Reasoning

Reward-Guided Speculative Decoding for Efficient LLM Reasoning ICML 2025 RLMEval: Evaluating Research-Level Neural Theorem Proving EMNLP 2025 RMath: A Logic Reasoning-Focused Datasets Toward Mathematical Multistep Reasoning Tasks AAAI 2025 Robustness in Single-Audience Value-based Abstract Argumentation: Complexity Results IJCAI 2025 Robust Tracking via Mamba-based Context-aware Token Learning AAAI 2025 rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking ICML 2025 RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World Scenarios ACL 2025 RULEBREAKERS: Challenging LLMs at the Crossroads between Formal Logic and Human-like Reasoning ICML 2025 s1: Simple test-time scaling EMNLP 2025 S^3cMath: Spontaneous Step-Level Self-Correction Makes Large Language Models Better Mathematical Reasoners AAAI 2025 SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities ACL 2025 Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal Verification ACL 2025 Safety in Large Reasoning Models: A Survey EMNLP 2025 Safety Reasoning with Guidelines ICML 2025 SAKURA: On the Multi-hop Reasoning of Large Audio-Language Models Based on Speech and Audio Information Interspeech 2025 Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification ICML 2025 SAMULE: Self-Learning Agents Enhanced by Multi-level Reflection EMNLP 2025 SANCTUARY: An Efficient Evidence-based Automated Fact Checking System ACL 2025 Sarang at FinCausal 2025: Contextual QA for Financial Causality Detection Combining Extractive and Generative Models COLING 2025 SATBench: Benchmarking LLMs’ Logical Reasoning via Automated Puzzle Generation from SAT Formulas EMNLP 2025 Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search ICML 2025 Scaling LLMs’ Social Reasoning: Sprinkle Cognitive “Aha Moment” into Fundamental Long-thought Logical Capabilities ACL 2025 SCITAT: A Question Answering Benchmark for Scientific Tables and Text Covering Diverse Reasoning Types ACL 2025 SCRIBE: Structured Chain Reasoning for Interactive Behaviour Explanations using Tool Calling EMNLP 2025 Search-in-Context: Efficient Multi-Hop QA over Long Contexts via Monte Carlo Tree Search with Dynamic KV Retrieval ACL 2025