9). The Danger of Overthinking – This paper investigates overthinking in Large Reasoning Models (LRMs)—a phenomenon where models prioritize extended internal reasoning over interacting with their environment.
LLMS
-
Inner Thinking Transformers: Scaling Reasoning in Small LLMs
By
–
10). Inner Thinking Transformers – A new method that enhances reasoning efficiency in small-scale LLMs via dynamic depth scaling. ITT aims to mitigate parameter bottlenecks in LLMs, providing scalable reasoning efficiency without expanding model size.
-
Open-Reasoner-Zero: Efficient RL Framework Outperforms DeepSeek-R1
By
–
7). Open-Reasoner-Zero – an open-source large-scale minimalist RL framework to enhance reasoning. Achieves significant scalability requiring only 1/30th of the training steps of DeepSeek-R1-Zero-Qwen-32B to outperform it on GPQA Diamond.
-
MoBA: New Attention Mechanism for Efficient Long-Context LLMs
By
–
8). MoBA – A new attention mechanism that enhances efficiency in handling long-context sequences for LLMs while maintaining strong performance.
-
Complete RAG Guide: LangChain Implementations and Advanced Retrieval
By
–
bRAG: Complete RAG Guide A comprehensive project showcasing RAG implementations with LangChain – from basics to advanced features like multi-query retrieval, ColBERT indexing, and RAG-Fusion. Check out this 1.7K+ starred guide https://
github.com/bRAGAI/bRAG-la
ngchain/
… -
LangChain Korean Tutorial: RAG, Agents and Core Technologies
By
–
LangChain Korean Tutorial A comprehensive guide combining documentation, videos, and hands-on examples for mastering LangChain in Korean. Features practical implementations of RAG, agents, and core LangChain technologies. Check it out here https://
github.com/teddylee777/la
ngchain-kr
… -
Build AI Agents Fast with CopilotKit LangGraph
By
–
Build AI Agents Fast Create powerful AI agents with CopilotKit's CoAgents & LangGraph in just 30 minutes. Includes full stack implementation and LangSmith monitoring capabilities. Start building your agent now! https://
dev.to/copilotkit/age
nts-101-how-to-build-your-first-ai-agent-in-30-minutes-1042
… -
RAG Tutorial: Enhancing LLMs with Retrieval-Augmented Generation
By
–
RAG Tutorial Dive into Retrieval-Augmented Generation with this tutorial using Hugging Face and OpenAI. Build powerful RAG systems with LangChain's vector stores to enhance LLM capabilities and reduce hallucinations. Watch the tutorial: https://
youtube.com/watch?v=i0wcc8
qjfJw
… -
Building Local Agentic RAG Systems with LangChain Qdrant
By
–
Local Agentic RAG Tutorial Learn to build a privacy-focused RAG system that runs 100% locally using LangChain, Qdrant, and Ollama. This tutorial shows you how to implement agentic RAG with local embeddings and multiple data source support. Watch the full tutorial:
-
CUDA through PyTorch sufficient for most training scenarios
By
–
Yes, I mean 99% of the time it's fine to just use CUDA through PyTorch (eager or compiled). If you train million-dollar-expensive LLMs, then maybe writing your own optimized CUDA kernels and custom NCCL would probably worthwhile so you can shave off some $$$ off your training