4 papers
ToolSample: Dual Dynamic Sampling Methods with Curriculum Learning for RL-based Tool Learning
Zihao Feng, Xiaoxue Wang, Bowen Wu +4
While reinforcement learning (RL) is increasingly used for LLM-based tool learning, its efficiency is often hampered by an overabundance of simple samples that provide diminishing…
RAIDEN-R1: Improving Role-awareness of LLMs via GRPO with Verifiable Reward
Zongsheng Wang, Kaili Sun, Bowen Wu +3
Role-playing conversational agents (RPCAs) face persistent challenges in maintaining role consistency. To address this, we propose RAIDEN-R1, a novel reinforcement learning framewo…
F5R-TTS: Improving Flow-Matching based Text-to-Speech with Group Relative Policy Optimization
Xiaohui Sun, Ruitong Xiao, Jianye Mo +3
We present F5R-TTS, a novel text-to-speech (TTS) system that integrates Group Relative Policy Optimization (GRPO) into a flow-matching based architecture. By reformulating the dete…
Improving Generalization in Intent Detection: GRPO with Reward-Based Curriculum Sampling
Zihao Feng, Xiaoxue Wang, Ziwei Bai +4
Intent detection, a critical component in task-oriented dialogue (TOD) systems, faces significant challenges in adapting to the rapid influx of integrable tools with complex interr…