LLM Agents and Reinforcement Learning
9 repos
Systems and frameworks for building autonomous agents powered by large language models, with emphasis on reinforcement learning, tool use, and scalable training approaches. The cluster covers agent architectures, reward modeling, multi-agent coordination, and optimization techniques for making LLMs more capable at complex reasoning and task execution. Repositories range from foundational agent systems to specialized approaches like retrieval-augmented reasoning and efficient model scaling.
Python · 8
reinforcement-learning ·22,871
llm ·21,954
rl ·17,367
agent ·17,002
llm-reasoning ·11,498
machine-learning-systems ·11,498
mlsys ·11,498
llm-agent ·11,498
intern-s1 ·5,195
internvl ·5,195
