Hierarchical Online Prompt Mutation with Dual-Loop Feedback for Guardrailed Evidence Document Generation: A Production-Evaluation Case Study

• URL: http://arxiv.org/abs/2606.01472v1
• Date: Sun, 31 May 2026 22:17:44 GMT
• Title: Hierarchical Online Prompt Mutation with Dual-Loop Feedback for Guardrailed Evidence Document Generation: A Production-Evaluation Case Study
• Abstract summary: HOPM is a hierarchical online prompt mutation framework evaluated on a real marketplace dispute-evidence workflow.<n>The paper includes control setup, sample sizes, confidence intervals, paired tests, prompt-token categories, pseudocode, schema, rubric, guardrail taxonomy, and a constructed example.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: High-stakes production document-generation systems require language models to be adaptive, evidence-grounded, and auditable. We present HOPM, a hierarchical online prompt mutation framework evaluated on a real marketplace dispute-evidence workflow. HOPM treats prompts as online policies: a family/version router selects a prompt, deterministic guardrails attribute failures to mutable prompt-token categories, and dual feedback from human review and an automated judge updates both routing and mutation priorities. The primary evidence is an observed matched production-evaluation ablation: seven variants are evaluated on the same 600 cases each, enabling component comparisons against static prompting, manual iteration, bandit-only routing, mutation-only adaptation, human-only feedback, auto-judge-only feedback, and full dual-loop HOPM. Full HOPM improves count win rate over a static control from 34.7% to 45.7% (+11.0 pp; paired McNemar p = 1.31e-11) and amount-weighted win rate from 22.3% to 41.4% (+19.1 pp; 95% paired bootstrap CI [10.3, 28.9] pp). It also increases mean Likert quality from 3.18 to 4.40 and reduces issue-flag rate from 15.3% to 5.2%. Supporting review artifacts cover 770 generated-text reviews, 318 labeled reviewer exports, a 10-case/61-rating calibration slice, and a 70-case/350-rating OCR benchmark; these artifacts calibrate rubric, guardrail, title-risk, and OCR-risk interpretation rather than substituting for the production ablation. The paper includes control setup, sample sizes, confidence intervals, paired tests, prompt-token categories, pseudocode, schema, rubric, guardrail taxonomy, and a constructed example so the evaluation structure can be reproduced without exposing proprietary evidence.

