5 papers · 1 filter
State2State: Environment-Derived Mid-Training for LLM Agents
Xuanyu Lei, Yiqi Zhu, Chenliang Li +6
Training LLM agents commonly relies on supervised fine-tuning from expert trajectories or online reinforcement learning over human-specified tasks with handcrafted verifiers. Thoug…
Writing-RL: Advancing Long-form Writing via Adaptive Curriculum Reinforcement Learning
Xuanyu Lei, Chenliang Li, Yuning Wu +7
Recent advances in Large Language Models(LLMs) have enabled strong performance in long-form writing, but current training paradigms remain limited: Supervised Fine-Tuning (SFT) rem…
Scaling External Knowledge Input Beyond Context Windows of LLMs via Multi-Agent Collaboration
Zijun Liu, Zhennan Wan, Peng Li +3
With the rapid advancement of post-training techniques for reasoning and information seeking, large language models (LLMs) can incorporate a large quantity of retrieved knowledge t…
Thinking with Visual Abstract: Enhancing Multimodal Reasoning via Visual Abstraction
Dairu Liu, Ziyue Wang, Minyuan Ruan +4
Images usually convey richer detail than text, but often include redundant information, which potentially downgrades multimodal reasoning performance. When faced with lengthy or co…
Advancing Language Multi-Agent Learning with Credit Re-Assignment for Interactive Environment Generalization
Zhitao He, Zijun Liu, Peng Li +5
LLM-based agents have made significant advancements in interactive environments, such as mobile operations and web browsing, and other domains beyond computer using. Current multi-…