cs.MANov 9, 2026

Unprompted coordination through shared memory in LLM agents: a locked two-implementation replication and extension

Authors: Pekka Abrahamsson, Muhammad Waseem, Esa Karjalainen, Petrus Jussila, Henri Hansen, Jussi Rasku, Bilhanan Silverajan, Kai-Kristian Kemell

Organizations: Tampere University, Finland

Abstract

Coordination between large language-model agents has become a central question for AI safety and software engineering, as such agents are deployed in groups that share infrastructure. Existing research typically tells the agents that partners exist or asks them to coordinate. Whether coordination arises through shared state alone, with nothing disclosing that anyone else is present, is the key question for deployments that share caches and memory between agents, yet it has rarely been examined, and to our knowledge not with independent replication; this study does both. Four agents each received a short arithmetic task and a key-value store presented to each as its own scratch space; two held complementary halves of one computation, and no prompt mentioned other agents, sharing or collaboration. For reliability, the environment was rebuilt independently from a written protocol, and both implementations ran under hashed locks on design, data and analysis. The results bear novelty value in three respects. Joint success occurred only through the shared store. Whether a model coordinated depended not on its vendor tier but on whether it wrote its intermediate result and looked at the store again, and one ordinary sentence, "check your workspace again before submitting", switched that second look on and off. The findings held under replication. For practice, state shared between agents is a communication channel and should be separated, namespaced and logged. For research, designs should be locked before the data, and the parse rule, endpoint and parameters reported. Future work should test open-weight models and separate using another agent's output from intending to communicate.

Figures & tables

Explore similar work

CardsList
  1. Zero-Shot Coordination among LLM Agents

    Nov 4, 2026Adrian Hayler, Shashank Reddy Chirra, Andrei Lupu +4Multi-Agent CoordinationZero-Shot Coordination

  2. From Signals to Structure: How Memory Architecture Drives Language Emergence in LLM Agents

    Jun 30, 2026Yashar Talebirad, Eden Redman, Ali Parsaee +1Multi-Agent LLM SystemsMulti-Agent Coordination

  3. No Attacker Needed: Unintentional Cross-User Contamination in Shared-State LLM Agents

    Apr 1, 2026Tiankai Yang, Jiate Li, Yi Nian +5LLM Agent SecurityLLM Agent Safety