1 citations · 2 across the 5 of their papers we have counts for
7 papers
Scheduling Recursive Reasoning in Looped Transformers
Boyuan Wang, Chengyao Yu, Jiaxi Ren +3
Recurrent reasoning models have attracted growing attention for scaling test-time computation, typically by iteratively refining latent states with shared parameters. However, thes…
Harnesses for Inference-Time Alignment over Execution Trajectories
Boyuan Wang, Bochao Li, Minghan Wang +2
Harness engineering has emerged as an important inference-time technique for large language model (LLM) agents, aiming to improve long-term performance through task decomposition a…
Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement Learning
Yun Qu, Yuhang Jiang, Boyuan Wang +4
Reinforcement learning (RL) often encounters delayed and sparse feedback in real-world applications, even with only episodic rewards. Previous approaches have made some progress in…
Predictive Inference With Fast Feature Conformal Prediction
Zihao Tang, Boyuan Wang, Chuan Wen +1
Conformal prediction is widely adopted in uncertainty quantification, due to its post-hoc, distribution-free, and model-agnostic properties. In the realm of modern deep learning, r…
Stop Wandering, Find the Keys: LLMs Discriminate Key States for Efficient Multi-Agent Exploration
Yun Qu, Boyuan Wang, Yuhang Jiang +7
With expansive state-action spaces, efficient multi-agent exploration remains a longstanding challenge in reinforcement learning. Although pursuing novelty, diversity, or uncertain…
Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks
Yun Qu, Boyuan Wang, Jianzhun Shao +15
The advancement of Offline Reinforcement Learning (RL) and Offline Multi-Agent Reinforcement Learning (MARL) critically depends on the availability of high-quality, pre-collected o…
LLM-Empowered State Representation for Reinforcement Learning
Boyuan Wang, Yun Qu, Yuhang Jiang +4
Conventional state representations in reinforcement learning often omit critical task-related details, presenting a significant challenge for value networks in establishing accurat…