Joey Dodds
Research Subjects
Research Interests
Joey Dodds has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Victor Nicolet
Amazon, Seattle, USA
4 shared publications - Daniel Kroening
Amazon, Seattle, USA
3 shared publications - Hui Guan
College of Information and Computer Sciences, University of Massachusetts Amherst, Amherst, MA, USA
2 shared publications - Ang Chen
University of Michigan, Ann Arbor, USA
1 shared publication - Brandon Paulsen
Amazon, Arlington, USA
1 shared publication - Jinwoo Kim
University of California at San Diego, La Jolla, USA
1 shared publication
Latest Publications
- Open Access
- 1 October 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 3 (ISSTA) , 687-709
NSync: Automated Cloud Infrastructure-as-Code Reconciliation with AI Agents
Cloud infrastructure is managed through a mix of interfaces—traditionally, cloud consoles, command-line interfaces (CLI), and SDKs are the tools of choice. Recently, Infrastructure-as-Code/IaC frameworks (e.g., Terraform) have quickly gained popularity. Unlike conventional tools, IaC frameworks encode the infrastructure in a ”source-of-truth” configuration. They are capable of automatically carrying out modifications to the cloud—deploying, updating, or destroying resources—to bring the actual infrastructure into alignment with the IaC configuration. When IaC frameworks are used together with consoles, CLI, or SDKs, IaC is unaware of changes through these non-IaC interfaces, and the IaC configuration no longer captures the intended state. This is called infrastructure drift. IaC frameworks will revert non-IaC changes based on the outdated IaC configuration, leading to misconfigurations or failures. We propose NSync, an automated system for IaC reconciliation, which aims to propagate out-of-band changes back to the IaC program in the form of an update. Our key insight is that infrastructure changes via IaC, consoles, CLI, or SDK eventually all occur via cloud API invocations—the lowest layer for cloud management operations. Hence, NSync gleans insights from API traces to detect drift (i.e., non-IaC changes) and reconcile it (i.e., update the IaC configuration to capture the changes). This is a challenging task—identifying the intended change from low-level, noisy API traces is not easy; moreover, because of the criticality of cloud infrastructure, NSync cannot directly test the synthesized updates in a live environment. NSync addresses these challenges using an agentic design. It infers high-level infrastructure change intent from cloud API sequences with the help of LLMs, and synthesizes targeted IaC updates using domain-specific context management with customized agent tooling; it further maintains an evolving knowledge base of past successful reconciliation runs, reusing prior insights to achieve higher accuracy on future tasks. In addition to system design, we contribute a novel evaluation pipeline for injecting drift into cloud infrastructure and assessing reconciliation attempts, by sourcing scenarios from authoritative cloud operation examples and transplanting them into an IaC-centric framework. Experiments across five real-world Terraform projects and 372 drift scenarios show that NSync outperforms the baseline both in terms of accuracy (from 0.71 to 0.97 pass@3) and token efficiency (1.47× improvement).
