Alibaba-NLP / qqrLinks
qqr is an RL training framework for open-ended agents.
☆205Updated 3 weeks ago
Alternatives and similar repositories for qqr
Users that are interested in qqr are comparing it to the libraries listed below
Sorting:
- Implementation for OAgents: An Empirical Study of Building Effective Agents☆306Updated 3 months ago
- Data Synthesis for Deep Research Based on Semi-Structured Data☆198Updated last month
- DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL☆281Updated 4 months ago
- LIMI: Less is More for Agency☆160Updated 3 months ago
- Open-source Agentic RL for LLMs — RLAnything & DemyAgent☆223Updated last week
- ☆93Updated 8 months ago
- [ICLR 2026] Efficient Agent Training for Computer Use☆135Updated 5 months ago
- Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments☆48Updated last month
- Towards a Unified View of Large Language Model Post-Training☆200Updated 5 months ago
- SSRL: Self-Search Reinforcement Learning☆206Updated 5 months ago
- MemEvolve & EvolveLab☆158Updated last month
- [NeurIPS 2025] The official repo of SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond☆191Updated 7 months ago
- ☆281Updated last week
- WideSearch: Benchmarking Agentic Broad Info-Seeking☆118Updated 4 months ago
- Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL.☆534Updated 5 months ago
- MiroRL is an MCP-first reinforcement learning framework for deep research agent.☆229Updated 5 months ago
- The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution☆217Updated last week
- REverse-Engineered Reasoning for Open-Ended Generation☆91Updated 5 months ago
- MiroMind-M1 is a fully open-source series of reasoning language models built on Qwen-2.5, focused on advancing mathematical reasoning.☆255Updated 5 months ago
- A construction kit for reinforcement learning environment management.☆326Updated this week
- Scaling Long-Horizon LLM Agent via Context-Folding☆106Updated 2 weeks ago
- The official repo of "WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents"☆101Updated 4 months ago
- A unified suite for generating elite reasoning problems and training high-performance LLMs, including pioneering attention-free architect…☆134Updated last week
- ☆271Updated last week
- Official Repository for "Glyph: Scaling Context Windows via Visual-Text Compression"☆561Updated 3 months ago
- ☆78Updated 7 months ago
- [NeurIPS 2025 Spotlight] Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning☆149Updated 4 months ago
- MMSearch-R1 is an end-to-end RL framework that enables LMMs to perform on-demand, multi-turn search with real-world multimodal search too…☆392Updated 5 months ago
- Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcemen…☆587Updated 5 months ago
- The offical repo for "Parallel-R1: Towards Parallel Thinking via Reinforcement Learning"☆256Updated last week