7 papers
Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models
Zihao Wei, Wenjie Shi, Liang Pang +8
Long-form chain-of-thought reasoning can improve LLM performance on complex tasks, but models often continue generating unnecessary reasoning after a correct answer has emerged. We…
Beyond Reasoning: Reinforcement Learning Unlocks Parametric Knowledge in LLMs
Wanli Yang, Hongyu Zang, Junwei Zhang +5
Reinforcement learning (RL) has achieved remarkable success in LLM reasoning, but whether it can also improve direct recall of parametric knowledge remains an open question. We stu…
HeavySkill: Heavy Thinking as the Inner Skill in Agentic Harness
Jianing Wang, Linsen Guo, Zhengyu Chen +8
Recent advances in agentic harness with orchestration frameworks that coordinate multiple agents with memory, skills, and tool use have achieved remarkable success in complex reaso…
DORA: A Scalable Asynchronous Reinforcement Learning System for Language Model Training
Tianhao Hu, Xiangcheng Liu, Yuchun Miao +16
Reinforcement learning (RL) has become a critical paradigm for LLM post-training, yet the rollout phase -- accounting for 50--80% of total step time -- is bottlenecked by skewed ge…
Self-Supervised Discovering of Interpretable Features for Reinforcement Learning
Wenjie Shi, Gao Huang, Shiji Song +3
Deep reinforcement learning (RL) has recently led to many breakthroughs on a range of complex control tasks. However, the agent's decision-making process is generally not transpare…
Multi Pseudo Q-learning Based Deterministic Policy Gradient for Tracking Control of Autonomous Underwater Vehicles
Wenjie Shi, Shiji Song, Cheng Wu +1
This paper investigates trajectory tracking problem for a class of underactuated autonomous underwater vehicles (AUVs) with unknown dynamics and constrained inputs. Different from…