3 citations · 3 across the 10 of their papers we have counts for
10 papers
When KV Cache Reuse Fails in Multi-Agent Systems: Cross-Candidate Interaction is Crucial for LLM Judges
Sichu Liang, Zhenglin Wang, Jiajia Chu +3
Multi-agent LLM systems routinely generate multiple candidate responses that are aggregated by an LLM judge. To reduce the dominant prefill cost in such pipelines, recent work advo…
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…
Large Language Models Have Intrinsic Meta-Cognition, but Need a Good Lens
Ziyang Ma, Qingyue Yuan, Zhenglin Wang +1
Previous research has primarily focused on the cognitive error detection capabilities of Large Language Models (LLMs), often prompting them to analyze mistakes in reasoning chains.…
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…
Benchmarking Temporal Reasoning and Alignment Across Chinese Dynasties
Zhenglin Wang, Jialong Wu, Pengfei LI +2
Temporal reasoning is fundamental to human cognition and is crucial for various real-world applications. While recent advances in Large Language Models have demonstrated promising…
WebWalker: Benchmarking LLMs in Web Traversal
Jialong Wu, Wenbiao Yin, Yong Jiang +8
Retrieval-augmented generation (RAG) demonstrates remarkable performance across tasks in open-domain question-answering. However, traditional search engines may retrieve shallow co…
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…
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…
Adaptive Prompt Learning with Distilled Connective Knowledge for Implicit Discourse Relation Recognition
Bang Wang, Zhenglin Wang, Wei Xiang +1
Implicit discourse relation recognition (IDRR) aims at recognizing the discourse relation between two text segments without an explicit connective. Recently, the prompt learning ha…