Malicious agents can deceive LLM-based task routers in Internet of Agents systems by generating fake skill descriptions, achieving up to 98% success rate across nine domains.
Tool-to-agent retrieval: Bridging tools and agents for scalable llm multi-agent systems
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Goal clarifications lose nearly all value after 10% of execution while input clarifications retain value until roughly 50%, and asking any type past mid-trajectory hurts performance more than never asking.
GRAIL achieves over 79 times lower latency than LLM-parsing baselines and higher Recall@10 than vector search by combining SLM-enhanced prediction, pseudo-document expansion, and MaxSim resonance on the new AgentTaxo-9K dataset of 9,240 agents.
citing papers explorer
-
Skill Description Deception Attack against Task Routing in Internet of Agents
Malicious agents can deceive LLM-based task routers in Internet of Agents systems by generating fake skill descriptions, achieving up to 98% success rate across nine domains.