collaborators

10 papers

cs.LG2026

EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents

Xuying Ning, Dongqi Fu, Tianxin Wei +13

Long-horizon LLM agents increasingly rely on external execution support to maintain state, track progress, invoke tools, verify outcomes, and reuse experience across interactions.…

cs.CL2026

SAGE-OPD: Selective Agent-Guided Intervention for Multi-Turn On-Policy Distillation

Yuhang Zhou, Lizhu Zhang, Yifan Wu +5

On-policy distillation (OPD) improves student models by training them on trajectories induced by their own policy, making it a promising approach for mitigating exposure bias in ag…

cs.LG2026

OmniOPD: Logit-Free On-Policy Distillation via Speculative Verification

Yuhang Zhou, Lizhu Zhang, Yifan Wu +5

On-Policy Distillation (OPD) trains a student model on its own generative trajectories under dense token-level feedback from a stronger teacher, mitigating both the off-policy dist…

cs.AI2026

DAG-MoE: From Simple Mixture to Structural Aggregation in Mixture-of-Experts

Jiarui Feng, Hanqing Zeng, Karish Grover +11

Mixture-of-Experts (MoE) models have become a leading approach for decoupling parameter count from computational cost in large language models, yet effectively scaling MoE performa…

cs.IR2026

Toward User Preference Alignment in LLM Recommendation via Explicit Context Feedback

Weizhi Zhang, Wooseong Yang, Yuxin Cui +9

Traditional recommender systems (RecSys) primarily infer user preferences from implicit signals (such as clicks, watches, and purchases), often neglecting the rich explicit context…

cs.CL2026

Generating Leakage-Free Benchmarks for Robust RAG Evaluation

Jiayi Liu, Jiaxing Zhang, Bowen Jin +1

Retrieval-augmented generation (RAG) is widely used to augment large language models (LLMs) with external knowledge. However, many benchmark datasets, designed to test RAG performa…