qqr is an RL training framework for open-ended agents.

Tongyi Deep Research, the Leading Open-source Deep Research Agent

Repo for "VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning"

[EMNLP 2025] ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents

[EMNLP 2025] Code for "Detecting Knowledge Boundary of Vision Large Language Models by Sampling-Based Inference"

E2Rank: Your Text Embedding can Also be an Effective and Efficient Listwise Reranker

A new evaluation paradigm for deep search that identifies specific LLM failure sources, introduces challenging hint-free datasets with holistic evaluation, and offers a strong baseline incorporating memory and verification.

ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Repo for NAACL 2025 Paper "Unfolding the Headline: Iterative Self-Questioning for News Retrieval and Timeline Summarization"