18 citations · 45 across the 14 of their papers we have counts for
14 papers
SiriusDeliver: Automating Data Warehouse Delivery at Tencent
Haining Xie, Xiaokai Zhou, Jiaming Yang +12
Enterprise data warehouses (DWs) support business-critical analytics, but warehouse task delivery remains a complicated production process involving context retrieval, workflow con…
Not All Problems Are Best Modeled as MILP: A DSL-Centric Framework for Flexible and Accurate Optimization Modeling
Shaofeng Zhang, Hongyuan Su, Qingwen Peng +4
Solving combinatorial optimization problems (COPs) requires not only efficient algorithms but also carefully crafted formulations. While recent works have leveraged LLMs to automat…
DataClawEval: A Benchmark for Data Engineering Agents in Real Industrial Harness
Debin Meng, Jiaming Yang, Zefang Zong +4
Large language models (LLMs) and LLM-based agents are increasingly being deployed to automate complex workflows, promising to revolutionize data management and processing. However,…
ATOD: Annealed Turn-Aware On-Policy Distillation for Multi-Turn Agentic Tasks
Qitai Tan, Zefang Zong, Mo Li +3
Training small language-model agents for long-horizon interactive tasks requires both fast imitation and reward-driven improvement. On-policy distillation (OPD) provides dense teac…
Efficient Agentic Reinforcement Learning with On-Policy Intrinsic Knowledge Boundary Enhancement
Dingwei Chen, Zefang Zong, Zhipeng Ma +5
Agentic reinforcement learning (RL) has proven effective for training LLM-based agents with external tool-use capabilities. However, we identify that agentic RL training induces in…
ATGPO: Agentic Turn-Group Policy Optimization with Adaptive Turn-level Clipping
Dingwei Chen, Zefang Zong, Zhipeng Ma +5
Reinforcement learning for agentic large language models (LLMs) typically relies on a sparse, trajectory-level outcome reward, making it difficult to evaluate the contribution of i…
ATPO: Agentic Turn-based Policy Optimization via Tree Search
Zefang Zong, Dingwei Chen, Yang Li +6
LLM agents have emerged as powerful systems for tackling multi-turn tasks by interleaving internal reasoning and external tool interactions. Agentic Reinforcement Learning has rece…
UniCO: Towards a Unified Model for Combinatorial Optimization Problems
Zefang Zong, Xiaochen Wei, Guozhen Zhang +3
Combinatorial Optimization (CO) encompasses a wide range of problems that arise in many real-world scenarios. While significant progress has been made in developing learning-based…
Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models
Fengli Xu, Qianyue Hao, Zefang Zong +17
Language has long been conceived as an essential tool for human reasoning. The breakthrough of Large Language Models (LLMs) has sparked significant research interest in leveraging…
Understanding World or Predicting Future? A Comprehensive Survey of World Models
Jingtao Ding, Yunke Zhang, Yu Shang +12
The concept of world models has garnered significant attention due to advancements in multimodal large language models such as GPT-4 and video generation models such as Sora, which…
Deep Reinforcement Learning for Demand Driven Services in Logistics and Transportation Systems: A Survey
Zefang Zong, Jingwei Wang, Tao Feng +3
Recent technology development brings the boom of numerous new Demand-Driven Services (DDS) into urban lives, including ridesharing, on-demand delivery, express systems and warehous…
Reinforced Epidemic Control: Saving Both Lives and Economy
Sirui Song, Zefang Zong, Yong Li +2
Saving lives or economy is a dilemma for epidemic control in most cities while smart-tracing technology raises people's privacy concerns. In this paper, we propose a solution for t…
DeepDPM: Dynamic Population Mapping via Deep Neural Network
Zefang Zong, Jie Feng, Kechun Liu +2
Dynamic high resolution data on human population distribution is of great importance for a wide spectrum of activities and real-life applications, but is too difficult and expensiv…
Multi-Channel Auto-Encoder for Speech Emotion Recognition
Zefang Zong, Hao Li, Qi Wang
Inferring emotion status from users' queries plays an important role to enhance the capacity in voice dialogues applications. Even though several related works obtained satisfactor…