Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

A Framework for LLM-based Multi-Agent Reinforced Training and Inference

Awesome-Large-Search-Models is a collection of papers and resources (Methods, Datasets and other resources) about search-oriented large reasoning models (Large search models). Awesome Large Search Models and Awesome Agentic Search.

Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models

Official Implementation of "Reasoning Language Models: A Blueprint"

FastCuRL: Curriculum Reinforcement Learning with Stage-wise Context Scaling for Efficient LLM Reasoning

Code for the 2025 ACL publication "Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs"

Paper list of safety in reasoning of Large Reasoning Models (LRMs).

Official code for the paper "SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning"

Walk Before You Run! Concise LLM Reasoning via Reinforcement Learning

Awesome-Large-Search-Models is a collection of key papers and resources focused on search-oriented large language models. Explore methods, datasets, and tools to enhance your understanding and development of large search models. 🌟🐙