14 papers
DataPraxis: Scaling Analytics Tasks via Verified Workspace Evolution
Nan Jia, Wenxuan Shi, Jingqing Ruan +11
General-purpose agents are increasingly expected to perform professional analytics work, which requires sustained reasoning, iterative investigation, and reliable evidence. Trainin…
Data World: Scaling Data Environments from Scratch
Zhanli Li, Zeyuan Xu, Chaoxu Pang +16
Data agents use code to process heterogeneous files and derive analytical insights. Scaling their training faces costly environment curation, privacy and intellectual-property rest…
DivOPD: Spread Wide, Look Close for Asynchronous On-Policy Distillation of Multi-turn Agents
Hanyang Wang, Zeyuan Liu, Zhengyu Chen +7
On-policy distillation (OPD) trains student agents through teacher supervision on their own interactions with an environment. However, in asynchronous multi-turn training, arrival-…
SCOPE: Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adaptive Weighting
Binbin Zheng, Xing Ma, Yiheng Liang +6
On-policy reinforcement learning has become the dominant paradigm for reasoning alignment in large language models, yet its sparse, outcome-level rewards make token-level credit as…
Memory-Augmented LLM-based Multi-Agent System for Automated Feature Generation on Tabular Data
Fengxian Dong, Zhi Zheng, Xiao Han +5
Automated feature generation extracts informative features from raw tabular data without manual intervention and is crucial for accurate, generalizable machine learning. Traditiona…
Harmonizing Dense and Sparse Signals in Multi-turn RL: Dual-Horizon Credit Assignment for Industrial Sales Agents
Haojin Yang, Ai Jian, Xinyue Huang +5
Optimizing large language models for industrial sales requires balancing long-term commercial objectives (e.g., conversion rate) with immediate linguistic constraints such as fluen…
TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemas
Ai Jian, Xiaoyun Zhang, Eryu Guo +6
Text-to-SQL parsing has achieved remarkable progress under the Full Schema Assumption. However, this premise fails in real-world enterprise environments where databases contain hun…
PaTaRM: Bridging Pairwise and Pointwise Signals via Preference-Aware Task-Adaptive Reward Modeling
Ai Jian, Jingqing Ruan, Xing Ma +5
Reward models (RMs) are central to reinforcement learning from human feedback (RLHF), providing the critical supervision signals that align large language models (LLMs) with human…
Higher Satisfaction, Lower Cost: A Technical Report on How LLMs Revolutionize Meituan's Intelligent Interaction Systems
Xuxin Cheng, Ke Zeng, Zhiquan Cao +65
Enhancing customer experience is essential for business success, particularly as service demands grow in scale and complexity. Generative artificial intelligence and Large Language…
Revisiting Entropy Regularization: Adaptive Coefficient Unlocks Its Potential for LLM Reinforcement Learning
Xiaoyun Zhang, Xiaojian Yuan, Di Huang +6
Reasoning ability has become a defining capability of Large Language Models (LLMs), with Reinforcement Learning with Verifiable Rewards (RLVR) emerging as a key paradigm to enhance…
Reasoner for Real-World Event Detection: Scaling Reinforcement Learning via Adaptive Perplexity-Aware Sampling Strategy
Xiaoyun Zhang, Jingqing Ruan, Xing Ma +4
Detecting abnormal events in real-world customer service dialogues is highly challenging due to the complexity of business data and the dynamic nature of customer interactions. Mor…
AMoPO: Adaptive Multi-objective Preference Optimization without Reward Models and Reference Models
Qi Liu, Jingqing Ruan, Hao Li +7
Existing multi-objective preference alignment methods for large language models (LLMs) face limitations: (1) the inability to effectively balance various preference dimensions, and…
When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning
Xiaoyun Zhang, Jingqing Ruan, Xing Ma +6
Large reasoning models (LRMs) achieve remarkable performance via long reasoning chains, but often incur excessive computational overhead due to redundant reasoning, especially on s…
Hummer: Towards Limited Competitive Preference Dataset
Li Jiang, Yusen Wu, Junwu Xiong +6
Preference datasets are essential for incorporating human preferences into pre-trained language models, playing a key role in the success of Reinforcement Learning from Human Feedb…