7 papers
When Does a Video-Language Model Stop Watching? Reward Strength Controls the Formation and Reversal of Visual Shortcuts in Multimodal RLVR
Zekun Xu
Reinforcement learning with verifiable rewards (RLVR) is increasingly applied to large vision-language models (LVLMs), yet outcome-only optimization can drive a model to stop atten…
Training Multi-Image Vision Agents via End2End Reinforcement Learning
Chengqi Dong, Chuhuai Yue, Hang He +7
Recent VLM-based agents aim to replicate OpenAI O3's "thinking with images" via tool use, yet most open-source methods restrict inputs to a single image, limiting their applicabili…
From Experience to Strategy: Empowering LLM Agents with Trainable Graph Memory
Siyu Xia, Zekun Xu, Jiajun Chai +7
Large Language Models (LLMs) based agents have demonstrated remarkable potential in autonomous task-solving across complex, open-ended environments. A promising approach for improv…
MTIR-SQL: Multi-turn Tool-Integrated Reasoning Reinforcement Learning for Text-to-SQL
Zekun Xu, Siyu Xia, Chuhuai Yue +6
As large language models (LLMs) are increasingly used in Text-to-SQL tasks, Reinforcement Learning (RL) has become a common method for improving performance. Existing methods prima…
AutoPrune: Each Complexity Deserves a Pruning Policy
Hanshi Wang, Yuhao Xu, Zekun Xu +5
The established redundancy in visual tokens within large vision-language models allows pruning to effectively reduce their substantial computational demands. Previous methods typic…
RLFactory: A Plug-and-Play Reinforcement Learning Post-Training Framework for LLM Multi-Turn Tool-Use
Jiajun Chai, Guojun Yin, Zekun Xu +9
Large language models excel at basic reasoning but struggle with tasks that require interaction with external tools. We present RLFactory, a plug-and-play reinforcement learning po…