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

• URL: http://arxiv.org/abs/2604.19457v1
• Date: Tue, 21 Apr 2026 13:37:19 GMT
• Title: Four-Axis Decision Alignment for Long-Horizon Enterprise AI Agents
• Abstract summary: Long-horizon enterprise agents make high-stakes decisions under lossy memory, multi-step reasoning, and binding regulatory constraints.<n>We propose that long-horizon decision behavior decomposes into four axes, each independently measurable and failable.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• 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.

Related papers

• Revelation Control [0.0]
  Revelation Control is the problem of choosing priced interventions that reveal hidden state only insofar as the revealed distinctions can change a consequential decision.<n>We develop this theory for learning systems, where states equivalent under declared current information can respond differently to future training and favor different actions.
  arXiv  Detail & Related papers  (2026-08-24T22:07:57Z)
• PRISM: : Planning and Reasoning with Intent in Simulated Embodied Environments [59.07829883257003]
  Built on five multi-room apartments, PRISM structures 300 human-verified tasks into three capability tiers.<n>PRISM exposes an agent-agnostic executable action API that allows arbitrary agents to be evaluated end-to-end.
  arXiv  Detail & Related papers  (2026-05-12T04:59:47Z)
• Interactive Critique-Revision Training for Reliable Structured LLM Generation [18.00222080273147]
  We propose DPA-GRPO, a paired-action training method for a two-player generator--verifier game with structured verifier interventions.<n>We analyze the unregularized game and show that positive probability on strictly lower-reward intervention or revision actions creates a profitable unilateral deviation.<n>Experiments on TaxCalc TY24 show that DPA-GRPO improves structured decision accuracy over zero-shot generation and generator-only RL baselines.
  arXiv  Detail & Related papers  (2026-05-08T17:00:38Z)
• IMPACT-CYCLE: A Contract-Based Multi-Agent System for Claim-Level Supervisory Correction of Long-Video Semantic Memory [73.22944697933603]
  Existing pipelines produce opaque, end-to-end outputs that expose no intermediate state for inspection.<n>We present IMPACT-Cycle, a supervisory multi-agent system that reformulates long-video understanding as a multimodal iterative claim-level maintenance.
  arXiv  Detail & Related papers  (2026-04-22T03:03:33Z)
• RCBSF: A Multi-Agent Framework for Automated Contract Revision via Stackelberg Game [5.711356514732554]
  We propose the Risk-Constrained Bilevel Stackelberg Framework (RCBSF), which formulates revision as a non-cooperative game.<n>We provide theoretical guarantees that this bilevel formulation converges to yield strictly superior utility over unguided configurations.
  arXiv  Detail & Related papers  (2026-04-12T17:27:55Z)
• Governed Reasoning for Institutional AI [0.0]
  Cognitive Core is a governed decision substrate built from nine typed cognitive primitives.<n>Human review is a condition of execution rather than a post-hoc check.<n>We benchmark three systems on an 11-case balanced prior authorization appeal evaluation set.
  arXiv  Detail & Related papers  (2026-04-12T14:09:18Z)
• Support Sufficiency as Consequence-Sensitive Compression in Belief Arbitration [0.0]
  When a system commits to a hypothesis, much of the evidential structure behind that commitment is lost to compression.<n>Standard accounts assume that selected content and scalar confidence suffice for downstream control.<n>We develop a recurrent arbitration architecture in which active constraint fields jointly determine a hypothesis geometry over candidates.
  arXiv  Detail & Related papers  (2026-04-06T18:28:45Z)
• DARC: Disagreement-Aware Alignment via Risk-Constrained Decoding [59.16244104797919]
  We propose **Disagreement-Aware Alignment via Risk-Constrained Decoding (DARC)**.<n>DARC frames response selection as distributionally robust, risk-sensitive decision making.<n>Experiments on alignment benchmarks show that DARC reduces disagreement and tail risk while maintaining competitive average quality.
  arXiv  Detail & Related papers  (2026-03-09T09:21:29Z)
• Conformal Tradeoffs: Guarantees Beyond Coverage [0.02648566468224904]
  Deployed conformal predictors are long-lived decision infrastructure operating over finite operational windows.<n> Marginal coverage does not determine deployment-facing quantities.<n>We provide a framework for operational certification and planning beyond coverage.
  arXiv  Detail & Related papers  (2026-02-20T07:58:25Z)
• LEC: Linear Expectation Constraints for False-Discovery Control in Selective Prediction and Routing Systems [95.35293543918762]
  Large language models (LLMs) often generate unreliable answers, while uncertainty methods fail to fully distinguish correct from incorrect predictions.<n>We address this issue through the lens of false discovery rate (FDR) control, ensuring that among all accepted predictions, the proportion of errors does not exceed a target risk level.<n>We propose LEC, which reinterprets selective prediction as a constrained decision problem by enforcing a Linear Expectation Constraint.
  arXiv  Detail & Related papers  (2025-12-01T11:27:09Z)
• COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees [51.5976496056012]
  COIN is an uncertainty-guarding selection framework that calibrates statistically valid thresholds to filter a single generated answer per question.<n>COIN estimates the empirical error rate on a calibration set and applies confidence interval methods to establish a high-probability upper bound on the true error rate.<n>We demonstrate COIN's robustness in risk control, strong test-time power in retaining admissible answers, and predictive efficiency under limited calibration data.
  arXiv  Detail & Related papers  (2025-06-25T07:04:49Z)
• Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization [58.390885294401066]
  Retrieval-augmented generation (RAG) has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs)<n>RAG pipelines often fail to ensure that model reasoning remains consistent with the evidence retrieved, leading to factual inconsistencies or unsupported conclusions.<n>We propose AlignRAG, a novel iterative framework grounded in Critique-Driven Alignment (CDA)<n>We introduce AlignRAG-auto, an autonomous variant that dynamically terminates refinement, removing the need to pre-specify the number of critique iterations.
  arXiv  Detail & Related papers  (2025-04-21T04:56:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.