collaborators

12 papers

cs.LG2026

PBSD: Privileged Bayesian Self-Distillation for Long-Horizon Credit Assignment

Yang Tian, Rui Wang, Xumeng Wen +5

Long-horizon agentic tasks pose a fundamental credit assignment challenge for outcome-base reinforcement learning: trajectory-level rewards verify final correctness but provide lim…

cs.LG2026

Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic-Procedural Memory

Sijia Li, Yuchen Huang, Zifan Liu +6

As intents unfold and environments change, multi-turn agents face continuously shifting decision contexts. Although reusing past experience is intuitively appealing, existing appro…

cs.LG2026

MedFeat: Model-Aware and Explainability-Driven Feature Engineering with LLMs for Clinical Tabular Prediction

Zizheng Zhang, Yiming Li, Justin Xu +6

In clinical tabular prediction, classical machine learning models with feature engineering often outperform neural methods. LLMs are increasingly used to automate this process, act…

cs.LG2026

GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation

Sijia Li, Yuchen Huang, Zifan Liu +7

Reinforcement learning has become a widely used post-training approach for LLM agents, where training commonly relies on outcome-level rewards that provide only coarse supervision.…

cs.RO2026

What to Ignore, What to React: Visually Robust RL Fine-Tuning of VLA Models

Yuanfang Peng, Jingjing Fu, Chuheng Zhang +6

Reinforcement learning (RL) fine-tuning has shown promise for Vision-Language-Action (VLA) models in robotic manipulation, but deployment-time visual shifts pose practical challeng…

cs.RO2026

Towards Backdoor-Based Ownership Verification for Vision-Language-Action Models

Ming Sun, Rui Wang, Xingrui Yu +5

Vision-Language-Action models (VLAs) support generalist robotic control by enabling end-to-end decision policies directly from multi-modal inputs. As trained VLAs are increasingly…