Paper

{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.06394v1</id>\n    <title>Talk Freely, Execute Strictly: Schema-Gated Agentic AI for Flexible and Reproducible Scientific Workflows</title>\n    <updated>2026-03-06T15:40:39Z</updated>\n    <link href='https://arxiv.org/abs/2603.06394v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.06394v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Large language models (LLMs) can now translate a researcher's plain-language goal into executable computation, yet scientific workflows demand determinism, provenance, and governance that are difficult to guarantee when an LLM decides what runs. Semi-structured interviews with 18 experts across 10 industrial R&amp;D stakeholders surface 2 competing requirements--deterministic, constrained execution and conversational flexibility without workflow rigidity--together with boundary properties (human-in-the-loop control and transparency) that any resolution must satisfy. We propose schema-gated orchestration as the resolving principle: the schema becomes a mandatory execution boundary at the composed-workflow level, so that nothing runs unless the complete action--including cross-step dependencies--validates against a machine-checkable specification.\n  We operationalize the 2 requirements as execution determinism (ED) and conversational flexibility (CF), and use these axes to review 20 systems spanning 5 architectural groups along a validation-scope spectrum. Scores are assigned via a multi-model protocol--15 independent sessions across 3 LLM families--yielding substantial-to-near-perfect inter-model agreement (Krippendorff a=0.80 for ED and a=0.98 for CF), demonstrating that multi-model LLM scoring can serve as a reusable alternative to human expert panels for architectural assessment.\n  The resulting landscape reveals an empirical Pareto front--no reviewed system achieves both high flexibility and high determinism--but a convergence zone emerges between the generative and workflow-centric extremes. We argue that a schema-gated architecture, separating conversational from execution authority, is positioned to decouple this trade-off, and distill 3 operational principles--clarification-before-execution, constrained plan-act orchestration, and tool-to-workflow-level gating--to guide adoption.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.MA'/>\n    <published>2026-03-06T15:40:39Z</published>\n    <arxiv:primary_category term='cs.AI'/>\n    <author>\n      <name>Joel Strickland</name>\n    </author>\n    <author>\n      <name>Arjun Vijeta</name>\n    </author>\n    <author>\n      <name>Chris Moores</name>\n    </author>\n    <author>\n      <name>Oliwia Bodek</name>\n    </author>\n    <author>\n      <name>Bogdan Nenchev</name>\n    </author>\n    <author>\n      <name>Thomas Whitehead</name>\n    </author>\n    <author>\n      <name>Charles Phillips</name>\n    </author>\n    <author>\n      <name>Karl Tassenberg</name>\n    </author>\n    <author>\n      <name>Gareth Conduit</name>\n    </author>\n    <author>\n      <name>Ben Pellegrini</name>\n    </author>\n  </entry>"
}