Model=Qwen3.5-9B2026.0557.8167.87
FlowSteerMethod Type=Agent+RL, Backbone Model=Qwen3.5-9B2026.0547.6658.91
AgentFlowMethod Type=Agent+RL, Backbone Model=Qwen3.5-9B2026.0544.5356.85
v4-flashMethod Type=Baseline, Backbone Model=v4-flash2026.0543.4358.64
SkillRLMethod Type=Agent+RL, Backbone Model=Qwen3.5-9B2026.0539.0650.11
AFlowMethod Type=Search-based workflow, Backbone Model=Qwen3.5-9B2026.0529.6943.65
Qwen3.5Method Type=Baseline, Backbone Model=Qwen3.5-9B2026.0525.7841.86
Qwen3.5Method Type=GRPO, Backbone Model=Qwen3.5-9B2026.0524.2240
Qwen3.5Method Type=SFT, Backbone Model=Qwen3.5-9B2026.0515.6234.69