7 papers
CRMWeaver: Building Powerful Business Agent via Agentic RL and Shared Memories
Yilong Lai, Yipin Yang, Ting Liang +4
Recent years have witnessed the rapid development of LLM-based agents, which shed light on using language agents to solve complex real-world problems. A prominent application lies…
VReST: Enhancing Reasoning in Large Vision-Language Models through Tree Search and Self-Reward Mechanism
Congzhi Zhang, Jiawei Peng, Zhenglin Wang +5
Large Vision-Language Models (LVLMs) have shown exceptional performance in multimodal tasks, but their effectiveness in complex visual reasoning is still constrained, especially wh…
AdaRewriter: Unleashing the Power of Prompting-based Conversational Query Reformulation via Test-Time Adaptation
Yilong Lai, Jialong Wu, Zhenglin Wang +1
Prompting-based conversational query reformulation has emerged as a powerful approach for conversational search, refining ambiguous user queries into standalone search queries. Bes…
SCOPE: Optimizing Key-Value Cache Compression in Long-context Generation
Jialong Wu, Zhenglin Wang, Linhai Zhang +3
Key-Value (KV) cache has become a bottleneck of LLMs for long-context generation. Despite the numerous efforts in this area, the optimization for the decoding phase is generally ig…
AdaCQR: Enhancing Query Reformulation for Conversational Search via Sparse and Dense Retrieval Alignment
Yilong Lai, Jialong Wu, Congzhi Zhang +2
Conversational Query Reformulation (CQR) has significantly advanced in addressing the challenges of conversational search, particularly those stemming from the latent user intent a…
SEED: Accelerating Reasoning Tree Construction via Scheduled Speculative Decoding
Zhenglin Wang, Jialong Wu, Yilong Lai +2
Large Language Models (LLMs) demonstrate remarkable emergent abilities across various tasks, yet fall short of complex reasoning and planning tasks. The tree-search-based reasoning…
Large, Small or Both: A Novel Data Augmentation Framework Based on Language Models for Debiasing Opinion Summarization
Yanyue Zhang, Pengfei Li, Yilong Lai +2
As more than 70 of reviews in the existing opinion summary data set are positive, current opinion summarization approaches are reluctant to generate negative summaries given th…