OlympiadBench

OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems[ACL 2024] 📖 arXiv | GitHub Note: We have made adjustments to the image content in the multimodal portion of the dataset and fixed previous issues where some images in the English physics subset were no

Papers using OlympiadBench (15)

Squeeze the Soaked Sponge: Efficient Off-policy Reinforcement Finetuning for Large Language Model2025 · 10 citesCATPO: Critique-Augmented Tree Policy Optimization2026Maximizing Rollout Informativeness under a Fixed Budget: A Submodular View of Tree Search for Tool-Use Agentic Reinforcement Learning2026PopuLoRA: Co-Evolving LLM Populations for Reasoning Self-Play2026SAGE: Multi-Agent Self-Evolution for LLM Reasoning2026PAPO: Stabilizing Rubric Integration Training via Decoupled Advantage Normalization2026ASI-Evolve: AI Accelerates AI2026PrAg-PO: Prompt Augmented Policy Optimization for Robust and Diverse Mathematical Reasoning2026EMA Policy Gradient: Taming Reinforcement Learning for LLMs with EMA Anchor and Top-k KL2026EBPO: Empirical Bayes Shrinkage for Stabilizing Group-Relative Policy Optimization2026Transformation-Augmented GRPO for Enhancing Exploration in Reasoning of Large Language Models2026WirelessMathLM: Teaching Mathematical Reasoning for LLMs in Wireless Communications with Reinforcement Learning2025SPEC-RL: Accelerating On-Policy Reinforcement Learning with Speculative Rollouts2025Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models2025$\texttt{SPECS}$: Faster Test-Time Scaling through Speculative Drafts2025