- 1 October 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 3 (ISSTA) , 687-709
Open AccessNSync: Automated Cloud Infrastructure-as-Code Reconciliation with AI Agents
Cloud infrastructure is managed through a mix of interfaces—traditionally, cloud consoles, command-line interfaces (CLI), and SDKs are the tools of choice. Recently, Infrastructure-as-Code/IaC frameworks (e.g., Terraform) have quickly gained popularity. Unlike conventional tools, IaC frameworks encode the infrastructure in a ”source-of-truth” configuration. They are capable of automatically carrying out modifications to the cloud—deploying, updating, or destroying resources—to bring the actual infrastructure into alignment with the IaC configuration. When IaC frameworks are used together with consoles, CLI, or SDKs, IaC is unaware of changes through these non-IaC interfaces, and the IaC configuration no longer captures the intended state. This is called infrastructure drift. IaC frameworks will revert non-IaC changes based on the outdated IaC configuration, leading to misconfigurations or failures. We propose NSync, an automated system for IaC reconciliation, which aims to propagate out-of-band changes back to the IaC program in the form of an update. Our key insight is that infrastructure changes via IaC, consoles, CLI, or SDK eventually all occur via cloud API invocations—the lowest layer for cloud management operations. Hence, NSync gleans insights from API traces to detect drift (i.e., non-IaC changes) and reconcile it (i.e., update the IaC configuration to capture the changes). This is a challenging task—identifying the intended change from low-level, noisy API traces is not easy; moreover, because of the criticality of cloud infrastructure, NSync cannot directly test the synthesized updates in a live environment. NSync addresses these challenges using an agentic design. It infers high-level infrastructure change intent from cloud API sequences with the help of LLMs, and synthesizes targeted IaC updates using domain-specific context management with customized agent tooling; it further maintains an evolving knowledge base of past successful reconciliation runs, reusing prior insights to achieve higher accuracy on future tasks. In addition to system design, we contribute a novel evaluation pipeline for injecting drift into cloud infrastructure and assessing reconciliation attempts, by sourcing scenarios from authoritative cloud operation examples and transplanting them into an IaC-centric framework. Experiments across five real-world Terraform projects and 372 drift scenarios show that NSync outperforms the baseline both in terms of accuracy (from 0.71 to 0.97 pass@3) and token efficiency (1.47× improvement).
- Open Access
- 1 October 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Programming Languages
- Vol. 10 (OOPSLA2) , 375-402
Incremental Program Synthesis from Event Logs
The goal of program synthesis is to enable non-expert users to write programs by providing a specification instead of an implementation. To truly realize this goal, the specification must require no expertise and no effort to generate. We consider the problem of synthesizing automation scripts from only the logs that are automatically collected by many systems. Using our approach, users can automate tasks they usually perform manually, without having to know how to program them. Because logs are collected automatically, the synthesis approach needs to scale to large sets of logs. We present a new algorithm to solve this task by incrementally extending an API-calling script with behavior exemplified by a sequence of log events, adding one sequence at a time. By minimizing the program modifications at each step, we preserve user intent and synthesize a program as general as possible. We show that our approach, implemented in a tool LogLoom, scales to synthesis tasks with more traces and more complex programs than existing techniques. LogLoom synthesizes scripts that are identical to reference solutions for 60 out of 72 benchmarks, compared to 14 for an existing symbolic approach and 39 for an LLM.
- 1 October 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Programming Languages
- Vol. 10 (OOPSLA2) , 375-402
Open AccessIncremental Program Synthesis from Event Logs
The goal of program synthesis is to enable non-expert users to write programs by providing a specification instead of an implementation. To truly realize this goal, the specification must require no expertise and no effort to generate. We consider the problem of synthesizing automation scripts from only the logs that are automatically collected by many systems. Using our approach, users can automate tasks they usually perform manually, without having to know how to program them. Because logs are collected automatically, the synthesis approach needs to scale to large sets of logs. We present a new algorithm to solve this task by incrementally extending an API-calling script with behavior exemplified by a sequence of log events, adding one sequence at a time. By minimizing the program modifications at each step, we preserve user intent and synthesize a program as general as possible. We show that our approach, implemented in a tool LogLoom, scales to synthesis tasks with more traces and more complex programs than existing techniques. LogLoom synthesizes scripts that are identical to reference solutions for 60 out of 72 benchmarks, compared to 14 for an existing symbolic approach and 39 for an LLM.
