2 citations · 8 across the 18 of their papers we have counts for
18 papers
Reformulate LLM Reinforcement Learning for Efficient Training under Black-box Discrepancy
Jiashun Liu, Runze Liu, Xu Wan +3
Reinforcement Learning (RL) has emerged as a pivotal post-training paradigm, yet it frequently suffers from unpredictable sub-optimum performance or even training collapses. Recent…
When RL Fails after SFT: Rejuvenating Model Plasticity for Robust SFT-to-RL Handoff
Runze Liu, Jiashun Liu, Xu Wan +2
Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) has become a standard pipeline for Large Language Model (LLM) post-training. SFT is expected to provide a usefu…
Local Guidance, Global Impact: Gaussian-Reshaped Trust Region Unlocks Behavior Transitions
Bingxu Liu, Jiashun Liu, Johan Obando-Ceron +5
While Proximal Policy Optimization (PPO) demonstrates strong performance in stationary settings, we show that its standard optimization paradigm struggles in continual and non-stat…
Temporal Difference Learning with Constrained Initial Representations
Jiafei Lyu, Jingwen Yang, Zhongjian Qiao +5
Recently, there have been numerous attempts to enhance the sample efficiency of off-policy reinforcement learning (RL) agents when interacting with the environment, including archi…
PROF: An LLM-based Reward Code Preference Optimization Framework for Offline Imitation Learning
Shengjie Sun, Jiafei Lyu, Runze Liu +4
Offline imitation learning (offline IL) enables training effective policies without requiring explicit reward annotations. Recent approaches attempt to estimate rewards for unlabel…
A Survey of Reinforcement Learning for Large Reasoning Models
Kaiyan Zhang, Yuxin Zuo, Bingxiang He +36
In this paper, we survey recent advances in Reinforcement Learning (RL) for reasoning with Large Language Models (LLMs). RL has achieved remarkable success in advancing the frontie…
When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL
Jiakang Wang, Runze Liu, Qingpeng Cai +7
Reinforcement learning (RL) has shown great promise in large language models (LLMs) post-training, which typically rely on token-level clipping to maintain stability during optimiz…
Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models
Runze Liu, Jiakang Wang, Yuling Shi +11
Reinforcement Learning (RL) has shown remarkable success in enhancing the reasoning capabilities of Large Language Models (LLMs). Process-Supervised RL (PSRL) has emerged as a more…
ReviewRL: Towards Automated Scientific Review with RL
Sihang Zeng, Kai Tian, Kaiyan Zhang +9
Peer review is essential for scientific progress but faces growing challenges due to increasing submission volumes and reviewer fatigue. Existing automated review approaches strugg…
Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR
Jiakang Wang, Runze Liu, Fuzheng Zhang +3
Reinforcement Learning with Verifiable Rewards (RLVR) has become an effective post-training method for improving the reasoning abilities of Large Language Models (LLMs). However, e…
Bohdi: Heterogeneous LLM Fusion with Automatic Data Exploration
Junqi Gao, Zhichang Guo, Dazhi Zhang +5
Heterogeneous Large Language Model (LLM) fusion integrates the strengths of multiple source LLMs with different architectures into a target LLM with low computational overhead. Whi…
GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning
Jian Zhao, Runze Liu, Kaiyan Zhang +8
Recent advancements in Large Language Models (LLMs) have shown that it is promising to utilize Process Reward Models (PRMs) as verifiers to enhance the performance of LLMs. However…
VLP: Vision-Language Preference Learning for Embodied Manipulation
Runze Liu, Chenjia Bai, Jiafei Lyu +3
Reward engineering is one of the key challenges in Reinforcement Learning (RL). Preference-based RL effectively addresses this issue by learning from human feedback. However, it is…
Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling
Runze Liu, Junqi Gao, Jian Zhao +5
Test-Time Scaling (TTS) is an important method for improving the performance of Large Language Models (LLMs) by using additional computation during the inference phase. However, cu…
RAT: Adversarial Attacks on Deep Reinforcement Agents for Targeted Behaviors
Fengshuo Bai, Runze Liu, Yali Du +2
Evaluating deep reinforcement learning (DRL) agents against targeted behavior attacks is critical for assessing their robustness. These attacks aim to manipulate the victim into sp…
A Large Language Model-Driven Reward Design Framework via Dynamic Feedback for Reinforcement Learning
Shengjie Sun, Runze Liu, Jiafei Lyu +3
Large Language Models (LLMs) have shown significant potential in designing reward functions for Reinforcement Learning (RL) tasks. However, obtaining high-quality reward code often…
SEABO: A Simple Search-Based Method for Offline Imitation Learning
Jiafei Lyu, Xiaoteng Ma, Le Wan +3
Offline reinforcement learning (RL) has attracted much attention due to its ability in learning from static offline datasets and eliminating the need of interacting with the enviro…
PEARL: Zero-shot Cross-task Preference Alignment and Robust Reward Learning for Robotic Manipulation
Runze Liu, Yali Du, Fengshuo Bai +2
In preference-based Reinforcement Learning (RL), obtaining a large number of preference labels are both time-consuming and costly. Furthermore, the queried human preferences cannot…