Beyond Single-Agent Safety: A Taxonomy of Risks in LLM-to-LLM Interactions

This paper examines why safety mechanisms designed for human-model interaction do not scale to environments where large language models (LLMs) interact with each other. Most current governance practices still rely on single-agent safety containment, prompts, fine-tuning, and moderation layers that constrain individual model behavior but leave the dynamics of multi-model interaction ungoverned. These mechanisms assume a dyadic setting: one model responding to one user under stable oversight. Yet research and industrial development are rapidly shifting toward LLM-to-LLM ecosystems, where outputs are recursively reused as inputs across chains of agents. In such systems, local compliance can aggregate into collective failure even when every model is individually aligned. We propose a conceptual transition from model-level safety to system-level safety, introducing the framework of the Emergent Systemic Risk Horizon (ESRH) to formalize how instability arises from interaction structure rather than from isolated misbehavior. The paper contributes (i) a theoretical account of collective risk in interacting LLMs, (ii) a taxonomy connecting micro, meso, and macro-level failure modes, and (iii) a design proposal for InstitutionalAI, an architecture for embedding adaptive oversight within multi-agent systems.

Paper

References (14)

09Petri: An open-source auditing framework for AI systems2025 · Anthropic
10Inspect AI: Framework for Large Language Model Evaluations2025
11Han, Hughes, E.2025 · arXiv preprint arXiv
12CAMEL: Communicative agents for "mind" exploration of large language models2023 · Advances in Neural Information Processing Systems

Scroll for more · 2 remaining

Similar papers

© 2026 NYSGPT2525 LLC