- Open Access
- 30 June 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 3 (FSE) , 4070-4093
EventADL: Open-Box Anomaly Detection and Localization Framework for Events in Cloud-Based Service Systems
Anomaly detection and localization (ADL) is critical for maintaining reliability and availability in cloud systems. Recent ADL developments focus on metric and log data, leaving event data unexplored. To address this gap, we propose EventADL, the first open-box event-based ADL framework for cloud-based service systems. To motivate the design of our framework, we conduct a systematic analysis on 520 real-world incidents, and provide insights into how anomalies and their root causes manifest through event data. EventADL has three phases: offline training, online anomaly detection, and root cause localization. During the training phase, EventADL first learns Event Semantic Patterns (ESPs), which capture normal interactions between system entities using historical event data, and then learns Event Frequency Patterns (EFPs), which capture the normal frequency of known ESPs. In the online anomaly detection phase, any data in the event stream that deviates significantly from either pattern is identified as anomalous. For localization, EventADL constructs an Intervention Graph that models the relationships between recent system interactions and the detected anomalies for automatic root cause localization. The framework is designed to operate efficiently with unlabeled data and to produce interpretable anomalies with their corresponding root causes. Our evaluation on three real cloud service systems and two real-world incidents demonstrates that EventADL outperforms existing methods, achieving F1-scores of at least 90% for anomaly detection and 100% top-3 accuracy in root cause localization.
- 30 June 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 3 (FSE) , 4070-4093
Open AccessEventADL: Open-Box Anomaly Detection and Localization Framework for Events in Cloud-Based Service Systems
Anomaly detection and localization (ADL) is critical for maintaining reliability and availability in cloud systems. Recent ADL developments focus on metric and log data, leaving event data unexplored. To address this gap, we propose EventADL, the first open-box event-based ADL framework for cloud-based service systems. To motivate the design of our framework, we conduct a systematic analysis on 520 real-world incidents, and provide insights into how anomalies and their root causes manifest through event data. EventADL has three phases: offline training, online anomaly detection, and root cause localization. During the training phase, EventADL first learns Event Semantic Patterns (ESPs), which capture normal interactions between system entities using historical event data, and then learns Event Frequency Patterns (EFPs), which capture the normal frequency of known ESPs. In the online anomaly detection phase, any data in the event stream that deviates significantly from either pattern is identified as anomalous. For localization, EventADL constructs an Intervention Graph that models the relationships between recent system interactions and the detected anomalies for automatic root cause localization. The framework is designed to operate efficiently with unlabeled data and to produce interpretable anomalies with their corresponding root causes. Our evaluation on three real cloud service systems and two real-world incidents demonstrates that EventADL outperforms existing methods, achieving F1-scores of at least 90% for anomaly detection and 100% top-3 accuracy in root cause localization.
- Open Access
- 10 June 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Programming Languages
- Vol. 9 (PLDI) , 1642-1665
Program Synthesis from Partial Traces
We present the first technique to synthesize programs that compose side-effecting functions, pure functions, and control flow, from partial traces containing records of only the side-effecting functions. This technique can be applied to synthesize API composing scripts from logs of calls made to those APIs, or a script from traces of system calls made by a workload, for example. All of the provided traces are positive examples, meaning that they describe desired behavior. Our approach does not require negative examples. Instead, it generalizes over the examples and uses cost metrics to prevent over-generalization. Because the problem is too complex for traditional monolithic program synthesis techniques, we propose a new combination of optimizing rewrites and syntax-guided program synthesis. The resulting program is correct by construction, so its output will always be able to reproduce the input traces. We evaluate the quality of the programs synthesized when considering various optimization metrics and the synthesizer's efficiency on real-world benchmarks. The results show that our approach can generate useful real-world programs.
- 10 June 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Programming Languages
- Vol. 9 (PLDI) , 1642-1665
Open AccessProgram Synthesis from Partial Traces
We present the first technique to synthesize programs that compose side-effecting functions, pure functions, and control flow, from partial traces containing records of only the side-effecting functions. This technique can be applied to synthesize API composing scripts from logs of calls made to those APIs, or a script from traces of system calls made by a workload, for example. All of the provided traces are positive examples, meaning that they describe desired behavior. Our approach does not require negative examples. Instead, it generalizes over the examples and uses cost metrics to prevent over-generalization. Because the problem is too complex for traditional monolithic program synthesis techniques, we propose a new combination of optimizing rewrites and syntax-guided program synthesis. The resulting program is correct by construction, so its output will always be able to reproduce the input traces. We evaluate the quality of the programs synthesized when considering various optimization metrics and the synthesizer's efficiency on real-world benchmarks. The results show that our approach can generate useful real-world programs.