Skip to content
conftrace_

multi-round reinforcement learning

1 paper

Explore in graph

Also known as

MULTI-ROUND RL

Co-occurring keywords · papers mentioning both

agentic language model (1) behavior tree (1) tool use (1) synthetic data generation (1)

Papers

AgenticQwen: Training Small Agentic Language Models with Dual Data Flywheels for Industrial-Scale Tool Use ACL 2026