papers

Publications (43)

cs.AI2026

AlphaOPT: Formulating Optimization Programs with Self-Improving LLM Experience Library

Minwei Kong, Ao Qu, Xiaotong Guo +12

Optimization modeling underlies critical decision-making across industries, yet remains difficult to automate: natural-language problem descriptions must be translated into precise…

cs.LG2025

Probing Neural Combinatorial Optimization Models

Zhiqin Zhang, Yining Ma, Zhiguang Cao +1

Neural combinatorial optimization (NCO) has achieved remarkable performance, yet its learned model representations and decision rationale remain a black box. This impedes both acad…

cs.LG2022

Fault-Tolerant Federated Reinforcement Learning with Theoretical Guarantee

Flint Xiaofeng Fan, Yining Ma, Zhongxiang Dai +3

The growing literature of Federated Learning (FL) has recently inspired Federated Reinforcement Learning (FRL) to encourage multiple agents to federatively build a better decision-…

cs.AI2024

Large Language Model with Graph Convolution for Recommendation

Yingpeng Du, Ziyan Wang, Zhu Sun +6

In recent years, efforts have been made to use text information for better user profiling and item characterization in recommendations. However, text information can sometimes be o…

cs.LG2023

Neural Multi-Objective Combinatorial Optimization with Diversity Enhancement

Jinbiao Chen, Zizhen Zhang, Zhiguang Cao +4

Most of existing neural methods for multi-objective combinatorial optimization (MOCO) problems solely rely on decomposition, which often leads to repetitive solutions for the respe…

cs.LG2026

Internalizing Curriculum Judgment for LLM Reinforcement Fine-Tuning

Han Zheng, Yining Ma, Karthick Gunasekaran +4

In LLM Reinforcement Fine-Tuning (RFT), curriculum learning drives both efficiency and performance. Yet, current methods externalize curriculum judgment via handcrafted heuristics…

cs.LG2023

MetaBox: A Benchmark Platform for Meta-Black-Box Optimization with Reinforcement Learning

Zeyuan Ma, Hongshu Guo, Jiacheng Chen +5

Recently, Meta-Black-Box Optimization with Reinforcement Learning (MetaBBO-RL) has showcased the power of leveraging RL at the meta-level to mitigate manual fine-tuning of low-leve…

eess.SY2023

Evolving Testing Scenario Generation Method and Intelligence Evaluation Framework for Automated Vehicles

Yining Ma, Wei Jiang, Lingtong Zhang +5

Interaction between the background vehicles (BVs) and automated vehicles (AVs) in scenario-based testing plays a critical role in evaluating the intelligence of the AVs. Current te…

cs.LG2025

Diversity Optimization for Travelling Salesman Problem via Deep Reinforcement Learning

Qi Li, Zhiguang Cao, Yining Ma +2

Existing neural methods for the Travelling Salesman Problem (TSP) mostly aim at finding a single optimal solution. To discover diverse yet high-quality solutions for Multi-Solution…

cs.LG2023

Learning to Search Feasible and Infeasible Regions of Routing Problems with Flexible Neural k-Opt

Yining Ma, Zhiguang Cao, Yeow Meng Chee

In this paper, we present Neural k-Opt (NeuOpt), a novel learning-to-search (L2S) solver for routing problems. It learns to perform flexible k-opt exchanges based on a tailored act…

cs.AI2026

Learning-guided Prioritized Planning for Lifelong Multi-Agent Path Finding in Warehouse Automation

Han Zheng, Yining Ma, Brandon Araki +2

Lifelong Multi-Agent Path Finding (MAPF) is critical for modern warehouse automation, which requires multiple robots to continuously navigate conflict-free paths to optimize the ov…

cs.LG2023

FedHQL: Federated Heterogeneous Q-Learning

Flint Xiaofeng Fan, Yining Ma, Zhongxiang Dai +3

Federated Reinforcement Learning (FedRL) encourages distributed agents to learn collectively from each other's experience to improve their performance without exchanging their raw…

cs.NE2026

Beyond Static Priors: Dynamic Neural Guidance for Large-Scale Ant Colony Optimization

Dat Thanh Tran, Van Khu Vu, Yining Ma

Neural-guided Ant Colony Optimization (ACO) suffers from a fundamental training-inference misalignment: policies are typically trained to generate static priors (e.g., heatmaps), y…

cs.AI2026

Rethinking Positional Encoding for Neural Vehicle Routing

Chuanbo Hua, Federico Berto, Andre Hottung +8

Transformer-based models have become the dominant paradigm for neural combinatorial optimization (NCO) of vehicle routing problems (VRPs), yet the role of positional encoding (PE)…

cs.LG2025

DesignX: Human-Competitive Algorithm Designer for Black-Box Optimization

Hongshu Guo, Zeyuan Ma, Yining Ma +3

Designing effective black-box optimizers is hampered by limited problem-specific knowledge and manual control that spans months for almost every detail. In this paper, we present \…

cs.NI2025

CICV5G: A 5G Communication Delay Dataset for PnC in Cloud-based Intelligent Connected Vehicles

