English

Four-Axis Decision Alignment for Long-Horizon Enterprise AI Agents

Artificial Intelligence 2026-04-22 v1

Abstract

Long-horizon enterprise agents make high-stakes decisions (loan underwriting, claims adjudication, clinical review, prior authorization) under lossy memory, multi-step reasoning, and binding regulatory constraints. Current evaluation reports a single task-success scalar that conflates distinct failure modes and hides whether an agent is aligned with the standards its deployment environment requires. We propose that long-horizon decision behavior decomposes into four orthogonal alignment axes, each independently measurable and failable: factual precision (FRP), reasoning coherence (RCS), compliance reconstruction (CRR), and calibrated abstention (CAR). CRR is a novel regulatory-grounded axis; CAR is a measurement axis separating coverage from accuracy. We exercise the decomposition on a controlled benchmark (LongHorizon-Bench) covering loan qualification and insurance claims adjudication with deterministic ground-truth construction. Running six memory architectures, we find structure aggregate accuracy cannot see: retrieval collapses on factual precision; schema-anchored architectures pay a scaffolding tax; plain summarization under a fact-preservation prompt is a strong baseline on FRP, RCS, EDA, and CRR; and all six architectures commit on every case, exposing a decisional-alignment axis the field has not targeted. The decomposition also surfaced a pre-registered prediction of our own, that summarization would fail factual recall, which the data reversed at large magnitude, an axis-level reversal aggregate accuracy would have hidden. Institutional alignment (regulatory reconstruction) and decisional alignment (calibrated abstention) are under-represented in the alignment literature and become load-bearing once decisions leave the laboratory. The framework transfers to any regulated decisioning domain via two steps: build a fact schema, and calibrate the CRR auditor prompt.

Keywords

Cite

@article{arxiv.2604.19457,
  title  = {Four-Axis Decision Alignment for Long-Horizon Enterprise AI Agents},
  author = {Vasundra Srininvasan},
  journal= {arXiv preprint arXiv:2604.19457},
  year   = {2026}
}

Comments

21 pages, 5 figures, 8 tables. PDFLaTeX. Code and artifacts: https://github.com/vasundras/decision-alignment-long-horizon-agents

R2 v1 2026-07-01T12:28:21.550Z