A collection of graph foundation models including papers, codes, and datasets.

Must-read papers on graph foundation models (GFMs)

Metacognitive Prompting Improves Understanding in Large Language Models (NAACL 2024)

NAACL2025 - Decomposition Dilemmas: Does Claim Decomposition Boost or Burden Fact-Checking Performance?

This is the official implementation of the paper "S²R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning"

Official repository for the paper "Alpha-SQL: Zero-Shot Text-to-SQL using Monte Carlo Tree Search" [ICML'25]

📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程

Skill-Targeted Adaptive Training

[ICML'25 Oral] Multi-agent Architecture Search via Agentic Supernet

Reinforced Multi-LLM Agents training

Deep Research

Emergent Hierarchical Reasoning in LLMs/VLMs through Reinforcement Learning

Fully open reproduction of DeepSeek-R1

A Survey of Reinforcement Learning for Large Reasoning Models

[EMNLP 2025] Awesome RAG Reasoning Resources

DeepConf: Deep Think with Confidence

Agentic-RAG explores advanced Retrieval-Augmented Generation systems enhanced with AI LLM agents.

[arxiv: 2505.02156] Adaptive Thinking via Mode Policy Optimization for Social Language Agents

[NeurIPS'25] Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning

[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards