Agent-RL's picture

4 4

Agent-RL

agentrl

·

https://github.com/Agent-RL

agentrl

AI & ML interests

None yet

Recent Activity

upvoted a paper 14 days ago

Surrogate Signals from Format and Length: Reinforcement Learning for Solving Mathematical Problems without Ground Truth Answers

upvoted an article 15 days ago

The 4 Things Qwen-3's Chat Template Teaches Us

updated a dataset about 2 months ago

agentrl/ReCall-data

View all activity

Organizations

None yet

agentrl's activity

upvoted a paper 14 days ago

Surrogate Signals from Format and Length: Reinforcement Learning for Solving Mathematical Problems without Ground Truth Answers

Paper • 2505.19439 • Published 16 days ago • 30

upvoted an article 15 days ago

Article

The 4 Things Qwen-3's Chat Template Teaches Us

By

•

Apr 30

• 52

upvoted a collection 2 months ago

ReSearch

Trained models as described in the paper "ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning" • 5 items • Updated Mar 27 • 6

upvoted a paper 3 months ago

ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning

Paper • 2503.19470 • Published Mar 25 • 18