MATH-500

https://github.com/openai/prm800k/blob/main/prm800k/math_splits/test.jsonl

Papers using MATH-500 (50)

Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space2025 · 26 citesStep-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback2025 · 1 citesMerlin's Whisper: Enabling Efficient Reasoning in Large Language Models via Black-box Persuasive Prompting2026VTC-R1: Vision-Text Compression for Efficient Long-Context Reasoning2026Locally Confident, Globally Stuck: The Quality-Exploration Dilemma in Diffusion Language Models2026KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks2026DeCoVec: Building Decoding Space based Task Vector for Large Language Models via In-Context Learning2026Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression2026Aligning Tree-Search Policies with Fixed Token Budgets in Test-Time Scaling of LLMs2026Long Chain-of-Thought Compression via Fine-Grained Group Policy Optimization2026Reevaluating Self-Consistency Scaling in Multi-Agent Systems2025Prompting Test-Time Scaling Is A Strong LLM Reasoning Data Augmentation2025From Implicit Exploration to Structured Reasoning: Leveraging Guideline and Refinement for LLMs2025MemLens: Uncovering Memorization in LLMs with Activation Trajectories2025MoL-RL: Distilling Multi-Step Environmental Feedback into LLMs for Feedback-Independent Reasoning2025Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty2025Steering LLM Thinking with Budget Guidance2025Kimi k1.5: Scaling Reinforcement Learning with LLMs2025Pairwise RM: Perform Best-of-N Sampling with Knockout Tournament2025Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling2025Thinking Preference Optimization2025SIFT: Grounding LLM Reasoning in Contexts via Stickers2025Think Twice: Enhancing LLM Reasoning by Scaling Multi-round Test-time Thinking2025Sample, Don't Search: Rethinking Test-Time Alignment for Language Models2025T1: Tool-integrated Self-verification for Test-time Compute Scaling in Small Language Models2025Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought2025DianJin-R1: Evaluating and Enhancing Financial Reasoning in Large Language Models2025Process Reward Models That Think2025Reinforcement Learning for Reasoning in Large Language Models with One Training Example2025Phi-4-Mini-Reasoning: Exploring the Limits of Small Reasoning Language Models in Math2025Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space2025Thinkless: LLM Learns When to Think2025Not All Correct Answers Are Equal: Why Your Distillation Source Matters2025PreMoe: Lightening MoEs on Constrained Memory by Expert Pruning and Retrieval2025Harnessing Negative Signals: Reinforcement Distillation from Teacher Data for LLM Reasoning2025Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models2025Fractional Reasoning via Latent Steering Vectors Improves Inference Time Compute2025ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs2025Agentar-Fin-R1: Enhancing Financial Intelligence through Domain Expertise, Training Efficiency, and Advanced Reasoning2025Inpainting-Guided Policy Optimization for Diffusion Large Language Models2025ScaleDiff: Scaling Difficult Problems for Advanced Mathematical Reasoning2025Socratic-Zero : Bootstrapping Reasoning via Data-Free Agent Co-evolution2025QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs2025Reasoning with Sampling: Your Base Model is Smarter Than You Think2025When to Ensemble: Identifying Token-Level Points for Stable and Fast LLM Ensembling2025Can LLMs Guide Their Own Exploration? Gradient-Guided Reinforcement Learning for LLM Reasoning2025Faster and Better LLMs via Latency-Aware Test-Time Scaling2025Walk Before You Run! Concise LLM Reasoning via Reinforcement Learning2025Adaptive Rectification Sampling for Test-Time Compute Scaling2025Controlling Large Language Model with Latent Actions2025