ThetaEvolve: Test-time Learning on Open Problems

The open-source code for the NeurIPS 2025 paper, "Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning."

https://hrl.boyuai.com/

[Survey] A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems

Open-source implementation of AlphaEvolve

ShinkaEvolve: Towards Open-Ended and Sample-Efficient Program Evolution

KDD2025, Generative Next POI Recommendation with Semantic ID

[NeurIPS 2025] CAM: A Constructivist View of Agentic Memory for LLM-Based Reading Comprehension

Universal memory layer for AI Agents

The code for NeurIPS 2025 paper "A-MEM: Agentic Memory for LLM Agents"

A Survey of Personalization: From RAG to Agent

Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL

This repository introduce a comprehensive paper list, datasets, methods and tools for memory research.

Awesome papers about unifying LLMs and KGs

[IJCAI'24] Official code for our paper "Make Graph Neural Networks Great Again: A Generic Integration Paradigm of Topology-Free Patterns for Traffic Speed Prediction".

[ICML 2023] "On Strengthening and Defending Graph Reconstruction Attack with Markov Chain Approximation"

Code for paper “Domain-Informed Negative Sampling Strategies for Dynamic Graph Embedding in Meme Stock-Related Social Networks”

Negative Sampling in Next-POI Recommendations: Observation, Approach, and Evaluation [ACM WWW-24]

DyGLib with CNEN (KDD 2024)

code and data for Improving Temporal Link Prediction via Temporal Walk Matrix Projection, NeurIPS 2024

ExNext: Self-Explainable Next POI Recommendation, ACM SIGIR Conference on Research and Development in Information Retrieval, 2024

The official PyTorch implementation for 2025-AAAI-Integrating Personalized Spatio-Temporal Clustering for Next POI Recommendation

Codes for CIKM'24 paper: DTFormer: A Transformer-Based Method for Discrete-Time Dynamic Graph Representation Learning

The pytorch implementation of DisenPOI.