AX·NEWS
Sign in

Software Engineering

Software Engineering news — Thursday 22 October 2026

133 stories from 5 sources, every one in English. Each links to its publisher.

Open in the live feedRSS feedOn a TV

  1. Jank – The native Clojure dialect with seamless C++ interop
    USHacker News Front Page

    Article URL: https://jank-lang.org/ Comments URL: https://news.ycombinator.com/item?id=50202762 Points: 126 # Comments: 18

  2. Docker is weird
    USHacker News Front Page

    Article URL: https://codeandcake.dev/posts/2026-10-22-docker-is-weird Comments URL: https://news.ycombinator.com/item?id=50202681 Points: 778 # Comments: 313

  3. Local Wikipedia: Wikipedia, but only for things a half hour walk from you
    USHacker News Front Page

    Article URL: https://edjefferson.com/localwiki/ Comments URL: https://news.ycombinator.com/item?id=50202285 Points: 1662 # Comments: 253

  4. LLMs are making formal software verification feasible at a much larger scale
    USHacker News Front Page

    Article URL: https://www.anthropic.com/research/formal-verification Comments URL: https://news.ycombinator.com/item?id=50202217 Points: 427 # Comments: 263

  5. Canadians are running out of time to oppose Bill C-22
    USHacker News Front Page

    Article URL: https://www.eff.org/deeplinks/2026/10/canadians-are-running-out-time-oppose-dangerous-c-22-surveillance-bill Comments URL: https://news.ycombinator.com/item?id=50202114 Points: 470 # Comments: 242

  6. We have Traits at Home
    USlobste.rs

    Comments

  7. a hacky fucked up way to portably access errno from outside of c
    USlobste.rs

    Comments

  8. How does Fable 5.1 hide messages in images?
    USHacker News Front Page

    Article URL: https://www.lesswrong.com/posts/WHEQps5PK8LrrcTAb/how-does-fable-5-1-hide-messages-in-images Comments URL: https://news.ycombinator.com/item?id=50201445 Points: 180 # Comments: 61

  9. Jared Kushner Hacked Phone Reveals Secret Negotiations, Millions in Transactions
    USHacker News Front Page

    Article URL: https://www.vanityfair.com/story/jared-kushner-hacked-phone-secret-negotiations Comments URL: https://news.ycombinator.com/item?id=50201259 Points: 201 # Comments: 81

  10. Ask HN: If the models are so good, why doesn't OpenAI just start 100 companies?
    USHacker News Front Page

    Title is a bit of an exaggeration but the question is more: if the frontier models are so good, why even sell them as your primary money maker? Couldn't OpenAI or Anthropic make a lot more money by just starting companies themselves that…

  11. Iron Age salt-mining complex found beneath Hallstatt in Austria
    USHacker News Front Page

    Article URL: https://archaeologymag.com/2026/09/iron-age-salt-mining-complex-beneath-hallstatt/ Comments URL: https://news.ycombinator.com/item?id=50200957 Points: 114 # Comments: 56

  12. Docker is weird
    USlobste.rs

    Comments

  13. The HTML-in-Canvas API origin trial
    USHacker News Front Page

    Article URL: https://developer.chrome.com/blog/html-in-canvas-origin-trial Comments URL: https://news.ycombinator.com/item?id=50200164 Points: 111 # Comments: 49

  14. One of the Greatest Inventions in the History of Human Transport
    USHacker News Front Page

    Article URL: https://humantransit.org/2024/12/one-of-the-greatest-inventions-in-the-history-of-human-transport.html Comments URL: https://news.ycombinator.com/item?id=50200152 Points: 242 # Comments: 125

  15. Quad9 DNS Resolver to exit France
    USlobste.rs

    Comments

  16. The Regression Tests Nobody Writes: Capturing How Software Actually Behaves
    USStack Overflow Blog
  17. Mojo v1.2.0
    USlobste.rs

    Comments

  18. A complete bypass of eMudhra’s 1FA OTP login system
    USHacker News Front Page

    Article URL: https://mastodon.catgirl.cloud/@49016/117475976434068995 Comments URL: https://news.ycombinator.com/item?id=50199757 Points: 129 # Comments: 37

