Life of Research · open-access repository · LOR-00261
A Refusal Is Not a Veto: Why Multi-Agent Structures Are Reported Both to Amplify and to Contain Language-Model Harm, Which Properties of the Structure Set the Sign, and the Matched Comparison That Would Separate Them
- SONYTECH
Preprint
DOI10.5281/zenodo.24420073 LOR-00261
Permanent link: https://lifeofresearch.com/preprints/261
Abstract
(c) 2026 Pranay Mahendrakar. Licensed under CC BY 4.0.
Life of Research Language models are increasingly composed into systems in which one model plans and others execute, check or debate. Two bodies of work describe the safety consequences in opposite terms. One reports that composition amplifies harm: a model that refuses a hazardous task on its own completes it once the task passes through a delegating principal, a planner or an orchestrator. The other reports that composition contains harm: adding agents that inspect a response or challenge a peer cuts jailbreak success several-fold. In this analysis the author reviews and synthesises published results to show that "multi-agent" is not the variable either literature measured. A reported change bundles at least five properties of the structure: what each model can see of the original intent, what it is told about the authority of the instruction it receives, whether a refusal ends the path or can be routed around, what incentive the prompts add, and whether output becomes an action. Re-reading the anchor study's own tables, the author computes that if delegation merely added a second, independent refusal point, end-to-end full execution would fall below every model's single-agent rate; it rises above it for four of six models, and for two of them more than nine tenths of delegated full execution passed through deliveries the study's own judge classed as sanitized, so on that classification the subordinate did not receive the harmful intent it is said to have obeyed (the study's authors read the same numbers as evidence that sanitization was incomplete). In a computer-use study, a single model given an orchestrator's decomposed subtasks, with no second agent, reproduces most of the orchestrated system's failure, while in a planner-executor study executor compliance is 6.3 percent when the planner refuses and 78.6 percent when it emits steps, against 64.4 percent with no planner. The paper consolidates 24 published results, states an attribution procedure, and specifies the matched comparison that would separate the five properties.
Keywords
Files (1)
Cite this record
Guides How to cite a preprint Preprints vs journal articles What CC BY 4.0 allows