Large language model (LLM)-based multi-agent systems increasingly rely on intermediate communication to coordinate complex tasks. While most existing systems communicate through natural language, recent work shows that latent communication, particularly through transformer key-value (KV) caches, can improve efficiency and preserve richer task-relevant information. However, KV caches also encode contextual inputs, intermediate reasoning states, and agent-specific information, creating an opaque channel through which sensitive content may propagate across agents without explicit textual disclosure. To address this, we introduce \textbf{LCGuard} (Latent Communication Guard), a framework for safe KV-based latent communication in multi-agent LLM systems. LCGuard treats shared KV caches as latent working memory and learns representation-level transformations before cache artifacts are transmitted across agents. We formalize representation-level sensitive information leakage operationally through reconstruction: a shared cache artifact is unsafe if an adversarial decoder can recover agent-specific sensitive inputs from it. This leads to an adversarial training formulation in which the adversary learns to reconstruct sensitive inputs, while LCGuard learns transformations that preserve task-relevant semantics and reduce reconstructable information. Empirical evaluations across multiple model families and multi-agent benchmarks show that LCGuard consistently reduces reconstruction-based leakage and attack success rates while maintaining competitive task performance compared to standard KV-sharing baselines.
SafeCoEvo: Co-Evolving Safety Harnesses and Guards for LLM Agents at Test-Time
East China Normal University(华东师范大学);Shanghai Innovation Institute(上海创新研究院);Xiamen University(厦门大学);Harbin Institute of Technology(哈尔滨工业大学);University College London(伦敦大学学院);Huawei Noah’s Ark Lab, UK(华为诺亚方舟实验室(英国));MemoraX AI
StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Balancing
Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Beihang University(北京航空航天大学);Fudan University(复旦大学);Renmin University of China(中国人民大学);KAUST(阿卜杜拉国王科技大学)
HazardAuditor: From Executable Threats to Safer Computer-Use Agents
Ant Group(蚂蚁集团);Zhejiang University(浙江大学);Fudan University(复旦大学);Hunan Institute of Advanced Technology(湖南先进技术研究院);Shanghai Innovation Institute(上海创新研究院);Deakin University(迪肯大学)
GuardianBench: A Same-Scene Instruction-Contrastive Benchmark for Latent Contextual Risk in Embodied AI
Shandong University(山东大学);National University of Singapore(新加坡国立大学);Nanjing University of Aeronautics and Astronautics(南京航空航天大学);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Xiaomi Corporation(小米公司)