MiniF-2F-Test

The 'MiniF-2F-Test' is a benchmark dataset that contains a collection of formal physics theorems used to evaluate the performance of automatic theorem proving systems in the physics domain.

Papers using MiniF-2F-Test (7)

GDEPO: Group Dual-dynamic and Equal-right Advantage Policy Optimization with Enhanced Training Data Utilization for Sample-Constrained Reinforcement Learning2026PhysProver: Advancing Automatic Theorem Proving for Physics2026GAR: Generative Adversarial Reinforcement Learning for Formal Theorem Proving2025StepFun-Prover Preview: Let's Think and Verify Step by Step2025Rewarding the Unlikely: Lifting GRPO Beyond Distribution Sharpening2025DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition2025STP: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving2025