Metraipolis › archive › dc_ffda0de116e7

Unprompted coordination through shared memory in LLM agents: a locked two-implementation replication and extension — arXiv:2611.12412

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.12412
License (as archived)
CC0-1.0
Archived
2026-11-10T18:40:13.228Z
SHA-256 of the archived text
8c7599f7b5e3166c271f5d919f05749af3cd74a00247acabbf3587730c4da150
Stable URL of this page
https://metraipolis.com/documento/dc_ffda0de116e7

How to cite

Unprompted coordination through shared memory in LLM agents: a locked two-implementation replication and extension — arXiv:2611.12412 — arXiv (en), https://arxiv.org/abs/2611.12412 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ffda0de116e7 (Metraipolis archive dc_ffda0de116e7, sha256 8c7599f7b5e3166c271f5d919f05749af3cd74a00247acabbf3587730c4da150)
BibTeX
@misc{dcffda0de116e7,
  title = {Unprompted coordination through shared memory in LLM agents: a locked two-implementation replication and extension — arXiv:2611.12412},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.12412},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ffda0de116e7; sha256 8c7599f7b5e3166c271f5d919f05749af3cd74a00247acabbf3587730c4da150},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.12412. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 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 never 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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Multiagent Systems (cs.MA) ; Computation and Language (cs.CL); Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2611.12412 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-10T18:37:22.456Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).