Reasoning

EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoning ACL 2026 E-ViC: Reasoning Beyond Text via Embodied Visual Chain for Spatial Intelligence ACL 2026 Evidence-Augmented Policy Optimization with Reward Co-Evolution for Long-Context Reasoning ACL 2026 Evidence-Driven Reasoning for Industrial Maintenance Using Heterogeneous Data ACL 2026 Evolving Agents ACL 2026 Evo-PI: Aligning Medical Reasoning via Evolving Principle-Guided Supervision ACL 2026 Execution as Verification: Fine-Grained Self-Correcting Reasoning for Complex KBQA ACL 2026 ExecVerify: White-Box RL with Verifiable Stepwise Rewards for Code Execution Reasoning ACL 2026 Experiments or Outcomes? Probing Scientific Feasibility in Large Language Models ACL 2026 Exploring Layer Activation Dynamic of CoT via Knowledge Probe ACL 2026 Exploring Spatial Intelligence from a Generative Perspective CVPR 2026 Extending Embodied Question Answering from Perception to Decision CVPR 2026 Extending First-Order Logic for Factual Reasoning over Knowledge Graphs ACL 2026 Failure Modes in Multi-Hop QA: The Weakest Link Effect and the Recognition Bottleneck ACL 2026 FAST-EQA: Efficient Embodied Question Answering with Global and Local Region Relevancy WACV 2026 Figure It Out: Improve the Frontier of Reasoning with Executable Visual States ACL 2026 FinChain: A Symbolic Benchmark for Verifiable Chain-of-Thought Financial Reasoning ACL 2026 FLAIR: Steering LLM Mathematical Problem Solving based on A Fuzzy-Logic-AssIsted Reasoner ACL 2026 FlowSearch: Advancing Deep Research with Dynamic Structured Knowledge Flow ACL 2026 Foresight Optimization for Strategic Reasoning in Large Language Models ACL 2026 Forest Before Trees: Latent Superposition for Efficient Visual Reasoning ACL 2026 Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs ACL 2026 From "Aha Moments" to Controllable Thinking: Toward Meta-Cognitive Reasoning in LRMs via Decoupled Reasoning and Control ACL 2026 From Answers to Arguments: Toward Trustworthy Clinical Diagnostic Reasoning with Toulmin-Guided Curriculum Goal-Conditioned Learning ACL 2026 From Data-Centric to Sample-Centric: Enhancing LLM Reasoning via Progressive Optimization ACL 2026