5 papers
SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems
Haowen Dai, Zonghao Ying, Wenfeng Li +10
Multi-agent systems improve capability through task decomposition and role specialization, but these same mechanisms introduce an important safety blind spot: a harmful objective c…
JADE: Expert-Grounded Dynamic Evaluation for Open-Ended Professional Tasks
Lanbo Lin, Jiayao Liu, Tianyuan Yang +5
JADE is a two‑layer evaluation system that encodes expert knowledge as predefined evaluation skills and adds claim‑level, evidence‑gated assessment to more reliably evaluate AI age…
Out of Sight, Not Out of Mind: Unveiling Latent Attack in Latent-based Multi-Agent Systems
Chenxi Wang, Ruiyang Huang, Jiayan Sun +2
Latent-based multi-agent systems replace parts of explicit inter-agent communication with hidden representations, offering a new direction for efficient and flexible agent collabor…
FadeMem: Biologically-Inspired Forgetting for Efficient Agent Memory
Lei Wei, Xiao Peng, Xu Dong +2
Large language models deployed as autonomous agents face critical memory limitations, lacking selective forgetting mechanisms that lead to either catastrophic forgetting at context…
Think-Augmented Function Calling: Improving LLM Parameter Accuracy Through Embedded Reasoning
Lei Wei, Xiao Peng, Jinpeng Ou +1
Large language models (LLMs) have demonstrated remarkable capabilities in function calling for autonomous agents, yet current mechanisms lack explicit reasoning transparency during…