mlsanityData to 14 Oct 2026

TRACE: A Metrologically-Grounded Engineering Framework for Trustworthy Agentic AI Systems in Operationally Critical Domains

arXiv 2605.03838 ↗First posted 5 May 2026cs.CL cs.AI cs.HCcited by 1

On the map: LLM agents and tool use → Agent threats, guardrails and governance

Abstract (arXiv)

We introduce TRACE, a cross-domain engineering framework for trustworthy agentic AI in operationally critical domains. TRACE combines a four-layer reference architecture with an explicit classical-ML vs. LLM-validator split (L2a/L2b), a stateful orchestration-and-escalation policy (L3), and bounded human supervision (L4); a metrologically grounded trust-metric suite mapped to GUM/VIM/ISO 17025; and a Model-Parsimony principle quantified by the Computational Parsimony Ratio (CPR). Three instantiations--clinical decision support, industrial multi-domain operations, and a judicial AI assistant--transfer the samearchitecture and metrics across principally different governance contexts. The L2a/L2b separation makes the use of large language models a deliberate design decision rather than an architectural default, with parsimony quantified through CPR. TRACE introduces CPR as a first-class design principle in trustworthy-AI engineering.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 12 of its 33 references that are in the map. First posted on arXiv 5 May 2026.

Builds on

12 of 33 references.

References · 12

  1. 2017On Calibration of Modern Neural Networkscited by 4,960
  2. 2019Green AIcited by 627
  3. 2025Small Language Models are the Future of Agentic AIcited by 270
  4. 2024Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Toolscited by 176
  5. 2021Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Bettercited by 154
  6. 2023FUTURE-AI: International consensus guideline for trustworthy and deployable artificial intelligence in healthcarecited by 60
  7. 2021Reliability Assessment and Safety Arguments for Machine Learning Components in System Assurancecited by 16
  8. 2025Tiered Agentic Oversight: A Hierarchical Multi-Agent System for Healthcare Safetycited by 8
  9. 2025A Framework for Responsible AI Systems: Building Societal Trust through Domain Definition, Trustworthy AI Design, Auditability, Accountability, and Governancecited by 5
  10. 2024Trustworthy Artificial Intelligence in the Context of Metrologycited by 4
  11. 2025A metrological framework for uncertainty evaluation in machine learning classification modelscited by 4
  12. 2026From Black-Box Confidence to Measurable Trust in Clinical AI: A Framework for Evidence, Supervision, and Staged Autonomycited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Trust Is Not a Score: Runtime Assurance Contracts for High-Risk AI Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Engineering Trustworthy Agentic AI for Critical Systems
  2. 2026Beyond Benchmark Islands: Toward Representative Trustworthiness Evaluation for Agentic AI
  3. 2026Trustworthy Agentic AI: A Comprehensive Cybersecurity and Systems Survey on Threat Landscapes, Defense Architectures, and Open Challenges
  4. 2026Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security
  5. 2026A Unified Evaluation Framework for Trustworthy Large Language Models, Agentic AI, and Multimodal Systems
  6. 2025Trustworthy Orchestration Artificial Intelligence by the Ten Criteria with Control-Plane Governance
  7. 2026Trustworthy AI Software Engineers
  8. 2025From Cloud-Native to Trust-Native: A Protocol for Verifiable Multi-Agent Systems