7 papers
HeaPA: Difficulty-Aware Heap Sampling and On-Policy Query Augmentation for LLM Reinforcement Learning
Weiqi Wang, Xin Liu, Binxuan Huang +13
RLVR has become a standard recipe for training LLMs on reasoning tasks with verifiable outcomes, but when rollout generation dominates the cost, efficiency hinges on which prompts…
Self-Rewarding PPO: Aligning Large Language Models with Demonstrations Only
Qingru Zhang, Liang Qiu, Ilgee Hong +11
Supervised fine-tuning (SFT) has emerged as a crucial method for aligning large language models (LLMs) with human-annotated demonstrations. However, SFT, being an off-policy approa…
Ask a Strong LLM Judge when Your Reward Model is Uncertain
Zhenghao Xu, Qin Lu, Qingru Zhang +9
Reward model (RM) plays a pivotal role in reinforcement learning with human feedback (RLHF) for aligning large language models (LLMs). However, classical RMs trained on human prefe…
Mitigating Lost in Multi-turn Conversation via Curriculum RL with Verifiable Accuracy and Abstention Rewards
Ming Li, Pei Chen, Zhenhao Zhang +10
Large Language Models demonstrate strong capabilities in single-turn instruction following but suffer from Lost-in-Conversation (LiC), a degradation in performance as information i…
Improving Sampling Efficiency in RLVR through Adaptive Rollout and Response Reuse
Yuheng Zhang, Wenlin Yao, Changlong Yu +5
Large language models (LLMs) have achieved impressive reasoning performance, with reinforcement learning with verifiable rewards (RLVR) emerging as a standard paradigm for post-tra…
SFT Doesn't Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMs
Jiacheng Lin, Zhongruo Wang, Kun Qian +14
Supervised Fine-Tuning (SFT) on domain-specific datasets is a common approach to adapt Large Language Models (LLMs) to specialized tasks but is often believed to degrade their gene…
WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning
Zhepei Wei, Wenlin Yao, Yao Liu +9
While reinforcement learning (RL) has demonstrated remarkable success in enhancing large language models (LLMs), it has primarily focused on single-turn tasks such as solving math…