mathematical reasoning

KVTuner: Sensitivity-Aware Layer-Wise Mixed-Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference ICML 2025 Language Models as Implicit Tree Search ICML 2025 Layer Swapping for Zero-Shot Cross-Lingual Transfer in Large Language Models ICLR 2025 Learning Like Humans: Advancing LLM Reasoning Capabilities via Adaptive Difficulty Curriculum Learning and Expert-Guided Self-Reformulation EMNLP 2025 Learning Theorem Rationale for Improving the Mathematical Reasoning Capability of Large Language Models AAAI 2025 Legal Mathematical Reasoning with LLMs: Procedural Alignment through Two-Stage Reinforcement Learning EMNLP 2025 LEMMA: Learning from Errors for MatheMatical Advancement in LLMs ACL 2025 Let’s Reason Formally: Natural-Formal Hybrid Reasoning Enhances LLM’s Math Capability EMNLP 2025 Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond ACL 2025 Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoning ACL 2025 LiteSearch: Efficient Tree Search with Dynamic Exploration Budget for Math Reasoning AAAI 2025 LLaMA-Berry: Pairwise Optimization for Olympiad-level Mathematical Reasoning via O1-like Monte Carlo Tree Search NAACL 2025 LLM2: Let Large Language Models Harness System 2 Reasoning NAACL 2025 LLM Reasoning Engine: Specialized Training for Enhanced Mathematical Reasoning NAACL 2025 LLMs Are Not Intelligent Thinkers: Introducing Mathematical Topic Tree Benchmark for Comprehensive Evaluation of LLMs NAACL 2025 LLMs cannot spot math errors, even when allowed to peek into the solution EMNLP 2025 LLM The Genius Paradox: A Linguistic and Math Expert’s Struggle with Simple Word-based Counting Problems NAACL 2025 Local Prompt Optimization NAACL 2025 LogicPro: Improving Complex Logical Reasoning via Program-Guided Learning ACL 2025 Long Chain-of-Thought Fine-tuning via Understanding-to-Reasoning Transition EMNLP 2025 LSRL: Process-Supervised GRPO on Latent Recurrent States Improves Mathematical Reasoning EMNLP 2025 MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale ACL 2025 MARGE: Improving Math Reasoning with Guided Exploration ICML 2025 MASS: Mathematical Data Selection via Skill Graphs for Pretraining Large Language Models ICML 2025 MathAgent: Leveraging a Mixture-of-Math-Agent Framework for Real-World Multimodal Mathematical Error Detection ACL 2025