Lists (4)
Stars
[ICLR'25] BigCodeBench: Benchmarking Code Generation Towards AGI
Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**
[ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference
[ICML 2025 Spotlight] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference
Adaptive Draft-Verification for Efficient Large Language Model Decoding (AAAI 2025 Oral)
Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024
Distributed Triton for Parallel Systems
Building Open LLM Web Agents with Self-Evolving Online Curriculum RL
Code repo for "WebArena: A Realistic Web Environment for Building Autonomous Agents"
⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)
Atropos is a Language Model Reinforcement Learning Environments fr B29E amework for collecting and evaluating LLM trajectories through diverse environments
free and open OpenAI Deep Research
Survey on LLM Agents (Published on CoLing 2025)
An interactive NVIDIA-GPU process viewer and beyond, the one-stop solution for GPU process management.
xLAM: A Family of Large Action Models to Empower AI Agent Systems
LLM Agent Framework in ComfyUI includes MCP sever, Omost,GPT-sovits, ChatTTS,GOT-OCR2.0, and FLUX prompt nodes,access to Feishu,discord,and adapts to all llms with similar openai / aisuite interfac…
ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning
AgentSociety: Large-scale Social Simulation to Understand Human Behaviors and Society through LLM-driven Agents
A curated list of reinforcement learning with human feedback resources (continually updated)
Code for Paper: Learning Adaptive Parallel Reasoning with Language Models
Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling
Official Repository of "Learning to Reason under Off-Policy Guidance"
Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning Tasks