cs.MANov 12, 2026

SwarmSafe-Delta: Isolating Message Effects on LLM Agent Safety

Authors: Junru Zhu

Organizations: Independent Researcher, United States

Abstract

When a tool-using LLM agent team violates policy, aggregate outcomes do not reveal whether an upstream message changed the executor's action. We introduce SwarmSafe-Delta, a paired executable protocol that freezes upstream computation, varies real, hidden, and format-matched placebo delivery, and scores a single committed action against deterministic benign and risky policy states under preassigned budgets. Across four models and constructed optional tasks, real delivery at N=4N=4 produces 21.4% risky-world violations, versus 5.0% with placebo and 1.0% with hidden delivery (paired differences +16.4 and +20.3 percentage points). Real delivery also improves benign task success, illustrating that suppressing communication sacrifices utility. In a second regime constructed to require an upstream lookup route, real delivery improves safe completion by 74.2 points relative to hidden delivery. These effects quantify message-delivery contrasts under specified information dependencies, not naturally occurring failure rates. Exploratory action-level analyses show that the effect depends strongly on whether the upstream message recommends a prerequisite check or direct execution; model differences also largely track these message compositions. The contribution is a controlled, execution-grounded measurement protocol rather than a general claim that agent communication is harmful or protective.

Figures & tables

Explore similar work

CardsList
  1. Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents

    Jul 31, 2026Minghui Pan, Jiayuxuan Yang, Yuanyuan Yuan +2LLM GuardrailsPrompt Injection Attacks on AI Agents

  2. Position: A Three-Layer Probabilistic Assume-Guarantee Architecture Is Structurally Required for Safe LLM Agent Deployment

    May 18, 2026S. Bensalem, Y. Dong, M. Franzle +6AI Agent ReliabilityLLM Guardrails

  3. Environment Steering: Using Data Flow Control to Improve Agent Utility and Safety

    Sep 19, 2026Charlie Summers, Prajwal Raghunath, Aaditya Pai +4AI Agent SecurityLLM Agent Safety