zai-org/GLM-4.5
Text Generation • 358B • Updated • 138k • • 1.41k
Good agents related space, model, dataset
Good agents related space, model, dataset collection
-
-
GLM 4.5V Demo App
🏃31Demo App of dmg file
-
nvidia/Cosmos-Reason1-7B
Image-Text-to-Text • 8B • Updated • 24.2k • 243 -
Web Search MCP
🔎165Search and extract web content for LLM ingestion
-
OpenGVLab/ScaleCUA-Data
Preview • Updated • 1.42k • 31 -
OpenGVLab/ScaleCUA-32B
Image-Text-to-Text • 33B • Updated • 146 • 21 -
Qwen/Qwen3-Omni-30B-A3B-Instruct
Any-to-Any • 35B • Updated • 1.6M • 962 -
Qwen3 VL Demo
😻112Chat with a multimodal AI using text and images
-
Qwen/Qwen3-VL-30B-A3B-Instruct
Image-Text-to-Text • 31B • Updated • 995k • • 587 -
pipecat-ai/smart-turn-v3
Voice Activity Detection • Updated • 182 -
Alibaba-NLP/Tongyi-DeepResearch-30B-A3B
Text Generation • 31B • Updated • 7.24k • 814 -
Tongyi DeepResearch
👀63Search and generate detailed answers to complex queries
-
AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning
Paper • 2509.08755 • Published • 56 -
Qwen/Qwen3-VL-2B-Thinking
Image-Text-to-Text • 2B • Updated • 70.3k • 116 -
nvidia/omnivinci
Feature Extraction • Updated • 317 • 178 -
MiniMaxAI/MiniMax-M2
Text Generation • 229B • Updated • 109k • • 1.5k -
WeiboAI/VibeThinker-1.5B
Text Generation • 2B • Updated • 3.42k • • 552 -
deepseek-ai/DeepSeek-V3.2-Speciale
Text Generation • 685B • Updated • 882 • • 716 -
CUGA Agent
🤖105Configurable Generalist Agent, leader in AppWorld Benchmark
-
Small Language Models for Efficient Agentic Tool Calling: Outperforming Large Models with Targeted Fine-tuning
Paper • 2512.15943 • Published • 3 -
AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents
Paper • 2512.23343 • Published • 30 -
General Agentic Memory Via Deep Research
Paper • 2511.18423 • Published • 172 -
Memory in the Age of AI Agents
Paper • 2512.13564 • Published • 160 -
KVzap: Fast, Adaptive, and Faithful KV Cache Pruning
Paper • 2601.07891 • Published • 3 -
LIMI: Less is More for Agency
Paper • 2509.17567 • Published • 104 -
AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts
Paper • 2601.11044 • Published • 35 -
The Responsibility Vacuum: Organizational Failure in Scaled Agent Systems
Paper • 2601.15059 • Published • 4 -
Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice
Text-to-Speech • 0.9B • Updated • 1.56M • 170 -
FlashLabs/Chroma-4B
Any-to-Any • 6B • Updated • 228 • 382 -
Continual GUI Agents
Paper • 2601.20732 • Published • 5 -
Recursive Language Models
Paper • 2512.24601 • Published • 99 -
When to Memorize and When to Stop: Gated Recurrent Memory for Long-Context Reasoning
Paper • 2602.10560 • Published • 31 -
MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning
Paper • 2601.21468 • Published • 25 -
Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning
Paper • 2602.10090 • Published • 53 -
GLM-5: from Vibe Coding to Agentic Engineering
Paper • 2602.15763 • Published • 203 -
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16
Text Generation • 124B • Updated • 988k • • 407 -
Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
Paper • 2512.20848 • Published • 44 -
MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild
Paper • 2603.17187 • Published • 141 -
Context-Value-Action Architecture for Value-Driven Large Language Model Agents
Paper • 2604.05939 • Published • 10 -
OpenMOSS-Team/MOSS-TTS-Nano-100M
Text-to-Speech • Updated • 56k • 231 -
Learning to Act and Cooperate for Distributed Black-Box Consensus Optimization
Paper • 2605.00691 • Published • 4 -
SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Tasks
Paper • 2604.20087 • Published • 15 -
THUIR/MemoryBench
Viewer • Updated • 4.06k • 4.02k • 18