SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks
Paper
• 2503.15478 • Published
• 13
Song Jiang
songjiang
AI & ML interests
None yet
Recent Activity
upvoted a paper 1 day ago
ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning upvoted a paper 5 months ago
SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models upvoted a paper 5 months ago
Large Reasoning Models Learn Better Alignment from Flawed Thinking Organizations
None yet
authored a paper 11 months ago
authored a paper over 2 years ago