5 papers
TTHE: Test-Time Harness Evolution
Jun Nie, Yonggang Zhang, Jun Song +5
The behavior of an LLM agent is determined not only by the underlying model, but also by its harness: the executable program that constructs context, invokes tools, verifies interm…
RewardFlow: Topology-Aware Reward Propagation on State Graphs for Agentic RL with Large Language Models
Xiao Feng, Bo Han, Zhanke Zhou +5
Reinforcement learning (RL) shows promise for enhancing LLM agentic reasoning, yet sparse terminal rewards hinder fine-grained optimization. Process reward modeling offers an alter…
TVWorld: Foundations for Remote-Control TV Agents
Zhantao Ma, Quanfeng Lu, Shuai Zhong +3
Recent large vision-language models (LVLMs) have demonstrated strong potential for device control. However, existing research has primarily focused on point-and-click (PnC) interac…
SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control
Quanfeng Lu, Zhantao Ma, Shuai Zhong +4
The rapid advancement of large vision language models (LVLMs) and agent systems has heightened interest in mobile GUI agents that can reliably translate natural language into inter…
Using In-Context Learning for Automatic Defect Labelling of Display Manufacturing Data
Babar Hussain, Qiang Liu, Gang Chen +2
This paper presents an AI-assisted auto-labeling system for display panel defect detection that leverages in-context learning capabilities. We adopt and enhance the SegGPT architec…