Metraipolis › archive › dc_dadd55ff8a70

Emergence, Not Bandwidth: Physical Coupling and the Limits of Learned Multi-Agent Communication — arXiv:2609.34373

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.34373
License (as archived): CC0-1.0
Archived: 2026-10-07T20:54:18.208Z
SHA-256 of the archived text: c9d5ec78a819567b01ec9b4f9644326fa3ccb3a9d0c769eac31a72df0c5c549a
Stable URL of this page: https://metraipolis.com/documento/dc_dadd55ff8a70

How to cite

Emergence, Not Bandwidth: Physical Coupling and the Limits of Learned Multi-Agent Communication — arXiv:2609.34373 — arXiv (en), https://arxiv.org/abs/2609.34373 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dadd55ff8a70 (Metraipolis archive dc_dadd55ff8a70, sha256 c9d5ec78a819567b01ec9b4f9644326fa3ccb3a9d0c769eac31a72df0c5c549a)

BibTeX

@misc{dcdadd55ff8a70,
  title = {Emergence, Not Bandwidth: Physical Coupling and the Limits of Learned Multi-Agent Communication — arXiv:2609.34373},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34373},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dadd55ff8a70; sha256 c9d5ec78a819567b01ec9b4f9644326fa3ccb3a9d0c769eac31a72df0c5c549a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34373. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Rate-limited multi-agent teams raise three questions the emergent-communication literature has answered only empirically: what an optimal message should encode, what compression costs over a horizon, and when a learned protocol is unique enough for a teammate to read. We answer them for rate-limited Dec-POMDPs, then measure how far reinforcement learning falls short of the optimum. Our theorems fix what is achievable independently of any learner, so a gap between an engineered and a learned sender at the same bit budget is an optimization fact, not an information-theoretic one. We instantiate this on three MuJoCo arenas spanning zero, partial and rigid physical coupling, charging every condition exactly 2 bits per decision, and create the discriminating regime by closing a physical side channel within one arena, holding bodies, task and reward fixed. Communication value is governed by coupling: under rigid coupling through a shared object, no channel beats silence (+0.001 +/- 0.001, p = 0.982, n = 25), since proprioception already carries that information; without coupling, every condition solves the task; under partial coupling, the engineered 2-bit sender reaches an interquartile mean of 1.000 but the learned one reaches 0.482, indistinguishable from silence (p = 0.400, n = 25). With a shared alphabet, bandwidth cannot explain the gap. Warm-starting from an engineered receiver localizes the failure: the same channel reaches 0.857 versus 0.562 cold-started (p < 0.001), so it is neither representational nor one of maintenance; reinforcement learning fails to discover the protocol. Cross-play shows learned protocols are individually meaningful but mutually unintelligible: self-play 0.980 collapses to 0.144 across seeds, and our best constructed alignment leaves at least 77% of that gap. All headline results use 25 seeds per arena and seven published baselines at matched rate.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.MA).
Categorie arXiv: Machine Learning (cs.LG) ; Multiagent Systems (cs.MA); Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.34373 — 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 2026-10-07T20:24:41.727Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).