Dynamic Cogeneration of Bug Reproduction Test in Agentic Program Repair
arXiv:2601.19066v2 Announce Type: replace Abstract: Bug Reproduction Tests (BRTs) have been used in many Automated Program Repair (APR) systems, primarily for validating promising fixes and aiding fix generation. In practice, when developers submit a patch, they often implement the BRT alongside the fix. Our experience deploying agentic APR reveals that developers similarly desire a BRT within AI-generated patches to increase their confidence. However, canonical APR systems tend to generate BRTs and fixes separately, and focus on producing only the fix in the final patch. In this paper, we study agentic APR in the context of cogeneration, where the APR agent is instructed to generate both a fix and a BRT in the same patch. We evaluate the effectiveness of different cogeneration strategies
View PDF HTML (experimental)
Abstract:Bug Reproduction Tests (BRTs) have been used in many Automated Program Repair (APR) systems, primarily for validating promising fixes and aiding fix generation. In practice, when developers submit a patch, they often implement the BRT alongside the fix. Our experience deploying agentic APR reveals that developers similarly desire a BRT within AI-generated patches to increase their confidence. However, canonical APR systems tend to generate BRTs and fixes separately, and focus on producing only the fix in the final patch. In this paper, we study agentic APR in the context of cogeneration, where the APR agent is instructed to generate both a fix and a BRT in the same patch. We evaluate the effectiveness of different cogeneration strategies on 120 human-reported bugs at Google and characterize different cogeneration strategies by their influence on APR agent behavior. We develop and evaluate patch selectors that account for test change information to select patches with plausible fixes (and plausible BRTs). Finally, we analyze the root causes of failed cogeneration trajectories. Importantly, we show that cogeneration allows the APR agent to generate BRTs for at least as many bugs as a dedicated BRT agent, without compromising the generation rate of plausible fixes, thereby reducing engineering effort in maintaining and coordinating separate generation pipelines for fix and BRT at scale.
Subjects:
Software Engineering (cs.SE); Artificial Intelligence (cs.AI)
Cite as: arXiv:2601.19066 [cs.SE]
(or arXiv:2601.19066v2 [cs.SE] for this version)
https://doi.org/10.48550/arXiv.2601.19066
arXiv-issued DOI via DataCite
Submission history
From: Runxiang Cheng [view email] [v1] Tue, 27 Jan 2026 01:02:57 UTC (257 KB) [v2] Tue, 31 Mar 2026 05:36:04 UTC (334 KB)
Sign in to highlight and annotate this article
Conversation starters
Daily AI Digest
Get the top 5 AI stories delivered to your inbox every morning.
More about
announceproductreport
Exclusive | The Sudden Fall of OpenAI’s Most Hyped Product Since ChatGPT - WSJ
<a href="https://news.google.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?oc=5" target="_blank">Exclusive | The Sudden Fall of OpenAI’s Most Hyped Product Since ChatGPT</a> <font color="#6f6f6f">WSJ</font>
Exclusive | The Sudden Fall of OpenAI’s Most Hyped Product Since ChatGPT - WSJ
<a href="https://news.google.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?oc=5" target="_blank">Exclusive | The Sudden Fall of OpenAI’s Most Hyped Product Since ChatGPT</a> <font color="#6f6f6f">WSJ</font>
Hershey applies AI across its supply chain operations
Artificial intelligence is moving beyond software and further into the physical side of business. Companies in food production and logistics are starting to use data systems to support day-to-day decisions, not long-term planning. That change is visible in The Hershey Company’s latest strategy update. At its Investor Day, the company said it plans to use […] The post Hershey applies AI across its supply chain operations appeared first on AI News .
Knowledge Map
Connected Articles — Knowledge Graph
This article is connected to other articles through shared AI topics and tags.
More in Research Papers
AI Inspires New Research Topics In Materials Science - miragenews.com
<a href="https://news.google.com/rss/articles/CBMihwFBVV95cUxQRlVFdkRBaHRvYkJJdFRlMTZmajEzeFRPU0hGWWdfbi02V1FnTUdVQ2pmY2VZLUV2NlB4V3BFdEVlSVZkUlhRSTZaNWFKMmcyWXJYbnNqbUhMTmp0NnFtMEppOXlPZkJSNHJfck5VSEVYcmUtX1k2QkJlR1BvUEdTTkp3UmlYRkk?oc=5" target="_blank">AI Inspires New Research Topics In Materials Science</a> <font color="#6f6f6f">miragenews.com</font>
From brain scans to alloys: Teaching AI to make sense of complex research data - Penn State University
<a href="https://news.google.com/rss/articles/CBMiwAFBVV95cUxPZDFHdkptQ2VUM2hmWjhqQkxoRnBiTWoxMXRRR21MUG5TamdUMlFRWmhvYVNHaFVNREVKU3VmSnVOdDVZYnNLb2ppYXRVRTZmVFVMV1pLTlVhUm9ybTNZbGtvZTdIMnIyMHNpOEk5aU9TSmxxS2Y4V2MwazYwY3JlX1Axbk1nd3pfcWhFdUJaaDJWRXJaMFIyTTROcmFHeXI3ZzFudXJ2M1h6UHI1LW1Ca1dta2RkM3BiYndocGk3Yjg?oc=5" target="_blank">From brain scans to alloys: Teaching AI to make sense of complex research data</a> <font color="#6f6f6f">Penn State University</font>
Locating Risk: Task Designers and the Challenge of Risk Disclosure in RAI Content Work
arXiv:2505.24246v4 Announce Type: replace Abstract: As AI systems are increasingly tested and deployed in open-ended and high-stakes domains, crowdworkers are often tasked with responsible AI (RAI) content work. These tasks include labeling violent content, moderating disturbing text, or simulating harmful behavior for red teaming exercises to shape AI system behaviors. While prior research efforts have highlighted the risks to worker well-being associated with RAI content work, far less attention has been paid to how these risks are communicated to workers by task designers or individuals who design and post RAI tasks. Existing transparency frameworks and guidelines, such as model cards, datasheets, and crowdworksheets, focus on documenting model information and dataset collection process
Togedule: Scheduling Meetings with Large Language Models and Adaptive Representations of Group Availability
arXiv:2505.01000v5 Announce Type: replace Abstract: Scheduling is a perennial-and often challenging-problem for many groups. Existing tools are mostly static, showing an identical set of choices to everyone, regardless of the current status of attendees' inputs and preferences. In this paper, we propose Togedule, an adaptive scheduling tool that uses large language models to dynamically adjust the pool of choices and their presentation format. With the initial prototype, we conducted a formative study (N=10) and identified the potential benefits and risks of such an adaptive scheduling tool. Then, after enhancing the system, we conducted two controlled experiments, one each for attendees and organizers (total N=66). For each experiment, we compared scheduling with verbal messages, shared c
Discussion
Sign in to join the discussion
No comments yet — be the first to share your thoughts!