Metraipolis › archive › dc_cef61391d01b

Real Computation or Merely Naming? A Pre-Registered Mechanism Audit of 25 Cognitive-Architecture Modules in an LLM-Based Agent System — arXiv:2610.41604

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41604
License (as archived): CC0-1.0
Archived: 2026-11-02T07:09:25.985Z
SHA-256 of the archived text: e590191be7ec031941c88f1a808af3059902bf5b9c88079e3a955d946ab23d51
Stable URL of this page: https://metraipolis.com/documento/dc_cef61391d01b

How to cite

Real Computation or Merely Naming? A Pre-Registered Mechanism Audit of 25 Cognitive-Architecture Modules in an LLM-Based Agent System — arXiv:2610.41604 — arXiv (en), https://arxiv.org/abs/2610.41604 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cef61391d01b (Metraipolis archive dc_cef61391d01b, sha256 e590191be7ec031941c88f1a808af3059902bf5b9c88079e3a955d946ab23d51)

BibTeX

@misc{dccef61391d01b,
  title = {Real Computation or Merely Naming? A Pre-Registered Mechanism Audit of 25 Cognitive-Architecture Modules in an LLM-Based Agent System — arXiv:2610.41604},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41604},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cef61391d01b; sha256 e590191be7ec031941c88f1a808af3059902bf5b9c88079e3a955d946ab23d51},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41604. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Agent systems built on local large language models are increasingly marketed through the vocabulary of cognitive architecture: modules named global workspace, theory of mind, causal reasoning, or active inference are listed as features, and the presence of the name is taken as the presence of the mechanism. We ask the prior question -- does the named computation actually happen -- and contribute a transferable verification method for the claim-implementation gap: a four-question static audit protocol with line-number evidence and call-chain tracing, demonstrated on two systems. We audit a system claiming 25 cognitive mechanisms, pre-register falsifiable predictions for 11 modules and execute the interventions, replicate the protocol on the IIT-phi core of a second, independent system with its own pre-committed falsification criteria, and run two repair experiments as positive controls. In 18 of 25 modules the computed value never reaches any production output; three idle-wiring shapes new to the dead-code and code-smell literatures emerge (connected-but-never-called, called-but-inert, called-but-content-blind). Of 61 frozen criteria across 12 interventions, 53 were confirmed, two partially adjudicated, five falsified, one adjudication-ambiguous. Repairs raised planner task success from 0.028 to 1.000 and cut state-controller error by 52%. Module names and module computations must be audited as independent claims; the protocol and the five-class failure taxonomy are reusable for the claim-implementation gap at two-system, case-level depth.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.41604 — 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 2026-11-02T07:06:59.347Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).