Related papers

• CARRE: Counterfactual Action Retrieval and Reason Evaluation for Explainable Churn Prescription [5.823033362443801]
  We present CARRE, a three-stage framework that combines retrieval-augmented candidate generation, cost-aware counterfactual scoring, and large language model (LLM) reasoning.<n>On the IBM Telco Customer Churn dataset, CARRE achieves 79.8% greater mean model-predicted risk reduction than the plain SHAP baseline.
  arXiv  Detail & Related papers  (2026-09-09T06:08:02Z)
• From Monolithic Blending to Agentic Orchestration: Dynamic Response for Conversational Assistants at Scale [17.274780841826438]
  We report a production migration of a customer-support assistant at a large accommodation marketplace.<n>DR replaces a single Qwen3-235B-A22B blended responder with a bounded ReAct orchestrator over typed tools.<n>We attribute each effect to its cause and claim as architecture effects only those measured on identical replayed turns.
  arXiv  Detail & Related papers  (2026-09-04T22:38:10Z)
• TrustRoboReward: Preference-Ordered Isotonic Score Editing for Multi-Paradigm Robot Reward Models [40.42873860258522]
  We propose TrustRoboReward, a multi-paradigm reward modeling framework equipped with Preference-Ordered Isotonic Score Editing (POISE)<n>POISE rectifies pointwise scores and eliminates cross-paradigm reversal conflicts unresolved by TrustJudge.<n>Qwen3-VL-4B trained with POISE achieves an overall reward score of 77.96%, nearly matching GPT-5-mini (78.09%, gap 0.13%) and outperforming the strongest RoboReward-4B baseline by 10.13%.
  arXiv  Detail & Related papers  (2026-08-09T05:25:22Z)
• Diagnosing Fine-Grained Inconsistency Classification in Financial Disclosure Text [3.2712318205295907]
  Financial disclosures contain numerical claims, temporal statements, entity references, policy commitments, and risk descriptions that may conflict in qualitatively different ways.<n>We study this problem as fine-grained inconsistency.<n>A fine-tuned 300M encoder reaches 61.9% accuracy, compared with 61.5% for a LoRA-adapted Qwen3.5-9B model and 61.3% for GPT-adapted generative models.
  arXiv  Detail & Related papers  (2026-07-29T01:03:53Z)
• CUSUM-Shaped Inference-Time Monitoring and Targeted Re-Decoding for Quantized Small Language Model Reasoning [0.6999740786886536]
  MGT-B maps overlapping windows of pre-sampling uncertainty and degeneration features to position-conditional empirical tail probabilities.<n>We audit whether the effect persists on problem identities first observed after the manual choice of log threshold h = 10.<n>Neither analysis is confirmatory, and the empirical factors are not established as a valid e-process or e-detector.
  arXiv  Detail & Related papers  (2026-07-22T13:34:17Z)
• Compliance-Scored Best-of-N Guardrail Orchestration for Multimodal Document Generation in Payments Dispute Defense [0.0]
  High-stakes enterprise document generation includes financial dispute narratives, compliance notices, and audit summaries.<n>Prior to a unified guardrail layer, production systems often stitched together separate PII redaction, content moderation, and format validation steps.<n>We present a guardrail orchestration layer for text and image inputs that couples multi-candidate generation with an explicit compliance score used for early exit.
  arXiv  Detail & Related papers  (2026-06-01T00:24:30Z)
• Step-wise Rubric Rewards for LLM Reasoning [72.17879367869503]
  Reinforcement Learning with Verifiable Rewards (RLVR) is widely used to improve reasoning in large language models.<n>We find 18.2% of steps in correct responses are wrong yet positively rewarded.<n>Across six mathematical reasoning benchmarks, SRaR improves average accuracy over RaR by 3.57 points.
  arXiv  Detail & Related papers  (2026-05-17T07:08:14Z)
• Distributional Energy-Based Models for Uncertainty-Aware Structured LLM Reasoning [40.342912574072024]
  Large Language Models produce structured outputs such as travel plans or code solutions.<n>Individual reasoning steps may appear correct while the output as a whole violates budgets, fails test cases, or contradicts earlier deductions.<n>We propose a learned quality scorer with deterministic analytical constraint penalties for verifying structured LLM outputs.
  arXiv  Detail & Related papers  (2026-05-15T17:08:27Z)
• Multi-Dimensional Behavioral Evaluation of Agentic Stock Prediction Systems Using Large Language Model Judges with Closed-Loop Reinforcement Learning Feedback [1.2362187555287152]
  Forecast evaluation in finance has relied on aggregate accuracy metrics and predictive-accuracy tests built on point-forecast errors.<n>We propose a behavioral forecast-evaluation methodology that complements accuracy tests by assessing the intermediate decision process itself.
  arXiv  Detail & Related papers  (2026-05-07T06:31:34Z)
• AuditRepairBench: A Paired-Execution Trace Corpus for Evaluator-Channel Ranking Instability in Agent Repair [21.974153439592317]
  AuditBench is a paired-execution trace corpus of 576,000 registered cells (96,000 executed)<n>It operationalizes evaluator-channel-blocking ranking instability within a declared observability boundary.<n>It is supported by mechanism-anchored validation on an 80-case source-level channel-surgery subset.
  arXiv  Detail & Related papers  (2026-05-06T08:12:09Z)
• AgentEval: DAG-Structured Step-Level Evaluation for Agentic Workflows with Error Propagation Tracking [13.891522069967507]
  We present AgentEval, a framework that formalizes agent executions as evaluation directed acyclic graphs (DAGs)<n>AgentEval achieves 2.17x higher failure detection recall than end-to-end evaluation and 72% root cause accuracy against an 81% human ceiling.
  arXiv  Detail & Related papers  (2026-04-26T07:38:47Z)
• Automated Self-Testing as a Quality Gate: Evidence-Driven Release Management for LLM Applications [51.56484100374058]
  We present an automated self-testing framework that introduces quality gates with evidence-based release decisions.<n>We evaluate the framework through a longitudinal case study of an internally deployed multi-agent conversational AI system.
  arXiv  Detail & Related papers  (2026-03-13T20:44:15Z)
• From Black Box to Glass Box: Cross-Model ASR Disagreement to Prioto Review in Ambient AI Scribe Documentation [43.148402136307716]
  Cross-model disagreement among heterogeneous ASR systems can act as a reference-free uncertainty signal.<n>We transcribed 50 publicly available medical audio clips with eight ASR systems spanning commercial APIs and open-source engines.<n>Low-agreement regions were enriched for content disagreements, with the content fraction increasing from 53.9% to 73.9% across quintiles of high-risk mass.
  arXiv  Detail & Related papers  (2026-03-02T13:02:13Z)
• RecGPT-V2 Technical Report [41.57739441038769]
  Large language models (LLMs) have demonstrated remarkable potential in transforming recommender systems from implicit behavioral pattern matching to explicit intent reasoning.<n>We present RecGPT-V2 with four key innovations to transform recommender systems from implicit behavioral pattern matching to explicit intent reasoning.<n>Online A/B tests on Taobao demonstrate significant improvements: +2.98% CTR, +3.71% IPV, +2.19% TV, and +11.46% NER.
  arXiv  Detail & Related papers  (2025-12-16T15:40:44Z)
• Generating Natural-Language Surgical Feedback: From Structured Representation to Domain-Grounded Evaluation [66.7752700084159]
  High-quality feedback from a surgical trainer is pivotal for improving trainee performance and long-term skill acquisition.<n>We present a structure-aware pipeline that learns a surgical action ontology from real trainer-to-trainee transcripts.
  arXiv  Detail & Related papers  (2025-11-19T06:19:34Z)
• Large Language Models are not Fair Evaluators [60.27164804083752]
  We find that the quality ranking of candidate responses can be easily hacked by altering their order of appearance in the context. This manipulation allows us to skew the evaluation result, making one model appear considerably superior to the other. We propose a framework with three simple yet effective strategies to mitigate this issue.
  arXiv  Detail & Related papers  (2023-05-29T07:41:03Z)

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.