thu-coai / GlyphLinks
Official Repository for "Glyph: Scaling Context Windows via Visual-Text Compression"
☆539Updated last month
Alternatives and similar repositories for Glyph
Users that are interested in Glyph are comparing it to the libraries listed below
Sorting:
- ToolOrchestra is an end-to-end RL training framework for orchestrating tools and agentic workflows.☆430Updated last week
- LightMem: Lightweight and Efficient Memory-Augmented Generation☆473Updated 2 weeks ago
- DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL☆218Updated 2 months ago
- LIMI: Less is More for Agency☆155Updated 2 months ago
- Data Synthesis for Deep Research Based on Semi-Structured Data☆190Updated last week
- ☆424Updated 2 weeks ago
- [DAI 2025] Beyond GPT-5: Making LLMs Cheaper and Better via Performance–Efficiency Optimized Routing☆197Updated 2 weeks ago
- 🛠️ DeepAgent: A General Reasoning Agent with Scalable Toolsets☆906Updated this week
- Implementation for OAgents: An Empirical Study of Building Effective Agents☆297Updated 2 months ago
- A Scientific Multimodal Foundation Model☆624Updated 3 months ago
- The offical repo for "Parallel-R1: Towards Parallel Thinking via Reinforcement Learning"☆244Updated last month
- An Open-Source Large-Scale Reinforcement Learning Project for Search Agents☆521Updated last month
- Official repository for DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research☆476Updated this week
- Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL.☆510Updated 3 months ago
- Official code repository for Sketch-of-Thought (SoT)☆129Updated 7 months ago
- Next paradigm for LLM Agent. Unify plan and action through recursive code generation for adaptive, human-like decision-making.☆515Updated 3 weeks ago
- Qwen3Guard is a multilingual guardrail model series developed by the Qwen team at Alibaba Cloud.☆388Updated 2 months ago
- 🐉 Loong: Synthesize Long CoTs at Scale through Verifiers.☆476Updated last month
- The evaluation benchmark on MCP servers☆231Updated 3 months ago
- Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcemen…☆537Updated 3 months ago
- [EMNLP 2025] The official implementation for paper "Agentic-R1: Distilled Dual-Strategy Reasoning"☆100Updated 4 months ago
- A reproduction of the Deepseek-OCR model including training☆200Updated last month
- A MemAgent framework that can be extrapolated to 3.5M, along with a training framework for RL training of any agent workflow.☆844Updated 4 months ago
- Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B☆553Updated last month
- SSRL: Self-Search Reinforcement Learning☆195Updated 4 months ago
- ☆449Updated last week
- UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse Modalities and Granularities☆131Updated 7 months ago
- Efficient Agent Training for Computer Use☆134Updated 3 months ago
- ☆73Updated 2 months ago
- ☆84Updated 8 months ago