# When Passing Tests Hides Vulnerabilities: An Empirical Study of Silent Failures in Agentic Systems arXiv: https://arxiv.org/abs/2609.10548 ยท HTML: https://mlsanity.com/paper/2609.10548/ ## Key facts - Cited by 1 papers in the map (data through 14 Oct 2026). - Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. - Builds on 32 of its 52 references that are in the map. - First posted on arXiv 25 Jun 2026. ## Placed in - LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/) ## Builds on (most cited first, 30 of 32) - [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021) - [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023) - [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023) - [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023) - [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024) - [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024) - [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023) - [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025) - [RepairAgent: An Autonomous, LLM-Based Agent for Program Repair](https://mlsanity.com/paper/2403.17134/) (2024) - [Do Users Write More Insecure Code with AI Assistants?](https://mlsanity.com/paper/2211.03622/) (2022) - [Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems](https://mlsanity.com/paper/2505.00212/) (2025) - [The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey](https://mlsanity.com/paper/2404.11584/) (2024) - [Multi-Agent Risks from Advanced AI](https://mlsanity.com/paper/2502.14143/) (2025) - [AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?](https://mlsanity.com/paper/2509.03312/) (2025) - [Examining Zero-Shot Vulnerability Repair with Large Language Models](https://mlsanity.com/paper/2112.02125/) (2021) - [On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents](https://mlsanity.com/paper/2408.00989/) (2024) - [CodeR: Issue Resolving with Multi-Agent and Task Graphs](https://mlsanity.com/paper/2406.01304/) (2024) - [CVEfixes: Automated Collection of Vulnerabilities and Their Fixes from Open-Source Software](https://mlsanity.com/paper/2107.08760/) (2021) - [CWEval: Outcome-driven Evaluation on Functionality and Security of LLM Code Generation](https://mlsanity.com/paper/2501.08200/) (2025) - [How Effective Are Neural Networks for Fixing Security Vulnerabilities](https://mlsanity.com/paper/2305.18607/) (2023) - [A Survey of Useful LLM Evaluation](https://mlsanity.com/paper/2406.00936/) (2024) - [BattleAgentBench: A Benchmark for Evaluating Cooperation and Competition Capabilities of Language Models in Multi-Agent Systems](https://mlsanity.com/paper/2408.15971/) (2024) - [Multi-Agent Large Language Models for Conversational Task-Solving](https://mlsanity.com/paper/2410.22932/) (2024) - [Let the Trial Begin: A Mock-Court Approach to Vulnerability Detection using LLM-Based Agents](https://mlsanity.com/paper/2505.10961/) (2025) - [Risk Analysis Techniques for Governed LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2508.05687/) (2025) - [Challenges in Human-Agent Communication](https://mlsanity.com/paper/2412.10380/) (2024) - [VulnRepairEval: An Exploit-Based Evaluation Framework for Assessing Large Language Model Vulnerability Repair Capabilities](https://mlsanity.com/paper/2509.03331/) (2025) - [Beyond Single-Agent Safety: A Taxonomy of Risks in LLM-to-LLM Interactions](https://mlsanity.com/paper/2512.02682/) (2025) - [A Systematic Literature Review on Detecting Software Vulnerabilities with Large Language Models](https://mlsanity.com/paper/2507.22659/) (2025) - [Helping LLMs Improve Code Generation Using Feedback from Testing and Static Analysis](https://mlsanity.com/paper/2412.14841/) (2024) ## Built on by (most cited first, 1 of 1) - [Where Did the Repair First Go Wrong? Localizing the Origins of Silent Failures in Agentic Vulnerability Repair](https://mlsanity.com/paper/2610.06163/) (2026) ## Abstract (arXiv) LLM-based agents for automated code repair have received significant attention in recent years from both research and software engineering practice perspectives. However, limited attention has been paid to patches that pass syntactic and functional verification but still retain or introduce security vulnerabilities. The aim of this research is to systematically identify and categorize such silent failures in LLM-based agentic code repair. We conducted an empirical study using 1,030 valid execution traces produced by seven agent frameworks with GPT-4o-mini across two security-focused datasets, SecurityEval and CVEfixes. Through three iterations of qualitative coding and manual verification, 170 confirmed silent failures were identified. The key results are: (i) Three main categories of silent failures were identified: Omission, Introduction, and Inadequacy. Omission accounts for 48.2% of the confirmed failures, Introduction for 30.6%, and Inadequacy for 21.2%. (ii) Ten fine-grained failure codes were classified under these three categories, showing how agents omit required security controls, apply incomplete defenses, or introduce new vulnerabilities during repair. (iii) Current test-passing evaluation and LLM-based reviewer roles were insufficient to expose or intercept these failures in the confirmed cases. (iv) Similar insecure solutions appeared across different frameworks, suggesting possible shared model-, prompt-, or task-level influences, while single-agent and multi-agent systems showed different failure profiles. The results of this study will assist researchers and practitioners in improving the evaluation of LLM-based agentic code repair and developing targeted verification methods that go beyond functional correctness and cover all generated artifacts.