collaborators

7 papers

cs.LG2026

Efficient Reinforcement Learning for Long-Horizon Tool-Use Agentic Tasks

Zelei Cheng, Amritansh Mishra, Sambit Sahu +1

Long-horizon tool-using agents must reason over user goals, domain policies, tool calls, simulator state, and delayed verifiable rewards. Reinforcement learning (RL) is a natural f…

cs.CL2026

SEAD: Competence-Aware On-Policy Distillation via Entropy-Guided Supervision

Chia-Hsuan Lee, Zelei Cheng, Yu Wang +4

On-policy distillation (OPD) has a property absent in offline distillation and RL: teacher supervision quality depends on student competence. Incoherent rollouts yield noisy gradie…

cs.AI2026

GPO: Learning from Critical Steps to Improve LLM Reasoning

Jiahao Yu, Zelei Cheng, Xian Wu +1

Large language models (LLMs) are increasingly used in various domains, showing impressive potential on different tasks. Recently, reasoning LLMs have been proposed to improve the \…

cs.CL2026

Decomposing the Delta: What Do Models Actually Learn from Preference Pairs?

Chia-Hsuan Lee, Mingyang Zhou, Renkun Ni +6

Preference optimization methods such as DPO and KTO are widely used for aligning language models, yet little is understood about what properties of preference data drive downstream…

cs.AI2026

Building Coding Agents via Entropy-Enhanced Multi-Turn Preference Optimization

Jiahao Yu, Zelei Cheng, Xian Wu +1

Software engineering presents complex, multi-step challenges for Large Language Models (LLMs), requiring reasoning over large codebases and coordinated tool use. The difficulty of…

cs.CL2025

UC-MOA: Utility-Conditioned Multi-Objective Alignment for Distributional Pareto-Optimality

Zelei Cheng, Xin-Qiang Cai, Yuting Tang +4

Reinforcement Learning from Human Feedback (RLHF) has become a cornerstone for aligning large language models (LLMs) with human values. However, existing approaches struggle to cap…