Artificial Intelligence › Core AI ›

Reasoning

2595 directly classified papers

Papers per year

Papers

CoMAT: Chain of Mathematically Annotated Thought Improves Mathematical Reasoning EMNLP 2025

Step Guided Reasoning: Improving Mathematical Reasoning using Guidance Generation and Step Reasoning EMNLP 2025

PLAN-TUNING: Post-Training Language Models to Learn Step-by-Step Planning for Complex Problem Solving EMNLP 2025

Semantic Inversion, Identical Replies: Revisiting Negation Blindness in Large Language Models EMNLP 2025

Follow the Flow: Fine-grained Flowchart Attribution with Neurosymbolic Agents EMNLP 2025

Empowering Math Problem Generation and Reasoning for Large Language Model via Synthetic Data based Continual Learning Framework EMNLP 2025

Socratic-MCTS: Test-Time Visual Reasoning by Asking the Right Questions EMNLP 2025

Hidden in Plain Sight: Reasoning in Underspecified and Misspecified Scenarios for Multimodal LLMs EMNLP 2025

Stepwise Informativeness Search for Improving LLM Reasoning EMNLP 2025

ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoning EMNLP 2025

AgentPro: Enhancing LLM Agents with Automated Process Supervision EMNLP 2025

Augmenting Multi-Agent Communication with State Delta Trajectory EMNLP 2025

Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language Models EMNLP 2025

Collaborative Beam Search: Enhancing LLM Reasoning via Collective Consensus EMNLP 2025

CityEQA: A Hierarchical LLM Agent on Embodied Question Answering Benchmark in City Space EMNLP 2025

Examining False Positives under Inference Scaling for Mathematical Reasoning EMNLP 2025

R2I-Bench: Benchmarking Reasoning-Driven Text-to-Image Generation EMNLP 2025

Dynamic Collaboration of Multi-Language Models based on Minimal Complete Semantic Units EMNLP 2025

CCQA: Generating Question from Solution Can Improve Inference-Time Reasoning in SLMs EMNLP 2025

ConstraintLLM: A Neuro-Symbolic Framework for Industrial-Level Constraint Programming EMNLP 2025

Do Large Language Models excel in Complex Logical Reasoning with Formal Language? EMNLP 2025

ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models EMNLP 2025

Stepwise Reasoning Checkpoint Analysis: A Test Time Scaling Method to Enhance LLMs’ Reasoning EMNLP 2025

RLMEval: Evaluating Research-Level Neural Theorem Proving EMNLP 2025

DART: Distilling Autoregressive Reasoning to Silent Thought EMNLP 2025