Reasoning

Learning Multi-View Spatial Reasoning from Cross-View Relations CVPR 2026 Learning Shortcut Models for Efficient Recursive Reasoning ACL 2026 Learning to Reason in 4D: Dynamic Spatial Understanding for Vision Language Models CVPR 2026 Learn Like Humans: Use Meta-cognitive Reflection for Efficient Self-Improvement ACL 2026 LegalDrill: Diagnosis-Driven Synthesis for Legal Reasoning in Small Language Models ACL 2026 Leibniz: Theory-of-Mind Driven Neuro-Symbolic Logical Reasoning via Multi-Agent Collaboration ACL 2026 LePREC: Reasoning as Classification over Structured Factors for Assessing Relevance of Legal Issues ACL 2026 Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention ACL 2026 Less Languages, Less Tokens: An Efficient Unified Logic Cross-lingual Chain-of-Thought Reasoning Framework ACL 2026 Let VLMs Grade Their Own Thoughts: A Self-Quantification Approach to Reasoning-Aware Reward Modeling CVPR 2026 LightReasoner: Can Small Language Models Teach Large Language Models Reasoning? ACL 2026 LiTS: A Modular Framework for LLM Tree Search ACL 2026 LLM Parameters for Math Across Languages: Shared or Separate? ACL 2026 LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals ACL 2026 LOGICAL-COMMONSENSEQA: A Benchmark for Logical Commonsense Reasoning ACL 2026 Logical Phase Transitions: Understanding Collapse in LLM Logical Reasoning ACL 2026 Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning ACL 2026 Look Less, Reason More: Rollout-Guided Adaptive Pixel-Space Reasoning ACL 2026 Look Light, Think Heavy: What Multimodal Chain-of-Thought Reasoning Can and Cannot Do ACL 2026 Macaron: Controlled, Human-Written Benchmark for Multilingual and Multicultural Reasoning via Template-Filling ACL 2026 MAGIC: Deep Geometric Evolution with Structural Consensus for Temporal Knowledge Graph Reasoning ACL 2026 Make LLMs See Like Investigators, Not Just Think More: The Role of Structured Analysis in Investigative Reasoning ACL 2026 MalruleLib: Large-Scale Executable Misconception Reasoning with Step Traces for Modeling Student Thinking in Mathematics ACL 2026 MANSION: Multi-floor lANguage-to-3D Scene generatIOn for loNg-horizon tasks CVPR 2026 MARD: Module-Aware Reasoning Distillation for Language Models with Adaptive Supervision ACL 2026