7 papers
Towards Cost-effective LLMs Routing with Batch Prompting
Haotian Xu, Kangfei Zhao, Jiadong Xie
Large Language Model (LLM) serving systems must balance task performance against monetary cost. Two prominent optimization techniques have emerged independently: LLM routing, which…
Argus: Evidence Assembly for Scalable Deep Research Agents
Zhen Zhang, Liangcai Su, Zhuo Chen +7
Deep research agents have achieved remarkable progress on complex information seeking tasks. Even long ReAct style rollouts explore only a single trajectory, while recent state of…
VideoTIR: Accurate Understanding for Long Videos with Efficient Tool-Integrated Reasoning
Zhe Gao, Shiyu Shen, Taifeng Chai +7
Existing Multimodal Large Language Models (MLLMs) often suffer from hallucinations in long video understanding (LVU), primarily due to the imbalance between textual and visual toke…
Reinforcing Structured Chain-of-Thought for Video Understanding
Peiyao Wang, Haotian Xu, Noranart Vesdapunt +6
Multi-modal Large Language Models (MLLMs) show promise in video understanding. However, their reasoning often suffers from thinking drift and weak temporal comprehension, even when…
GEM: A Gym for Agentic LLMs
Zichen Liu, Anya Sims, Keyu Duan +16
The training paradigm for large language models (LLMs) is moving from static datasets to experience-based learning, where agents acquire skills via interacting with complex environ…
REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization
Jian Hu, Jason Klein Liu, Haotian Xu +1
Reinforcement Learning from Human Feedback~(RLHF) plays a crucial role in aligning Large Language Models~(LLMs). The dominant algorithm, Proximal Policy Optimization~(PPO), employs…