paper-with-me

Papers

Governed Reasoning for Institutional AI

2026-04-12 · Mamadou Seck arxiv

Institutional decisions -- regulatory compliance, clinical triage, prior authorization appeal -- require a different AI architecture than general-purpose agents provide. Agent frameworks infer authority conversationally, reconstruct accountability from logs, and produce silent errors: incorrect determinations that execute without any human review signal. We propose Cognitive Core: a governed decision substrate built from nine typed cognitive primitives (retrieve, classify, investigate, verify, challenge, reflect, deliberate, govern, generate), a four-tier governance model where human review is a condition of execution rather than a post-hoc check, a tamper-evident SHA-256 hash-chain audit ledger endogenous to computation, and a demand-driven delegation architecture supporting both declared and autonomously reasoned epistemic sequences. We benchmark three systems on an 11-case balanced prior authorization appeal evaluation set. Cognitive Core achieves 91% accuracy against 55% (ReAct) and 45% (Plan-and-Solve). The governance result is more significant: CC produced zero silent errors while both baselines produced 5-6. We introduce governability -- how reliably a system knows when it should not act autonomously -- as a primary evaluation axis for institutional AI alongside accuracy. The baselines are implemented as prompts, representing the realistic deployment alternative to a governed framework. A configuration-driven domain model means deploying a new institutional decision domain requires YAML configuration, not engineering capacity.

📄 PDF Abstract BibTeX arXiv:2604.10658

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

GRACE-RAG: Governed Retrieval Architecture for Canonical Evidence Synthesis, Enabling Lightweight Deployment in Closed-Domain Institutional Settings

2026-05-08 · Asit Desai, Aman Kumar, Prashant Devadiga arxiv

Retrieval-Augmented Generation (RAG) systems are widely used in institutional question answering settings where responses must be grounded in authoritative documentation (Gao et al., 2023). In entity-dense domains where …

Question Answering

Governing Actions, Not Agents: Institutional Attestation as a Governance Model for Autonomous AI Systems

2026-06-24 · Jakob Salfeld-Nebgen arxiv

Autonomous AI agents may begin to perform consequential, irreversible actions such as clinical prescribing and production software deployment. This paper observes that human institutions have governed powerful autonomous…

Correct Is Not Governed: Provenance Integrity in Agentic Workflows

2026-08-13 · Jesus Salas arxiv

Agentic workflows are commonly evaluated by whether they reach the correct outcome. That is insufficient in institutional settings, where a correct action may rely on the wrong authority, an unsupported completion claim,…

Do Large Language Models Encode Institutional Experience? Evidence from Cross-Linguistic Moral Reasoning Under Ambiguity

2026-05-29 · Nattavudh Powdthavee arxiv

Large language models (LLMs) exhibit systematic differences in moral reasoning across languages, yet the source of this variation remains unclear. We test the hypothesis that languages encode aspects of the institutional…

Making it normal for new enrollments: Effect of institutional and pandemic influence on selecting an engineering institution under the COVID-19 pandemic situation

2021-03-23 · Prashant Mahajan, Vaishali Patil

The COVID19 pandemic has forced Indian engineering institutions (EIs) to bring their previous half shut shades completely down. Fetching new admissions to EI campuses during the pandemic has become a now or never situati…