{
  "abstract": "The security of multi-turn autonomous agent architectures is fundamentally compromised by context-steering vulnerabilities, specifically Salami attacks, where adversarial intent is incrementally dispersed across sequential interaction turns. Conventional probabilistic filters and static language guardrails fail under such trajectory-based manipulation due to the lack of dynamic state memory and the presence of model-vs-payload space mismatch.\n\nTo resolve this challenge at its mathematical core, we formulate multi-turn intent containment as a data-driven, state-space control problem governed by Unfalsified Control Theory and Koopman Operator dynamics. By lifting discrete token interaction streams into an infinite-dimensional Hilbert space, the nonlinear evolution of multi-turn dialogue trajectories is linearized into observable subspace projections. We define a dual-subspace energy framework that continuously evaluates the instantaneous directional momentum of user intent relative to an immutable, zero-calibration energy density hyperplane boundary.\n\nTo eliminate subspace saturation and contextual information decay during extended multi-turn sessions, we introduce a session-isolated adaptive dual-loop learner augmented with a sliding-window forgetting operator. This mechanism guarantees bounded memory dissipation while preserving short-term intent trajectory momentum. Upon falsification—defined strictly by a negative Lyapunov-like energy density derivative—the system executes an immediate, deterministic state-transition into a closed-loop containment sandbox, accompanied by a zero-remanence memory sanitization protocol that destroys volatile trajectory information.\n\nBy operating entirely as a deterministic, Python-native linear algebra transformation, the proposed architecture provides mathematically guaranteed, real-time intent containment for both digital API gateways and physical kinetic actuator interfaces without reliance on offline retraining, empirical threshold tuning, or hyperparameter optimization.",
  "abstract_shown": true,
  "affiliations": [
    "Bangsaen AI Labs"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 1,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Tanet Wonghong",
      "orcid": "0000-0003-1590-2915"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/d200nmy12b3ev.bib",
  "cited_by": 0,
  "doi": "10.5281/zenodo.23555956",
  "fulltext_url": null,
  "id": "d200nmy12b3ev",
  "issns": [],
  "landing_url": "https://zenodo.org/records/23555956",
  "language": "eng",
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [],
  "openalex": null,
  "pdf_url": "https://zenodo.org/api/records/23555956/files/Journal%202026.pdf/content",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-22",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/d200nmy12b3ev.ris",
  "sources": [
    {
      "first_seen": "2026-11-05T12:20:15Z",
      "native_id": "23555956",
      "source": "zenodo",
      "url": "https://zenodo.org/records/23555956"
    }
  ],
  "subjects": [],
  "title": "Session-Isolated Unfalsified Adaptive Control for Multi-Turn Intent Containment in Autonomous Agent Architectures",
  "title_text": "Session-Isolated Unfalsified Adaptive Control for Multi-Turn Intent Containment in Autonomous Agent Architectures",
  "type": "preprint",
  "updated_at": "2026-11-05T12:20:15Z",
  "url": "https://research.draconitic.com/paper/d200nmy12b3ev",
  "venue": "Zenodo",
  "versions": []
}