Tsinghua-dhy / UR2Links
UR2: Unify RAG and Reasoning through Reinforcement Learning
☆126Updated last month
Alternatives and similar repositories for UR2
Users that are interested in UR2 are comparing it to the libraries listed below
Sorting:
- [BIRD-INTERACT] Re-imagines Text-to-SQL evaluation via lens of dynamic interactions.☆455Updated 3 weeks ago
- "LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?"☆582Updated 2 months ago
- Official Repo of "RobustFlow: Towards Robust Agentic Workflow Generation"☆231Updated 2 months ago
- The enhanced model is specially trained for aquatic targets, achieving higher accuracy. It can detect sailboats, humans, other vessels, b…☆47Updated 8 months ago
- ☆55Updated last month
- ☆104Updated 3 months ago
- AI-powered tool for analyzing GitHub trending repositories and URL metadata☆25Updated last week
- Logic-in-frames: Dynamic keyframe search via visual semantic-logical verification for long video understanding☆57Updated last month
- switch2ai - A JetBrains IDE plugin enabling seamless collaboration between JetBrains IDEs and various AI agents (Cursor, Qoder, Claude co…☆169Updated 2 months ago
- Repo-level benchmark for real-world Code Agents: from repo understanding → env setup → incremental dev/bug-fixing → task delivery, with c…☆243Updated 3 months ago
- Gotta Hear Them All: Towards Sound Source Aware Audio Generation.☆67Updated 2 months ago
- Marco Search Agent for Realistic and Challenging Agentic Search☆240Updated 2 months ago
- your finance bro Agent for trading and investing☆107Updated 2 months ago
- [AAAI 2026 Oral] FreeAskWorld is an interactive simulation framework that integrates large language models (LLMs) for high-level plannin…☆195Updated last week
- On Predictability of Reinforcement Learning Dynamics for Large Language Models☆51Updated last month
- CPG-SPMT: Control-oriented Parameter-Grouped Single Particle Model with Thermal effects☆38Updated 2 months ago
- A multi-agent debate framework supporting AI-vs-AI and Human-vs-AI modes with customizable models, personas, and role-specific prompts.☆64Updated last month
- ☆357Updated 6 months ago
- INFTY Engine: An Optimization Toolkit to Support Continual AI☆566Updated 4 months ago
- [USENIX Security'25] THEMIS: Towards Practical Intellectual Property Protection for Post-Deployment On-Device Deep Learning Models☆108Updated 5 months ago
- A lightweight React component that renders its children only on the client side, helping avoid SSR hydration errors in frameworks like Ne…☆31Updated 2 months ago
- MTLA: Multi-head Temporal Latent Attention☆761Updated 3 months ago
- A curated list of awesome papers, resources, and tools for Visual Prompt Tuning (VPT).☆106Updated 2 months ago
- 🐾 PawHaven — An open-source, enterprise-ready full-stack project powered by React, NestJS, and pnpm, featuring a Monorepo architecture t…☆86Updated last week
- [AAAI 2026 Oral] Official repository for InfiGUI-G1. We introduce Adaptive Exploration Policy Optimization (AEPO) to overcome semantic al…☆123Updated last month
- Beyond log-likelihood: exploring alternative objectives for supervised fine-tuning of language model post-training☆54Updated 3 months ago
- ☆223Updated 2 weeks ago
- ☆293Updated 6 months ago
- [NeurIPS'25] KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems☆112Updated 2 months ago
- We introduce the Audio Logical Reasoning (ALR) dataset, consisting of 6,446 text-audio annotated samples specifically designed for comple…☆1,103Updated last month