Misleading the Planner through Deceptive Resumes: Registration-Time Injection in Centralized Multi-Agent Systems

arXiv:2609.15516 · cs.CR · Submitted 2026-09-14 · Read on arXiv

cs.CR

Submitted: 2026-09-14

Updated: 2026-09-14

Comments: 18 pages, 11 figures, including appendices

Code: https://github.com/microsoft/autogen

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Grounding — 24× in this paper · explained in 3 episodes
• Transformer — 19× in this paper · explained in 2 episodes
• Task Decomposition — 18× in this paper · explained in 2 episodes
• Verification — 16× in this paper · explained in 2 episodes
• Multi-Agent System — 10× in this paper · explained in 5 episodes
• Steering — 8× in this paper · explained in 2 episodes
• Benchmark — 6× in this paper · explained in 2 episodes
• Agentic System — 4× in this paper · explained in 2 episodes
• Abstraction — 3× in this paper · explained in 1 episode
• Consistency — 3× in this paper · explained in 3 episodes
• Agent Mismatch Rate — 2× in this paper
• Agentic AI — 2× in this paper · explained in 1 episode
• Analyzer — 2× in this paper · explained in 1 episode
• Dedicated Verification Task Ratio — 2× in this paper
• Excessive Effort Rate — 2× in this paper
• LLM-as-a-Judge — 2× in this paper · explained in 3 episodes
• Missing Intermediate Result Ratio — 2× in this paper
• Multi-agent Collaboration — 2× in this paper · explained in 2 episodes
• Multi-agent system (MAS) — 2× in this paper · explained in 2 episodes
• RAG — 2× in this paper · explained in 3 episodes
• Vagueness Concretization Ratio — 2× in this paper
• Verification Intent Rate — 2× in this paper
• AI Agents — 1× in this paper · explained in 2 episodes
• Adaptive Planning — 1× in this paper · explained in 1 episode
• Agent Participation Rate — 1× in this paper
• Agentic AI systems — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• Multi-agent Collaborative Framework — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Transformer Architecture — 1× in this paper · explained in 2 episodes

Sources

• Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks
• IsolateGPT: An Execution Isolation Architecture for LLM-Based Agentic Systems
• AttriGuard: Defeating Indirect Prompt Injection in LLM Agents via Causal Attribution of Tool Invocations
• Overcoming the Retrieval Barrier: Indirect Prompt Injection in the Wild for LLM Systems
• Towards a Science of Scaling Agent Systems

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs