Multi-LLM Systems Exhibit Robust Semantic Collapse

arXiv:2605.17193 · cs.MA, cs.AI, cs.CL · Submitted 2026-05-16 · Read on arXiv

cs.MA, cs.AI, cs.CL

Submitted: 2026-05-16

Updated: 2026-10-14

Comments: 94 pages, 12 figures, 13 tables; includes Supplementary Information

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

Terminology

• Conformity — 1× in this paper · explained in 2 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes

Related papers

• Highway Congestion Reduction through Reinforcement Learning Based Eulerian Headway Control
• Auditable and Deployable Multi-Agent Motion Planning via Posetal Games from Legal Guidelines
• ORACLE-SWE: Quantifying the Contribution of Critical Information Signals on SWE Agents
• You Only Align Once: Propagating Cooperative Behaviors in Multi-Agent Systems through Seed Agents
• Deny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent Systems
• MA-SAPO: Multi-Agent Reasoning for Score-Aware Prompt Optimization