3 papers
cs.AI2026
Repair or Resample? Rethinking Failure Debugging in LLM Multi-Agent Systems
Zhongwen Luan, Xiaoyu Zhang, Ming Hu +3
As large language model (LLM)-based multi-agent systems (MASs) are increasingly applied to long-horizon complex tasks, their reliability has emerged as the core bottleneck hinderin…
cs.MA2026
CoWeaver: A Bi-directional, Learnable and Explainable Matching Engine for Mixed Human-Agent Science Collaboration
Jiayao Gu, Kexin Chu, Peidong Liu +5
LLM-based agents excel at writing articles, coding and information retrieval. However, they fail to form strong collaborations within the scientific community due to the bidirectio…
cs.AI2025
PD: A Project Duplication Detection Framework via Adapted Multi-Agent Debate
Dezheng Bao, Yueci Yang, Chutian Yu +9
Project duplication detection is critical for project quality assessment because it helps avoid investment in repeated proposals. Existing methods usually cast it as ranking and re…