Iterative Audit Convergence in LLM-Managed Multi-Agent Systems: A Case Study in Prompt Engineering Quality Assurance

• URL: http://arxiv.org/abs/2605.12280v1
• Date: Tue, 12 May 2026 15:39:04 GMT
• Title: Iterative Audit Convergence in LLM-Managed Multi-Agent Systems: A Case Study in Prompt Engineering Quality Assurance
• Abstract summary: This paper reports a single-system empirical case study of agent-driven auditing applied to AEGIS.<n>We report a seven-category post-hoc defect taxonomy with explicit coding rules, observed non-monotonic convergence, and audit-scope expansion.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Prompt specifications for multi-agent large language model (LLM) systems carry data contracts and integration logic across many interdependent files but are rarely subjected to structured-inspection rigor. This paper reports a single-system empirical case study of iterative, agent-driven auditing applied to AEGIS (Autonomous Engineering Governance and Intelligence System), a production seven-lane orchestration pipeline whose prompt-specification surface comprises approximately 7150 lines: 6907 across seven lane PROMPT.md files and a 245-line shared Ticket Contract. Nine sequential audit rounds, executed by Claude sub-agents using a checklist-driven walkthrough adapted from Weinberg and Freedman, surfaced 51 prompt-specification consistency defects, distinct from the 51 STRIDE-categorized adversarial code findings reported in the companion preprint. Per-round counts were 15, 8, 12, 2, 8, 1, 4, 1, and 0. We report a seven-category post-hoc defect taxonomy with explicit coding rules, observed non-monotonic convergence consistent with cascading edits and audit-scope expansion, and an audit protocol distilled from the study, with the final locked checklist released as a reproducibility appendix. Single-file review missed defect classes that were surfaced only by later expanded-scope rounds in this system. The same LLM family authored and audited the specifications; replication with dissimilar models and human reviewers is required before generalization.