Xinrui Zhang, Peizhi Zhang, Junpeng Huang +4

Cloud-based intelligent connected vehicles (CICVs) leverage cloud computing and vehicle-to-everything (V2X) to enable efficient information exchange and cooperative control. Howeve…

cs.MA2024

Enhancing the Performance of Multi-Vehicle Navigation in Unstructured Environments using Hard Sample Mining

Yining Ma, Ang Li, Qadeer Khan +1

Contemporary research in autonomous driving has demonstrated tremendous potential in emulating the traits of human driving. However, they primarily cater to areas with well built r…

cs.AI2026

Towards Efficient Constraint Handling in Neural Solvers for Routing Problems

Jieyi Bi, Zhiguang Cao, Jianan Zhou +5

Neural solvers have achieved impressive progress in addressing simple routing problems, particularly excelling in computational efficiency. However, their advantages under complex…

cs.AI2024

Learning to Handle Complex Constraints for Vehicle Routing Problems

Jieyi Bi, Yining Ma, Jianan Zhou +4

Vehicle Routing Problems (VRPs) can model many real-world scenarios and often involve complex constraints. While recent neural methods excel in constructing solutions based on feas…

cs.LG2024

Hierarchical Neural Constructive Solver for Real-world TSP Scenarios

Yong Liang Goh, Zhiguang Cao, Yining Ma +3

Existing neural constructive solvers for routing problems have predominantly employed transformer architectures, conceptualizing the route construction as a set-to-sequence learnin…

cs.LG2025

Learning to Segment for Vehicle Routing Problems

Wenbin Ouyang, Sirui Li, Yining Ma +1

Iterative heuristics are widely recognized as state-of-the-art for Vehicle Routing Problems (VRPs). In this work, we exploit a critical observation: a large portion of the solution…

math.OC2025

Learning-Guided Rolling Horizon Optimization for Long-Horizon Flexible Job-Shop Scheduling

Sirui Li, Wenbin Ouyang, Yining Ma +1

Long-horizon combinatorial optimization problems (COPs), such as the Flexible Job-Shop Scheduling Problem (FJSP), often involve complex, interdependent decisions over extended time…

cs.LG2023

Learning Generalizable Models for Vehicle Routing Problems via Knowledge Distillation

Jieyi Bi, Yining Ma, Jiahai Wang +4

Recent neural methods for vehicle routing problems always train and test the deep models on the same instance distribution (i.e., uniform). To tackle the consequent cross-distribut…

cs.NE2024

Deep Reinforcement Learning for Dynamic Algorithm Selection: A Proof-of-Principle Study on Differential Evolution

Hongshu Guo, Yining Ma, Zeyuan Ma +5

Evolutionary algorithms, such as Differential Evolution, excel in solving real-parameter optimization challenges. However, the effectiveness of a single algorithm varies across dif…

cs.AI2024

MVMoE: Multi-Task Vehicle Routing Solver with Mixture-of-Experts

Jianan Zhou, Zhiguang Cao, Yaoxin Wu +4

Learning to solve vehicle routing problems (VRPs) has garnered much attention. However, most neural solvers are only structured and trained independently on a specific problem, mak…

cs.LG2024

Symbol: Generating Flexible Black-Box Optimizers through Symbolic Equation Learning

Jiacheng Chen, Zeyuan Ma, Hongshu Guo +3

Recent Meta-learning for Black-Box Optimization (MetaBBO) methods harness neural networks to meta-learn configurations of traditional black-box optimizers. Despite their success, t…

cs.LG2022

Learning to Iteratively Solve Routing Problems with Dual-Aspect Collaborative Transformer

Yining Ma, Jingwen Li, Zhiguang Cao +4

Recently, Transformer has become a prevailing deep architecture for solving vehicle routing problems (VRPs). However, it is less effective in learning improvement models for VRP be…

cs.NE2024

Auto-configuring Exploration-Exploitation Tradeoff in Evolutionary Computation via Deep Reinforcement Learning

Zeyuan Ma, Jiacheng Chen, Hongshu Guo +2

Evolutionary computation (EC) algorithms, renowned as powerful black-box optimizers, leverage a group of individuals to cooperatively search for the optimum. The exploration-exploi…

math.OC2024

LLaMoCo: Instruction Tuning of Large Language Models for Optimization Code Generation

Zeyuan Ma, Hongshu Guo, Jiacheng Chen +4

Recent research explores optimization using large language models (LLMs) by either iteratively seeking next-step solutions from LLMs or directly prompting LLMs for an optimizer. Ho…

cs.AI2026

Interpreting Neural Combinatorial Optimization via Evolving Programmatic Bottlenecks

