12 papers
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…
MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding
Fuwen Luo, Shengfeng Lou, Chi Chen +9
Video temporal understanding is crucial for multimodal large language models (MLLMs) to reason over events in videos. Despite recent advances in general video understanding, curren…
Browse and Concentrate: Comprehending Multimodal Content via prior-LLM Context Fusion
Ziyue Wang, Chi Chen, Yiqi Zhu +7
With the bloom of Large Language Models (LLMs), Multimodal Large Language Models (MLLMs) that incorporate LLMs with pre-trained vision models have recently demonstrated impressive…
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-…