6 papers
CONCAT: Consensus- and Confidence-Driven Ad Hoc Teaming for Efficient LLM-Based Multi-Agent Systems
Ziyang Ma, Dingyi Zhang, Sichu Liang +4
Although large language model (LLM) based multi-agent systems (MAS) show their capability to solve complex tasks and achieve higher performance over single agent systems, they lead…
Can Vision Replace Text in Working Memory? Evidence from Spatial n-Back in Vision-Language Models
Sichu Liang, Hongyu Zhu, Wenwen Wang +1
Working memory is a central component of intelligent behavior, providing a dynamic workspace for maintaining and updating task-relevant information. Recent work has used n-back tas…
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…
Evading Data Provenance in Deep Neural Networks
Hongyu Zhu, Sichu Liang, Wenwen Wang +3
Modern over-parameterized deep models are highly data-dependent, with large scale general-purpose and domain-specific datasets serving as the bedrock for rapid advancements. Howeve…
Revisiting Data Auditing in Large Vision-Language Models
Hongyu Zhu, Sichu Liang, Wenwen Wang +5
With the surge of large language models (LLMs), Large Vision-Language Models (VLMs)--which integrate vision encoders with LLMs for accurate visual grounding--have shown great poten…
RGAR: Recurrence Generation-augmented Retrieval for Factual-aware Medical Question Answering
Sichu Liang, Linhai Zhang, Hongyu Zhu +3
Medical question answering requires extensive access to specialized conceptual knowledge. The current paradigm, Retrieval-Augmented Generation (RAG), acquires expertise medical kno…