6 papers
Teacher-Guided Policy Optimization for On-Policy Reasoning Distillation under Large Policy Divergence
Xinyu Liu, Kechen Jiao, Chunyang Xiao +10
On-policy distillation (OPD) has become a promising paradigm for reasoning-oriented post-training of large language models (LLMs), especially when combined with reinforcement learn…
Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling
Xuehai Bai, Yang Shi, Yi-Fan Zhang +7
Recent image editing models have achieved remarkable progress in instruction following, multimodal understanding, and complex visual editing. However, existing benchmarks often fai…
Offline Two-Player Zero-Sum Markov Games with KL Regularization
Claire Chen, Yuheng Zhang, Xinyu Liu +3
We study the problem of learning Nash equilibria in offline two-player zero-sum Markov games. While existing approaches often rely on explicit pessimism to address distribution shi…
OracleTSC: Oracle-Informed Reward Hurdle and Uncertainty Regularization for Traffic Signal Control
Darryl Jacob, Xinyu Liu, Muchao Ye +2
Transparent decision-making is essential for traffic signal control (TSC) systems to earn public trust. However, traditional reinforcement learning-based TSC methods function as bl…
SAG-Agent: Enabling Long-Horizon Reasoning in Strategy Games via Dynamic Knowledge Graphs
Chenwei Tang, Lin Long, Xinyu Liu +6
Most commodity software lacks accessible Application Programming Interfaces (APIs), requiring autonomous agents to interact solely through pixel-based Graphical User Interfaces (GU…
Rewarding the Journey, Not Just the Destination: A Composite Path and Answer Self-Scoring Reward Mechanism for Test-Time Reinforcement Learning
Jingyu Xing, Chenwei Tang, Xinyu Liu +5
Reinforcement Learning (RL) has emerged as a powerful paradigm for advancing Large Language Models (LLMs), achieving remarkable performance in complex reasoning domains such as mat…