3 citations · 4 across the 8 of their papers we have counts for
9 papers
Reason--Imagine--Act: Closed-Loop LLM Decision Making with World Models for Autonomous Driving
Zhengqi Sun, Yiwen Sun, Boxuan Liu +3
Large language models (LLMs) are promising for autonomous driving, but semantics-only decision policies can yield physically unsafe behavior in dynamic traffic. Existing methods ei…
Adaptive Value Decomposition: Coordinating a Varying Number of Agents in Urban Systems
Yexin Li, Jinjin Guo, Haoyu Zhang +3
Multi-agent reinforcement learning (MARL) provides a promising paradigm for coordinating multi-agent systems (MAS). However, most existing methods rely on restrictive assumptions,…
AutoPBO: LLM-powered Optimization for Local Search PBO Solvers
Jinyuan Li, Yi Chu, Yiwen Sun +2
Pseudo-Boolean Optimization (PBO) provides a powerful framework for modeling combinatorial problems through pseudo-Boolean (PB) constraints. Local search solvers have shown excelle…
Discovering heuristics in a complex SAT solver with large language models
Yiwen Sun, Furong Ye, Zhihan Chen +2
The Satisfiability problem (SAT) is fundamental in computational complexity theory and has a wide range of industrial applications. Optimizing modern SAT solvers in real-world sett…
Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization
Jiacai Liu, Chaojie Wang, Chris Yuhao Liu +5
The role of reinforcement learning (RL) in enhancing the reasoning of large language models (LLMs) is becoming increasingly significant. Despite the success of RL in many scenarios…
OpenTensor: Reproducing Faster Matrix Multiplication Discovering Algorithms
Yiwen Sun, Wenye Li
OpenTensor is a reproduction of AlphaTensor, which discovered a new algorithm that outperforms the state-of-the-art methods for matrix multiplication by Deep Reinforcement Learning…
AutoSAT: Automatically Optimize SAT Solvers via Large Language Models
Yiwen Sun, Furong Ye, Xianyin Zhang +4
Conflict-Driven Clause Learning (CDCL) is the mainstream framework for solving the Satisfiability problem (SAT), and CDCL solvers typically rely on various heuristics, which have a…
OpenRL: A Unified Reinforcement Learning Framework
Shiyu Huang, Wentse Chen, Yiwen Sun +2
We present OpenRL, an advanced reinforcement learning (RL) framework designed to accommodate a diverse array of tasks, from single-agent challenges to complex multi-agent systems.…
Learning Graph-Enhanced Commander-Executor for Multi-Agent Navigation
Xinyi Yang, Shiyu Huang, Yiwen Sun +5
This paper investigates the multi-agent navigation problem, which requires multiple agents to reach the target goals in a limited time. Multi-agent reinforcement learning (MARL) ha…