Reinforcement Learning
489 subscribers
5 photos
3 files
223 links
RL discussions
Download Telegram
https://arxiv.org/html/2504.11536v1

Introducing ReTool, a reinforcement learning framework for strategic tool use in LLMs.
Enhances long-form reasoning by integrating real-time code execution.
Develops an automated RL paradigm for multi-turn code execution and tool invocation
https://arxiv.org/abs/2504.15777
Tina demonstrates that substantial reasoning performance can be developed using only minimal resources, by applying parameter-efficient updates during reinforcement learning (RL), using low-rank adaptation (LoRA), to an already tiny 1.5B parameter base model.