multi-step reasoning

AgentDiagnose: An Open Toolkit for Diagnosing LLM Agent Trajectories EMNLP 2025 ALARB: An Arabic Legal Argument Reasoning Benchmark EMNLP 2025 ASPERA: A Simulated Environment to Evaluate Planning for Complex Action Execution ACL 2025 Beyond the Destination: A Novel Benchmark for Exploration-Aware Embodied Question Answering ICCV 2025 Can Vision-Language Models Solve Visual Math Equations? EMNLP 2025 CER: Confidence Enhanced Reasoning in LLMs ACL 2025 ChatGen: Automatic Text-to-Image Generation From FreeStyle Chatting CVPR 2025 CodePlan: Unlocking Reasoning Potential in Large Language Models by Scaling Code-form Planning ICLR 2025 Comparing Language Models of Different Scales for Security-Focused Tabular Query Generation and Reasoning IJCNLP 2025 CSIRO LT at SemEval-2025 Task 8: Answering Questions over Tabular Data using LLMs SemEval 2025 Deliberate Reasoning in Language Models as Structure-Aware Planning with an Accurate World Model ACL 2025 Efficient Tool Use with Chain-of-Abstraction Reasoning COLING 2025 Emergent Wisdom at BEA 2025 Shared Task: From Lexical Understanding to Reflective Reasoning for Pedagogical Ability Assessment ACL 2025 Encoder of Thoughts: Enhancing Planning Ability in Language Agents Through Structural Embedding AAAI 2025 Entropy-based Exploration Conduction for Multi-step Reasoning ACL 2025 Explicitly Guided Difficulty-Controllable Visual Question Generation AAAI 2025 Exploring Backward Reasoning in Large Language Models NAACL 2025 FastMCTS: A Simple Sampling Strategy for Data Synthesis ACL 2025 First-Step Advantage: Importance of Starting Right in Multi-Step Math Reasoning ACL 2025 From Awareness to Adaptability: Enhancing Tool Utilization for Scientific Reasoning ACL 2025 Generating Commonsense Reasoning Questions with Controllable Complexity through Multi-step Structural Composition COLING 2025 GFlowVLM: Enhancing Multi-step Reasoning in Vision-Language Models with Generative Flow Networks CVPR 2025 GRADEO: Towards Human-Like Evaluation for Text-to-Video Generation via Multi-Step Reasoning ICML 2025 GraphInsight: Unlocking Insights in Large Language Models for Graph Structure Understanding ACL 2025 KGARevion: An AI Agent for Knowledge-Intensive Biomedical QA ICLR 2025