Stars
Serenity-inspired Agent Skill for supply-chain bottleneck stock research
Towards Self-Evolving Proactive AI with Perpetual Memory
Topology-Masked Diffusion Language Model for Text-Attributed Graph Learning
The best-benchmarked open-source AI memory system. And it's free.
SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal
[Up-To-Date] Awesome Agent Memory Paper Resource
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
The source code of Mem-Gallery: Benchmarking Multimodal Long-Term Conversational Memory for MLLM Agents.
[ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation
GSM8K-V: Can Vision Language Models Solve Grade School Math Word Problems in Visual Contexts
[TKDE2025] Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL | A curated list of resources (surveys, papers, benchmarks, and opensource projects) on large language model-based …
[ICLR 2026] Youtu-GraphRAG: Vertically Unified Agents for Graph Retrieval-Augmented Complex Reasoning
(ICML'25 Outstanding) CollabLLM: From Passive Responders to Active Collaborators
A curated list of resources for "Flow Matching Meets Biology and Life Science: A Survey". Nature Portfolio Journal Artificial Intelligence. https://www.nature.com/articles/s44387-025-00066-y
Repair malformed JSON from LLMs, APIs, logs, and user input in Python.
[NeurIPS 2025] 🌐 WebThinker: Empowering Large Reasoning Models with Deep Research Capability
Tongyi Deep Research, the Leading Open-source Deep Research Agent
[ACL 2026 KnowFM] Awesome Agentic Deep Research Resources
[Up-to-date] A curated list of resources on graph-empowered agents and agent-facilitated graph learning (Graphs Meet Agents).
Get started with building Fullstack Agents using Gemini 2.5 and LangGraph
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
Train transformer language models with reinforcement learning.
[NeurIPS'24] HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents. RAG + Knowledge Graphs + Personali…
PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation
Latest Advances on System-2 Reasoning