Related papers

• MTAC-IFBench: Benchmarking Instruction-Following in Multi-Turn Agentic Coding [83.0805548642958]
  MTAC-IFBench is a comprehensive benchmark for instruction-following in software development.<n>It features multi-turn progressive software development instructions with diverse constraints spanning 6 primary and 18 secondary categories.<n>MTAC-IFBench identifies significant deficiencies in existing code agents in multi-turn instruction-following, with their performance degrading rapidly as the interaction session grows longer.
  arXiv  Detail & Related papers  (2026-09-14T03:57:37Z)
• When Agents Implement Systems: A Case Study in Defects, Detection, and Evaluation Rigor [0.0]
  We present a case study of one such agent implementing a multi-component data system against a detailed pre-existing specification.<n>We catalog five such defects, categorized by constraint violated and detection method.<n>Across retrieval budgets from 1 to 10 and 100 questions against a pooled corpus of 2994 paragraphs, filtered recall reaches its ceiling by a budget of 3, expected once candidates are restricted to the gold paragraphs themselves.
  arXiv  Detail & Related papers  (2026-09-02T01:43:09Z)
• A-SR: Self-Evolving Agentic LLMs for Symbolic Regression via Hierarchical Coordination [51.06539604709775]
  We propose A-SR, a self-evolving agentic framework that shifts the control unit from expression edits to role-conditioned evidence views.<n>A-SR coordinates formula discovery through routing among coordination protocols, an online evaluator-reward role policy, and state-routed process memory.
  arXiv  Detail & Related papers  (2026-08-05T14:01:10Z)
• Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation [0.0]
  Fraud detection systems must scale with rising transaction volume while remaining explainable and reviewable.<n>We study a layered pipeline that combines a gradient-boosted classifier, graph-derived structural features, an autoencoder-based anomaly signal, and an investigation agent.<n>We conclude that each component contributes only under specific conditions, and that a plausible rationale from an investigation agent is not evidence of a better decision.
  arXiv  Detail & Related papers  (2026-07-21T16:37:41Z)
• Fantastic Adaptive Taxonomies and How to Use Them [100.20614173157708]
  AdaMAST converts execution traces into a compact, evidence-grounded failure taxonomy.<n>No code is hand-authored, no trace human-annotated.<n>In agent-system search, taxonomy-coded diagnoses of failed candidates outperform free-form.
  arXiv  Detail & Related papers  (2026-07-17T17:41:16Z)
• A Multi-Analyst LLM Pipeline for Auditable Rule Discovery Across 68 Public Physiological Corpora [0.0]
  Open physiological corpora can support detector design, but they do not directly specify which detector rules should be built for a new contactless monitoring platform.<n>We convert 68 public physiological corpora into an auditable library of candidate rule shapes for prospective validation.<n>The pipeline does not produce a validated clinical detector.
  arXiv  Detail & Related papers  (2026-07-07T20:56:37Z)
• 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)
• Towards Multi-Agent Autonomous Reasoning in Hydrodynamics [0.06999740786886537]
  We present a multi-agent system (MAS) prototype for hydrodynamics in which specialized agents are coordinated through a Layer Execution Graph (LEG)<n>A planner agent constructs query-specific execution topologies from natural-language routings that capture domain knowledge without hard-coding it as rigid control logic.<n>A reporter agent synthesizes the final response, while the runtime logs provenance for every tool invocation to support auditability.
  arXiv  Detail & Related papers  (2026-05-01T21:17:55Z)
• How Independent are Large Language Models? A Statistical Framework for Auditing Behavioral Entanglement and Reweighting Verifier Ensembles [46.63622714488747]
  Shared pretraining data, distillation, and alignment pipelines can induce hidden behavioral dependencies, latent entanglement.<n>In practice, this manifests as correlated reasoning patterns and synchronized failures.<n>We develop a statistical framework for auditing behavioral entanglement among black-box language models.
  arXiv  Detail & Related papers  (2026-04-08T23:32:06Z)
• Breaking the Illusion of Identity in LLM Tooling [0.0]
  No existing mitigation provides a systematic deployable constraint set output register.<n>This paper proposes seven outputside rules, each targeting a documented linguistic mechanism.
  arXiv  Detail & Related papers  (2026-04-08T09:15:14Z)
• LLM-based Schema-Guided Extraction and Validation of Missing-Person Intelligence from Heterogeneous Data Sources [0.7734726150561088]
  Missing-person and child-safety investigations rely on heterogeneous case documents, including structured forms, bulletin-style posters, and narrative web profiles.<n>Variations in layout, terminology, and data quality impede rapid triage, large-scale analysis, and search-planning.<n>This paper introduces the Guardian Pack, an AI-driven parsing and normalization pipeline that transforms multi-source investigative documents into a unified, schema-compliant representation.
  arXiv  Detail & Related papers  (2026-04-08T01:35:56Z)
• 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)
• Arbiter: Detecting Interference in LLM Agent System Prompts [0.0]
  Arbiter is a framework combining formal evaluation rules with multi-model LLM scouring to detect interference patterns in system prompts.<n> Applied to three major coding agent system prompts: Claude Code (Anthropic), Codex CLI (OpenAI), and Gemini CLI (Google)
  arXiv  Detail & Related papers  (2026-03-09T22:29:47Z)
• SPECA: Specification-to-Checklist Agentic Auditing for Multi-Implementation Systems -- A Case Study on Ethereum Clients [1.711666249985278]
  SPECA is a Specification-to-Checklist framework that turns normative requirements into checklists.<n>We instantiate SPECA in an in-the-wild security audit contest for the Fusaka upgrade, covering 11 production clients.<n>Our improved agent, evaluated against the ground truth of a competitive audit, achieved a strict recall of 27.3 percent on high-impact vulnerabilities.
  arXiv  Detail & Related papers  (2026-02-07T12:19:00Z)
• UNIDOC-BENCH: A Unified Benchmark for Document-Centric Multimodal RAG [82.84014669683863]
  Multimodal retrieval-augmented generation (MM-RAG) is a key approach for applying large language models to real-world knowledge bases.<n>UniDoc-Bench is the first large-scale, realistic benchmark for MM-RAG built from 70k real-world PDF pages.<n>Our experiments show that multimodal text-image fusion RAG systems consistently outperform both unimodal and jointly multimodal embedding-based retrieval.
  arXiv  Detail & Related papers  (2025-10-04T04:30:13Z)
• CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward [50.97588334916863]
  We develop CompassVerifier, an accurate and robust lightweight verifier model for evaluation and outcome reward.<n>It demonstrates multi-domain competency spanning math, knowledge, and diverse reasoning tasks, with the capability to process various answer types.<n>We introduce VerifierBench benchmark comprising model outputs collected from multiple data sources, augmented through manual analysis of metaerror patterns to enhance CompassVerifier.
  arXiv  Detail & Related papers  (2025-08-05T17:55:24Z)
• MMESGBench: Pioneering Multimodal Understanding and Complex Reasoning Benchmark for ESG Tasks [56.350173737493215]
  Environmental, Social, and Governance (ESG) reports are essential for evaluating sustainability practices, ensuring regulatory compliance, and promoting financial transparency.<n>MMESGBench is a first-of-its-kind benchmark dataset to evaluate multimodal understanding and complex reasoning across structurally diverse and multi-source ESG documents.<n>MMESGBench comprises 933 validated QA pairs derived from 45 ESG documents, spanning across seven distinct document types and three major ESG source categories.
  arXiv  Detail & Related papers  (2025-07-25T03:58:07Z)
• SOPBench: Evaluating Language Agents at Following Standard Operating Procedures and Constraints [59.645885492637845]
  SOPBench is an evaluation pipeline that transforms each service-specific SOP code program into a directed graph of executable functions.<n>Our approach transforms each service-specific SOP code program into a directed graph of executable functions and requires agents to call these functions based on natural language SOP descriptions.<n>We evaluate 18 leading models, and results show the task is challenging even for top-tier models.
  arXiv  Detail & Related papers  (2025-03-11T17:53:02Z)

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.