Skip to content

PaperCodex

Subscribe

Reasoning Enhancement

CodeI/O: Boost LLM Reasoning Across Domains by Learning from Code Input-Output Patterns

CodeI/O: Boost LLM Reasoning Across Domains by Learning from Code Input-Output Patterns 563

Large language models (LLMs) have demonstrated impressive capabilities in code generation and narrow reasoning tasks like mathematics. Yet, when it…

01/13/2026Procedural Reasoning, Reasoning Enhancement, Verifiable Chain-of-thought
SQuARE: Boost LLM Reasoning with Self-Generated Questions—No Retraining Needed

SQuARE: Boost LLM Reasoning with Self-Generated Questions—No Retraining Needed 757

Solving complex reasoning problems is a persistent challenge for Large Language Models (LLMs). While techniques like Chain-of-Thought (CoT) prompting have…

01/13/2026Chain-of-thought Prompting, Question Answering, Reasoning Enhancement
Copyright © 2026 PaperCodex.
  • Facebook
  • YouTube
  • Twitter

PaperCodex