Intelligent-Internet / ii-thoughtLinks
II-Thought-RL is our initial attempt at developing a large-scale, multi-domain Reinforcement Learning (RL) dataset
☆27Updated 5 months ago
Alternatives and similar repositories for ii-thought
Users that are interested in ii-thought are comparing it to the libraries listed below
Sorting:
- [EMNLP 2025] The official implementation for paper "Agentic-R1: Distilled Dual-Strategy Reasoning"☆99Updated 3 weeks ago
- Train your own SOTA deductive reasoning model☆106Updated 6 months ago
- ☆56Updated 2 months ago
- A fast, local, and secure approach for training LLMs for coding tasks using GRPO with WebAssembly and interpreter feedback.☆38Updated 5 months ago
- [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?☆77Updated 6 months ago
- accompanying material for sleep-time compute paper☆111Updated 4 months ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆55Updated 7 months ago
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆172Updated 8 months ago
- Simple examples using Argilla tools to build AI☆55Updated 10 months ago
- [ACL 2025] Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems☆105Updated 3 months ago
- ☆133Updated 6 months ago
- GPT-4 Level Conversational QA Trained In a Few Hours☆64Updated last year
- ☆40Updated 9 months ago
- Verifiers for LLM Reinforcement Learning☆72Updated 5 months ago
- Official homepage for "Self-Harmonized Chain of Thought" (NAACL 2025)☆92Updated 7 months ago
- Data preparation code for CrystalCoder 7B LLM☆45Updated last year
- ☆117Updated 4 months ago
- Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data genera…☆95Updated this week
- ☆23Updated last year
- ☆91Updated 3 months ago
- ☆67Updated 5 months ago
- Data Synthesis for Deep Research Based on Semi-Structured Data☆151Updated this week
- ☆99Updated last year
- Easy to use, High Performant Knowledge Distillation for LLMs☆93Updated 4 months ago
- LLM reads a paper and produce a working prototype☆56Updated 5 months ago
- Nexusflow function call, tool use, and agent benchmarks.☆29Updated 9 months ago
- Training an LLM to use a calculator with multi-turn reinforcement learning, achieving a **62% absolute increase in evaluation accuracy**.☆52Updated 4 months ago
- ☆68Updated 3 months ago
- ☆23Updated 7 months ago
- Experimental Code for StructuredRAG: JSON Response Formatting with Large Language Models☆111Updated 5 months ago