5 papers
M: Dual-Memory Augmentation for Long-Horizon Web Agents via Trajectory Summarization and Insight Retrieval
Dawei Yan, Haokui Zhang, Guangda Huzhang +8
Multimodal Large Language Models (MLLMs) based agents have demonstrated remarkable potential in autonomous web navigation. However, handling long-horizon tasks remains a critical b…
Building Autonomous GUI Navigation via Agentic-Q Estimation and Step-Wise Policy Optimization
Yibo Wang, Guangda Huzhang, Yuwei Hu +7
Recent advances in Multimodal Large Language Models (MLLMs) have substantially driven the progress of autonomous agents for Graphical User Interface (GUI). Nevertheless, in real-wo…
Optimal Transport-Based Token Weighting scheme for Enhanced Preference Optimization
Meng Li, Guangda Huzhang, Haibo Zhang +2
Direct Preference Optimization (DPO) has emerged as a promising framework for aligning Large Language Models (LLMs) with human preferences by directly optimizing the log-likelihood…
Establishing Reliability Metrics for Reward Models in Large Language Models
Yizhou Chen, Yawen Liu, Xuesi Wang +5
The reward model (RM) that represents human preferences plays a crucial role in optimizing the outputs of large language models (LLMs), e.g., through reinforcement learning from hu…
Residual Multi-Task Learner for Applied Ranking
Cong Fu, Kun Wang, Jiahua Wu +5
Modern e-commerce platforms rely heavily on modeling diverse user feedback to provide personalized services. Consequently, multi-task learning has become an integral part of their…