griver/Q-RAG

Retrieval and Retrieval-augmented LLMs

Empowering RAG with a memory-based data interface for all-purpose applications!

[EMNLP26] contextpilot: teaching agents for proactive context management via fine-grained rl

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

BABILong is a benchmark for LLM evaluation using the needle-in-a-haystack approach.

EvoEmbedding: Evolvable Representations for Long-Context Retrieval and Agentic Memory

Data and Code for EMNLP 2025 Findings Paper "MCTS-RAG: Enhancing Retrieval-Augmented Generation with Monte Carlo Tree Search"

Tevatron - Unified Document Retrieval Toolkit across Scale, Language, and Modality. Demo in SIGIR 2023, SIGIR 2025.

🚀 Ultra Recipe for Training Long-Horizon Search Agents - matching frontier AI's search capability with a 20B model + stateful harness