Complex Reasoning
Complex reasoning in artificial intelligence focuses on developing models capable of multi-step, logical inference and problem-solving, mirroring human cognitive abilities. Current research emphasizes improving large language models (LLMs) through techniques like chain-of-thought prompting, retrieval-augmented generation (RAG), and the integration of symbolic reasoning with neural networks, often incorporating multi-modal data (e.g., visual and textual information). These advancements are significant for enhancing the reliability and applicability of AI systems across diverse fields, including autonomous driving, robotics, and scientific discovery, by enabling more robust and accurate decision-making in complex scenarios.
552papers
Papers - Page 9
February 26, 2025
Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs
Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning?
Dealing with Inconsistency for Reasoning over Knowledge Graphs: A Survey
Random Forest-of-Thoughts: Uncertainty-aware Reasoning for Computational Social Science
February 25, 2025
VOILA: Evaluation of MLLMs For Perceptual Understanding and Analogical Reasoning
TextGames: Learning to Self-Play Text-Based Puzzle Games via Language Model Reasoning
Rank1: Test-Time Compute for Reranking in Information Retrieval
Verdict: A Library for Scaling Judge-Time Compute
Towards Better Understanding of Program-of-Thought Reasoning in Cross-Lingual and Multilingual Environments
Your Language Model May Think Too Rigidly: Achieving Reasoning Consistency with Symmetry-Enhanced Training
February 24, 2025
From System 1 to System 2: A Survey of Reasoning Large Language Models
Reasoning with Latent Thoughts: On the Power of Looped Transformers
Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoning
Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models
Reasoning Does Not Necessarily Improve Role-Playing Ability
February 23, 2025
February 22, 2025