[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
- agent
- artificial-intelligence
- benchmark
- multimodal
Repository Index
71,372 visible repositories in the index
25–37 of 37 · Most stars
Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI, specializing in vision-language reasoning.
- deepseek-r1
- llm
- r1v
- reasoning
Agent RL framework for LLM agents: multi-turn reinforcement learning with StarPO and reasoning-collapse diagnostics
- agent-rl
- agentic-ai
- llm-agents
- reinforcement-learning
⭐️ NLP Algorithms with transformers lib. Supporting Text-Classification, Text-Generation, Information-Extraction, Text-Matching, RLHF, SFT etc.
- nlp
- text-classification
- text-matching
- information-extraction
A modular RL library to fine-tune language models to human preferences
- language-modeling
- nlp
- reinforcement-learning
- dialogue-generation
Developer Asset Hub for NVIDIA Nemotron — A one-stop resource for training recipes, usage cookbooks, datasets, and full end-to-end reference examples to build with Nemotron models
- ai
- fine-tuning
- model-training
- nemotron
Official repository of 'Visual-RFT: Visual Reinforcement Fine-Tuning' & 'Visual-ARFT: Visual Agentic Reinforcement Fine-Tuning'’
开源 AI CRM，Salesforce 开源替代 + ChatGPT 式 AI 助手：客户管理、知识库查询、任务执行，全程对话完成。Open-source AI CRM and Salesforce alternative powered by conversational AI.
Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level
Multi-agent graph orchestration engine for building your own software factory. Bring your own QA workflow, and the engine enforces it.
- ai-agents
- developer-tools
- agent-orchestration
- agentic-workflow
Local-first, open-source security gateway for AI coding agents. Enforce tool-call policies, detect secrets, and audit actions on-device.
- ai-agent-security
- ai-agents
- agent-security
- ai-security-tool
Scikit-learn for Recursive Self-improvement (RSI). A modular framework for recursive harness evolution.
- meta-learning
- reinforcement-learning
- rsi
- ai-agents
TavernGym and TavernBench: a faithful, full-content Hearthstone Battlegrounds simulator with an RL interface, and a 960-task decision benchmark. Code and data for "Build, Don't Play".
- game-ai
- hearthstone
- reinforcement-learning
- rust