How and Why Agents Can Identify Bug-Introducing Commits
arXiv:2603.29378v1 Announce Type: new Abstract: \'Sliwerski, Zimmermann, and Zeller (SZZ) just won the 2026 ACM SIGSOFT Impact Award for asking: When do changes induce fixes? Their paper from 2005 served as the foundation for a wide array of approaches aimed at identifying bug-introducing changes (or commits) from fix commits in software repositories. But even after two decades of progress, the best-performing approach from 2025 yields a modest increase of 10 percentage points in F1-score on the most popular Linux kernel dataset. In this paper, we uncover how and why LLM-based agents can substantially advance the state-of-the-art in identifying bug-introducing commits from fix commits. We propose a simple agentic workflow based on searching a set of candidate commits and find that it raise
View PDF
Abstract:Śliwerski, Zimmermann, and Zeller (SZZ) just won the 2026 ACM SIGSOFT Impact Award for asking: When do changes induce fixes? Their paper from 2005 served as the foundation for a wide array of approaches aimed at identifying bug-introducing changes (or commits) from fix commits in software repositories. But even after two decades of progress, the best-performing approach from 2025 yields a modest increase of 10 percentage points in F1-score on the most popular Linux kernel dataset. In this paper, we uncover how and why LLM-based agents can substantially advance the state-of-the-art in identifying bug-introducing commits from fix commits. We propose a simple agentic workflow based on searching a set of candidate commits and find that it raises the F1-score from 0.64 to 0.81 on the most popular Linux kernel dataset, a bigger jump than between the original 2005 method (0.54) and the previous SOTA (0.64). We also uncover why agents are so successful: They derive short greppable patterns from the fix commit diff and message and use them to effectively search and find bug-introducing commits in large candidate sets. Finally, we also discuss how these insights might enable further progress in bug detection, root cause understanding, and repair.
Subjects:
Software Engineering (cs.SE)
Cite as: arXiv:2603.29378 [cs.SE]
(or arXiv:2603.29378v1 [cs.SE] for this version)
https://doi.org/10.48550/arXiv.2603.29378
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Niklas Risse [view email] [v1] Tue, 31 Mar 2026 07:48:27 UTC (83 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
announceinsightagentic
OutSystems Introduces Agentic Systems Engineering to Power Governed, Open Enterprise AI - AiThority
<a href="https://news.google.com/rss/articles/CBMixAFBVV95cUxNWU5mTGVIaXY0YWs0aUJ2aEdvSUxuSWpiRmZMVVJpX2R4dm5pbVdRUVpKZmt6Z1JOY1YxRy1DU0FTZGU0Qk1zVWtCcGJBVzFGVUtuRlBFY0NEYXVtSkZDWTFiSkhlSjM0c0d0VURQRGxMdUhfVjY0eXE0MEZyaFNUdmUzVTdYMU90Z1FxcFhxRzhPVDNiMHpGRWN1dTgtdlVNXy13SXBvMy1rT1NlbURScEhxSk9IRGZ5c201aWZ3cFRjOXNh?oc=5" target="_blank">OutSystems Introduces Agentic Systems Engineering to Power Governed, Open Enterprise AI</a> <font color="#6f6f6f">AiThority</font>
OpenBox
<p> See, verify, and govern every agent action. </p> <p> <a href="https://www.producthunt.com/products/openbox?utm_campaign=producthunt-atom-posts-feed&utm_medium=rss-feed&utm_source=producthunt-atom-posts-feed">Discussion</a> | <a href="https://www.producthunt.com/r/p/1112203?app_id=339">Link</a> </p>
TurboQuant, KIVI, and the Real Cost of Long-Context KV Cache
<h1> I Built a Free KV Cache Calculator for LLM Inference </h1> <p>When people talk about LLM deployment costs, they usually start with model weights.</p> <p>That makes sense, but once you push context length higher, KV cache becomes one of the real bottlenecks. In many long-context setups, it is the<br> dynamic memory cost that quietly starts dominating deployment decisions.</p> <p>I built a small free tool to make that easier to estimate:</p> <p><a href="https://turbo-quant.com/en/kv-cache-calculator" rel="noopener noreferrer">TurboQuant Tools</a></p> <p>It is a practical KV cache calculator for LLM inference. You can use it to estimate memory for:</p> <ul> <li>MHA models</li> <li>GQA models</li> <li>MQA models</li> <li>different context lengths</li> <li>different batch sizes</li> <li>di
Knowledge Map
Connected Articles — Knowledge Graph
This article is connected to other articles through shared AI topics and tags.
More in Self-Evolving AI
OutSystems Introduces Agentic Systems Engineering to Power Governed, Open Enterprise AI - AiThority
<a href="https://news.google.com/rss/articles/CBMixAFBVV95cUxNWU5mTGVIaXY0YWs0aUJ2aEdvSUxuSWpiRmZMVVJpX2R4dm5pbVdRUVpKZmt6Z1JOY1YxRy1DU0FTZGU0Qk1zVWtCcGJBVzFGVUtuRlBFY0NEYXVtSkZDWTFiSkhlSjM0c0d0VURQRGxMdUhfVjY0eXE0MEZyaFNUdmUzVTdYMU90Z1FxcFhxRzhPVDNiMHpGRWN1dTgtdlVNXy13SXBvMy1rT1NlbURScEhxSk9IRGZ5c201aWZ3cFRjOXNh?oc=5" target="_blank">OutSystems Introduces Agentic Systems Engineering to Power Governed, Open Enterprise AI</a> <font color="#6f6f6f">AiThority</font>
[Galaxy Unpacked 2026] Highlights From Galaxy Unpacked: The Beginning of Truly Agentic AI - samsung.com
<a href="https://news.google.com/rss/articles/CBMiugFBVV95cUxOZUdYYldZYUtxN3pTb2c3NGNub2UzM0VsLVZnd3ZTSE1IMFpJeWE3NHdabjY5TFhWem9VSm9PNnNfVGFQN1pEN2lldGpZZWk2dzBIN25VOTFpZjZsTU1TRTFzRk9MdDZSRVd6OFNaNkMzal82aVV0ZWJGMHppSlJMLUdvZVhYRENnQm90Q080NmlVQmJGUGhDWDBTQTg0V3Q1S20zTmdSclh5d0VBQXVaZlBKSF9TdDQ3VlE?oc=5" target="_blank">[Galaxy Unpacked 2026] Highlights From Galaxy Unpacked: The Beginning of Truly Agentic AI</a> <font color="#6f6f6f">samsung.com</font>
Samsung’s agentic AI elevates experience, supports Malaysia’s digital future - The Star
<a href="https://news.google.com/rss/articles/CBMivgFBVV95cUxOQmMzRU9MXzJEVFY3YVB6S2dQMmQwaFlNbmhXMXZ4UUduQmQxcWlacmVyamhOdGF1OGo3STNxQ2h5TUZJeDd6ZnNLRmxiOV9vb0d2MU5CYkVsTGQzWGxRTGE1akdwaFR1TXZoTnJ2dnFQU1lvQ2NhdG1XRDB4YmVDeE9DaXhQVzlsaU1aWU5Yek9wV0FmUFlnMHQxTzNaM1BBRENHQWpQdU1ZMGZDdTdRN1FxdXBWSERtcDdmTkt3?oc=5" target="_blank">Samsung’s agentic AI elevates experience, supports Malaysia’s digital future</a> <font color="#6f6f6f">The Star</font>
Discussion
Sign in to join the discussion
No comments yet — be the first to share your thoughts!