Infrastructure as code (IaC) tools automate cloud provisioning but verifying that deployed systems remain consistent with the IaC specifications remains challenging. Such configuration drift occurs because of bugs in the IaC specification, manual changes, or system updates. Large language model (LLM)-based agentic AI systems can automate the analysis of large volumes of telemetry data, making them suitable for the detection of configuration drift. However, existing agentic systems implicitly assume that the tools they invoke always return correct outputs, making them vulnerable to erroneous tool responses. Since agents cannot distinguish whether an anomalous tool output reflects a real infrastructure problem or a broken tool, such errors may cause missed drift or false alarms, reducing reliability precisely when it is most needed. We introduce RIVA (Robust Infrastructure by Verification Agents), a novel multi-agent system that performs robust IaC verification even when tools produce incorrect or misleading outputs. RIVA employs two specialized agents, a verifier agent and a tool generation agent, that collaborate through iterative cross-validation, multi-perspective verification, and tool call history tracking. Evaluation on the AIOpsLab benchmark demonstrates that RIVA, in the presence of erroneous tool responses, recovers task accuracy from 27.3% when using a baseline ReAct agent to 50.0% on average. RIVA also improves task accuracy 28% to 43.8% without erroneous tool responses. Our results show that cross-validation of diverse tool calls enables more reliable autonomous infrastructure verification in production cloud environments.
Figures & tables
Figure 1. The impact of erroneous tools on the accuracy of error detection and localization tasks in the AIOpsLab benchmark by agentic AI systems.
Figure 2. The RIVA system architecture and workflow.
Figure 3. The task success rate of RIVA (with K=2 ) and a ReAct agent in the presence of erroneous tools and without any erroneous tool.
Agent
Only correct
incorrect
incorrect
tools
get_logs
read_metrics
ReAct
28.00
25.93
28.57
RIVA (K=1)
27.67
24.80
29.02
RIVA (K=2)
43.75
46.67
53.33
RIVA (K=3)
0
0
0
Table 1. Average success rate of ReAct and RIVA with different K on AIOpsLab
Appendix figures & tables3 assets
Supplementary material from the paper’s appendix.
Appendix
Figure 6. The workflow of configuration drift detection by LLM agents on infrastructure deployed by IaC .
Figure 7. The distribution of number of steps required to complete tasks, for RIVA and the ReAct agent, with and without erroneous tool responses.
Figure 8. The distribution of maximum number of tokens required to complete tasks, for RIVA and the ReAct agent, with and without erroneous tool responses.
Large language model (LLM) agent reliability concerns dependable, safe, and verifiable behavior across tools, multi-step tasks, and changing environments.
We introduce a comprehensive validation framework for LLM-based agentic systems that provides systematic diagnosis and improvement of reliability failures. The framework includes fifteen failure-detection tools and two root-cause analysis modules that jointly uncover weaknesses across input handling, prompt design, and output generation. It integrates lightweight rule-based checks with LLM-as-a-judge assessments to support structured incident detection, classification, and repair. We applied the framework to IBM CUGA, evaluating its performance on the AppWorld and WebArena benchmarks. The analysis revealed recurrent planner misalignments, schema violations, brittle prompt dependencies, and more. Based on these insights, we refined both prompting and coding strategies, maintaining CUGA's benchmark results while enabling mid-sized models such as Llama 4 and Mistral Medium to achieve notable accuracy gains, substantially narrowing the gap with frontier models. Beyond quantitative validation, we conducted an exploratory study that fed the framework's diagnostic outputs and agent description into an LLM for self-reflection and prioritization. This interactive analysis produced actionable insights on recurring failure patterns and focus areas for improvement, demonstrating how validation itself can evolve into an agentic, dialogue-driven process. These results show a path toward scalable, quality assurance, and adaptive validation in production agentic systems, offering a foundation for more robust, interpretable, and self-improving agentic architectures.
LLM agents increasingly rely on reusable skill libraries, but these skills silently decay as the external services, packages, APIs, and configurations they reference evolve. Existing monitors detect such changes at the wrong granularity: they observe values, not the role those values play in a skill. A version string in a comment is noise; the same string in a pinned dependency is an operational obligation. We formulate skill drift as contract violation and introduce \sgname{}, which extracts executable environment contracts from skill documents and validates only those role-bearing assumptions against known or live conditions. This distinction turns noisy monitoring into a precision-first maintenance signal. Contract-free CI probes produce 40% false positives, while \sgname{} raises zero false alarms over 599 no-drift and hard-negative cases (Wilson 95% CI [0,0.6]%). In known-drift verification, \sgname{} achieves 100% precision and 76% recall with the strongest backbone; in a pre-registered study over 49 real skills, it discovers live drift with 86% conservative precision. Violated contracts also make repair actionable, improving one-round success from 10% without localization to 78%. We release \dbname{}, an 880-pair benchmark for skill degradation.
Linfeng Fan, Yuan Tian, Ziwei Li +1
Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China · King Abdullah University of Science and Technology, Thuwal, Saudi Arabia
Managing modern computing infrastructure has become a steadily harder problem due to the ever-increasing complexity. Recent advances in AI agents create a timely opportunity to automate infrastructure management tasks, but it remains unclear how well such agents can handle real-world infrastructure complexity. We present InfraBench, a benchmark for infrastructure agents organized around system layers, the operational lifecycle, and risk. The current prototype couples container, VM, and bare-metal backends with task-specific verifiers that distinguish functional repair from durability and cleanup, and analyzes retained action-trace findings for unsafe shortcuts. We evaluate 18 agent-model configurations on 12 seed tasks, with three attempts per task. Mean effective scores range from 45.5% to 89.2%; the strongest configuration completes 77.8% of attempts perfectly. In the available lifecycle checks, pass rates fall from 91.5% for functional repair to 80.9% for durability and 38.9% for cleanup. These results show why immediate recovery is an incomplete measure of operational capability. We use this evidence to motivate a planned expansion toward 40-60 tasks centered on managed cloud infrastructure and redesign after incidents, including provider-native Kubernetes networking. This extension is a research direction; the reported results remain those of the 12-task prototype. InfraBench, its tasks, evaluation harness, and live leaderboard are available at infraben.ch.
Yuan Gao, Zeren Yang, Junnan Li +6
Wanxiang · University of Wisconsin–Madison · Iowa State University