Haocheng Duan, Yuxin Guo, Jieyi Bi +4

Neural Combinatorial Optimization (NCO) achieves strong performance, yet its black-box nature remains a key roadblock to deployment and scientific diagnosis. Standard interpretabil…

cs.LG2026

RADAR: Learning to Route with Asymmetry-aware DistAnce Representations

Hang Yi, Ziwei Huang, Yining Ma +1

Recent neural solvers have achieved strong performance on vehicle routing problems (VRPs), yet they mainly assume symmetric Euclidean distances, restricting applicability to real-w…

cs.MA2025

MA-DV2F: A Multi-Agent Navigation Framework using Dynamic Velocity Vector Field

Yining Ma, Qadeer Khan, Daniel Cremers

In this paper we propose MA-DV2F: Multi-Agent Dynamic Velocity Vector Field. It is a framework for simultaneously controlling a group of vehicles in challenging environments. DV2F…

cs.RO2025

Real-world Troublemaker: A 5G Cloud-controlled Track Testing Framework for Automated Driving Systems in Safety-critical Interaction Scenarios

Xinrui Zhang, Lu Xiong, Peizhi Zhang +2

Track testing plays a critical role in the safety evaluation of autonomous driving systems (ADS), as it provides a real-world interaction environment. However, the inflexibility in…

cs.LG2025

RL4CO: an Extensive Reinforcement Learning for Combinatorial Optimization Benchmark

Federico Berto, Chuanbo Hua, Junyoung Park +30

Combinatorial optimization (CO) is fundamental to several real-world applications, from logistics and scheduling to hardware design and resource allocation. Deep reinforcement lear…

cs.LG2024

ConfigX: Modular Configuration for Evolutionary Algorithms via Multitask Reinforcement Learning

Hongshu Guo, Zeyuan Ma, Jiacheng Chen +4

Recent advances in Meta-learning for Black-Box Optimization (MetaBBO) have shown the potential of using neural networks to dynamically configure evolutionary algorithms (EAs), enha…

cs.LG2022

Efficient Neural Neighborhood Search for Pickup and Delivery Problems

Yining Ma, Jingwen Li, Zhiguang Cao +4

We present an efficient Neural Neighborhood Search (N2S) approach for pickup and delivery problems (PDPs). In specific, we design a powerful Synthesis Attention that allows the van…

cs.RO2023

Multi Agent Navigation in Unconstrained Environments using a Centralized Attention based Graphical Neural Network Controller

Yining Ma, Qadeer Khan, Daniel Cremers

In this work, we propose a learning based neural model that provides both the longitudinal and lateral control commands to simultaneously navigate multiple vehicles. The goal is to…

cs.AI2025

SHIELD: Multi-task Multi-distribution Vehicle Routing Solver with Sparsity and Hierarchy

Yong Liang Goh, Zhiguang Cao, Yining Ma +3

Recent advances toward foundation models for routing problems have shown great potential of a unified deep model for various VRP variants. However, they overlook the complex real-w…

cs.AI2026

ToolAnchor: Anchoring Counterfactual Context to Boost Agentic Tool-use Capability

Weiting Liu, Jieyi Bi, Wanqi Zhou +4

The paper introduces ToolAnchor, a method that injects counterfactual contexts to help large language model agents overcome reliance on familiar tools and adapt to new toolsets wit…

#tool-augmented language models#counterfactual reasoning#agent adaptation#reinforcement learning
cs.AI2024

Decision-making with Speculative Opponent Models

Jing Sun, Shuo Chen, Cong Zhang +2

Opponent modelling has proven effective in enhancing the decision-making of the controlled agent by constructing models of opponent agents. However, existing methods often rely on…

cs.LG2025

MetaBox-v2: A Unified Benchmark Platform for Meta-Black-Box Optimization

Zeyuan Ma, Yue-Jiao Gong, Hongshu Guo +11

Meta-Black-Box Optimization (MetaBBO) streamlines the automation of optimization algorithm design through meta-learning. It typically employs a bi-level structure: the meta-level p…

cs.AI2026

A General Neural Backbone for Mixed-Integer Linear Optimization via Dual Attention

Peixin Huang, Yaoxin Wu, Yining Ma +3

Mixed-integer linear programming (MILP) is a foundational framework for combinatorial optimization across science and engineering, but remains hard to solve at scale due to NP-hard…

cs.LG2022

Deep Reinforcement Learning for Solving the Heterogeneous Capacitated Vehicle Routing Problem

Jingwen Li, Yining Ma, Ruize Gao +4

Existing deep reinforcement learning (DRL) based methods for solving the capacitated vehicle routing problem (CVRP) intrinsically cope with homogeneous vehicle fleet, in which the…