paper-with-me

홈 › Papers

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

2026-05-12 · Elias Calboreanu arxiv

Prompt specifications for multi-agent large language model (LLM) systems carry data contracts and integration logic across interdependent files but are rarely subjected to structured-inspection rigor. We report a single-system case study of iterative, agent-driven auditing applied to AEGIS (Autonomous Engineering Governance and Intelligence System), a seven-lane production pipeline whose 7152-line specification surface was audited across nine rounds, surfacing 51 consistency defects (per-round counts of 15, 8, 12, 2, 8, 1, 4, 1, 0). We present a seven-category post hoc taxonomy with explicit coding rules, non-monotonic convergence consistent with cascading edits and audit-scope expansion, and a locked audit protocol. We further report two partial replications on a public synthetic mini-specification: a cross-LLM panel of four frontier vendors (OpenAI, Anthropic, Google, xAI; 12 traces; multi-vendor union detects all five seeded defects) and an inter-rater reliability check on a stratified subsample (Cohen's $κ$ = 0.80 on category, 0.46 on severity). The full reproducibility bundle accompanies the submission.

📄 PDF Abstract BibTeX arXiv:2605.12280

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

BUILD-AND-FIND: An Effort-Aware Protocol for Evaluating Agent-Managed Codebases

2026-05-07 · Jhen-Ke Lin arxiv

Most coding-agent benchmarks ask whether generated code behaves correctly. That remains essential, but repository-level engineering is increasingly agent-managed: one agent writes a repository, and later agents inspect, …

Safe and Policy-Compliant Multi-Agent Orchestration for Enterprise AI

2026-04-19 · Vinil Pasupuleti, Shyalendar Reddy Allala, Siva Rama Krishna Varma Bayyavarapu, Shrey Tyagi arxiv

Enterprise AI systems increasingly deploy multiple intelligent agents across mission-critical workflows that must satisfy hard policy constraints, bounded risk exposure, and comprehensive auditability (SOX, HIPAA, GDPR).…

Fortifying the Agentic Web: A Unified Zero-Trust Architecture Against Logic-layer Threats

2025-08-17 · Ken Huang, Yasir Mehmood, Hammad Atta, Jerry Huang 외 arxiv

This paper presents a Unified Security Architecture that fortifies the Agentic Web through a Zero-Trust IAM framework. This architecture is built on a foundation of rich, verifiable agent identities using Decentralized I…

A Deterministic Control Plane for LLM Coding Agents

2026-06-25 · Padmaraj Madatha arxiv

LLM coding harnesses grant agents broad file and shell access, yet the configuration layer that steers them -- rules files, agent definitions, IDE-specific markdown -- is largely unmanaged. A prevalence study of 10,008 p…

AuditBench: Evaluating Alignment Auditing Techniques on Models with Hidden Behaviors

2026-02-26 · Abhay Sheshadri, Aidan Ewart, Kai Fronsdal, Isha Gupta 외 arxiv

We introduce AuditBench, an alignment auditing benchmark. AuditBench consists of 56 language models with implanted hidden behaviors. Each model has one of 14 concerning behaviors--such as sycophantic deference, oppositio…