8 papers
SheetMind: An End-to-End LLM-Powered Multi-Agent Framework for Spreadsheet Automation
Xi Cheng, Ruiyan Zhu, Ke Liu +8
SheetMind is a modular multi‑agent framework that uses large language models to translate natural‑language instructions into spreadsheet actions, employing manager, action, and ref…
Adaptive Reinforcement for Open-ended Medical Reasoning via Semantic-Guided Reward Collapse Mitigation
Yizhou Liu, Dingkang Yang, Zizhi Chen +5
Reinforcement learning (RL) with rule-based reward functions has recently shown great promise in enhancing the reasoning depth and generalization ability of vision-language models…
Improving Multimodal Sentiment Analysis via Modality Optimization and Dynamic Primary Modality Selection
Dingkang Yang, Mingcheng Li, Xuecheng Wu +5
Multimodal Sentiment Analysis (MSA) aims to predict sentiment from language, acoustic, and visual data in videos. However, imbalanced unimodal performance often leads to suboptimal…
TeachPro: Multi-Label Qualitative Teaching Evaluation via Cross-View Graph Synergy and Semantic Anchored Evidence Encoding
Xiangqian Wang, Yifan Jia, Yang Xiang +3
Standardized Student Evaluation of Teaching often suffer from low reliability, restricted response options, and response distortion. Existing machine learning methods that mine ope…
Resolving Evidence Sparsity: Agentic Context Engineering for Long-Document Understanding
Keliang Liu, Zizhi Chen, Mingcheng Li +3
Document understanding is a long standing practical task. Vision Language Models (VLMs) have gradually become a primary approach in this domain, demonstrating effective performance…
Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle
Keliang Liu, Dingkang Yang, Ziyun Qian +7
In recent years, training methods centered on Reinforcement Learning (RL) have markedly enhanced the reasoning and alignment performance of Large Language Models (LLMs), particular…