collaborators

8 papers

cs.LG2026

Less Noise, More Voice: Reinforcement Learning for Reasoning via Instruction Purification

Yiju Guo, Tianyi Hu, Zexu Sun +1

Reinforcement Learning with Verifiable Rewards (RLVR) has advanced LLM reasoning, but remains constrained by inefficient exploration under limited rollout budgets, leading to low s…

cs.LG2026

CurES: From Gradient Analysis to Efficient Curriculum Learning for Reasoning LLMs

Yongcheng Zeng, Zexu Sun, Bokai Ji +7

Curriculum learning plays a crucial role in enhancing the training efficiency of large language models (LLMs) on reasoning tasks. However, existing methods often fail to adequately…

cs.LG2026

Solving the Granularity Mismatch: Hierarchical Preference Learning for Long-Horizon LLM Agents

Heyang Gao, Zexu Sun, Erxue Min +4

Large Language Models (LLMs) as autonomous agents are increasingly tasked with solving complex, long-horizon problems. Aligning these agents via preference-based offline methods li…

cs.CL2026

Prompt and Parameter Co-Optimization for Large Language Models

Xiaohe Bo, Rui Li, Zexu Sun +5

Prompt optimization and fine-tuning are two major approaches to improve the performance of Large Language Models (LLMs). They enhance the capabilities of LLMs from complementary pe…

cs.CL2026

AgentSkiller: Scaling Generalist Agent Intelligence through Semantically Integrated Cross-Domain Data Synthesis

Zexu Sun, Bokai Ji, Hengyi Cai +4

Large Language Model agents demonstrate potential in solving real-world problems via tools, yet generalist intelligence is bottlenecked by scarce high-quality, long-horizon data. E…

cs.CL2025

Evolving LLMs' Self-Refinement Capability via Synergistic Training-Inference Optimization

Yongcheng Zeng, Xinyu Cui, Xuanfa Jin +11

Self-Refinement refers to a model's ability to revise its own responses to produce improved outputs. This capability can also serve as a fundamental mechanism for Self-Improvement,…