Tags: #reasoning

PageIndex is a vectorless, reasoning-based RAG system that builds a hierarchical tree index from long documents for agentic, context-aware retrieval, simulating human expert navigation.

OptiLLM is an OpenAI API-compatible inference proxy that significantly boosts LLM accuracy and performance on reasoning tasks using 20+ state-of-the-art optimization techniques, requiring zero training.

A plug-and-play Python library implementing the Tree of Thoughts (ToT) algorithm to significantly enhance Large Language Model reasoning capabilities by up to 70%.

A comprehensive, curated collection of research papers and resources focused on enhancing and understanding the reasoning abilities of Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs).