SwarmSafe-Delta：隔离消息传递对 LLM 智能体安全的影响

View PDF HTML (experimental)

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 $N=4$ 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.

Comments:	10 pages, 3 figures, 3 tables
Subjects:	Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI)
Cite as:	arXiv:2611.16123 [cs.MA]
	(or arXiv:2611.16123v1 [cs.MA] for this version)
	https://doi.org/10.48550/arXiv.2611.16123 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Junru Zhu [view email]
[v1] Thu, 12 Nov 2026 00:17:32 UTC (944 KB)