Reasoning

ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding ICML 2025 Regress, Don’t Guess: A Regression-like Loss on Number Tokens for Language Models ICML 2025 RE-IMAGINE: Symbolic Benchmark Synthesis for Reasoning Evaluation ICML 2025 Relational Neurosymbolic Markov Models AAAI 2025 Removal of Hallucination on Hallucination: Debate-Augmented RAG ACL 2025 RePanda: Pandas-powered Tabular Verification and Reasoning ACL 2025 Reproducing the Argument Quality Prediction of Project Debater ACL 2025 Requirement Patterns for Engineering Multiagent Interaction Protocols IJCAI 2025 ReSeeding Latent States for Sequential Language Understanding EMNLP 2025 Responsibility Anticipation and Attribution in LTLf IJCAI 2025 Re-TASK: Revisiting LLM Tasks from Capability, Skill, and Knowledge Perspectives ACL 2025 Rethinking Addressing in Language Models via Contextualized Equivariant Positional Encoding ICML 2025 Rethinking Chain-of-Thought from the Perspective of Self-Training ICML 2025 Rethinking External Slow-Thinking: From Snowball Errors to Probability of Correct Reasoning ICML 2025 Rethinking the Role of Prompting Strategies in LLM Test-Time Scaling: A Perspective of Probability Theory ACL 2025 RethinkMCTS: Refining Erroneous Thoughts in Monte Carlo Tree Search for Code Generation EMNLP 2025 Retrieval-Augmented Process Reward Model for Generalizable Mathematical Reasoning ACL 2025 Revealing and Mitigating the Challenge of Detecting Character Knowledge Errors in LLM Role-Playing EMNLP 2025 Revealing the Barriers of Language Agents in Planning NAACL 2025 Reversal of Thought: Enhancing Large Language Models with Preference-Guided Reverse Reasoning Warm-up ACL 2025 ReVISE: Learning to Refine at Test-Time via Intrinsic Self-Verification ICML 2025 Revisiting Chain-of-Thought in Code Generation: Do Language Models Need to Learn Reasoning before Coding? ICML 2025 Revisiting Compositional Generalization Capability of Large Language Models Considering Instruction Following Ability ACL 2025 Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregation ACL 2025 Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities? ACL 2025