6 papers
DyTopo: Dynamic Topology Routing for Multi-Agent Reasoning via Semantic Matching
Yuxing Lu, Yucheng Hu, Xukai Zhao +1
Multi-agent systems built from prompted large language models can improve multi-round reasoning, yet most existing pipelines rely on fixed, trajectory-wide communication patterns t…
CLM-Bench: Benchmarking and Analyzing Cross-lingual Misalignment of LLMs in Knowledge Editing
Yucheng Hu, Wei Zhou, Juesi Xiao
Knowledge Editing (KE) has emerged as a promising paradigm for updating facts in Large Language Models (LLMs) without retraining. However, progress in Multilingual Knowledge Editin…
Language-Guided Tuning: Enhancing Numeric Optimization with Textual Feedback
Yuxing Lu, Yucheng Hu, Nan Sun +1
Configuration optimization remains a critical bottleneck in machine learning, requiring coordinated tuning across model architecture, training strategy, feature engineering, and hy…
RAG and RAU: A Survey on Retrieval-Augmented Language Model in Natural Language Processing
Yucheng Hu, Yuxing Lu
Large Language Models (LLMs) have catalyzed significant advancements in Natural Language Processing (NLP), yet they encounter challenges such as hallucination and the need for doma…
Rethinking Agent Design: From Top-Down Workflows to Bottom-Up Skill Evolution
Jiawei Du, Jinlong Wu, Yuzheng Chen +3
Most LLM-based agent frameworks adopt a top-down philosophy: humans decompose tasks, define workflows, and assign agents to execute each step. While effective on benchmark-style ta…
AnalyticKWS: Towards Exemplar-Free Analytic Class Incremental Learning for Small-footprint Keyword Spotting
Yang Xiao, Tianyi Peng, Rohan Kumar Das +2
Keyword spotting (KWS) offers a vital mechanism to identify spoken commands in voice-enabled systems, where user demands often shift, requiring models to learn new keywords continu…