List your company

Scientific Reasoning on Aggregate Scientific Reasoning Suite

61.4Mean@1Agentic Proposing
55.88857.31958.7560.181Feb 3, 2026

Evaluation results

MethodLinks
Agentic ProposingTraining Data=Agentic-Proposer-4B Generated Problems, Training Budget=10,000 trajectories, Optimizer=GRPO2026.0261.4
Qwen3-4B-Instruct-2507Protocol=zero-shot2026.0256.1