  19. Hedra is a 3D open world game I wrote from scratch while in highschool
    USHacker News Front Page

    Article URL: https://github.com/maxilevi/project-hedra/tree/pre-ai Comments URL: https://news.ycombinator.com/item?id=50199389 Points: 213 # Comments: 41

  20. AI and the Enclosure of the Scientific Commons
    USHacker News Front Page

    Article URL: https://arxiv.org/abs/2610.27251 Comments URL: https://news.ycombinator.com/item?id=50199230 Points: 116 # Comments: 69

  21. What is you opinion on submission quality since the `vibecoding` tag was removed?
    USlobste.rs

    Were concerns about its removal real, or has its absence moderated content to be higher quality? Were there any unexpected consequences? Is anyone willing to admit that their hope for its removal, or fear of its removal was misplaced? Is…

  22. Nvidia OpenShell
    USHacker News Front Page

    Article URL: https://github.com/NVIDIA/OpenShell Comments URL: https://news.ycombinator.com/item?id=50198675 Points: 481 # Comments: 206

  23. Objects, attributes, maps, oh my
    USlobste.rs

    Comments

  24. Expose only share links of a private service with caddy
    USlobste.rs

    Comments

  25. A farewell to Arc browser
    USHacker News Front Page

    Article URL: https://arc.net/ Comments URL: https://news.ycombinator.com/item?id=50197601 Points: 231 # Comments: 210

  26. Getting ready to operate GNU Taler in Germany
    USHacker News Front Page

    Article URL: https://www.taler.net/en/news/2026-13.html Comments URL: https://news.ycombinator.com/item?id=50197404 Points: 345 # Comments: 158

  27. Every AI model has the same "controversial" take on humans
    USHacker News Front Page

    Article URL: https://www.modelcompare.ai/blog/ai-models-controversial-take-on-humans Comments URL: https://news.ycombinator.com/item?id=50197313 Points: 593 # Comments: 563

  28. Overgrown, when plants invade your abandoned tabs
    USHacker News Front Page

    Article URL: https://charliegerard.dev/blog/overgrown-extension/ Comments URL: https://news.ycombinator.com/item?id=50197108 Points: 389 # Comments: 129

  29. Google cleared 300 hectares of Finnish forest
    USHacker News Front Page

    Article URL: https://www.techspot.com/news/114100-google-cleared-300-hectares-finnish-forest-data-center.html Comments URL: https://news.ycombinator.com/item?id=50196837 Points: 274 # Comments: 187

  30. Show HN: Run full iOS 16.5 firmware on Android Devices
    USHacker News Front Page

    https://hackios-web.vercel.app/en Comments URL: https://news.ycombinator.com/item?id=50196718 Points: 498 # Comments: 181

  31. Header Accordions: QPACK amplification attacks against HTTP/3 servers
    USlobste.rs

    Comments

  32. I built a garbage collector for Rust (2023)
    USlobste.rs

    Comments

  33. Quad9 (DNS Resolver) to Exit France
    USHacker News Front Page

    Article URL: https://quad9.net/news/blog/au-revoir-france/ Comments URL: https://news.ycombinator.com/item?id=50195959 Points: 1284 # Comments: 443

  34. MPs moving to restrict gambling ads in Canada
    USHacker News Front Page

    Article URL: https://www.cbc.ca/news/investigates/gambling-ads-restrictions-canada-9.7388888 Comments URL: https://news.ycombinator.com/item?id=50195873 Points: 176 # Comments: 81

  35. eMudhra to Exit global SSL/TLS Certificate Business
    USlobste.rs

    Comments

  36. Script dependencies with Nix
    USlobste.rs

    Comments

  37. What's Getting Pwned
    USHacker News Front Page

    Article URL: https://pwn.watch/ Comments URL: https://news.ycombinator.com/item?id=50195543 Points: 347 # Comments: 161

  38. Show HN: OnKey – I'm a bad singer, so I built an app to show where I'm off-key
    USHacker News Front Page

    Hi all I was pretty terrible at singing, now I’d say I’m bad but not terrible. This is because I’ve been using a singing app (won’t name it here) that scores me on my pitch and timing throughout the song so that I can improve. Lately…

  39. eMudhra to Exit Global SSL/TLS Certificate Business
    USHacker News Front Page

    Article URL: https://emudhra.com/en/press-release/emudhra-to-exit-global-ssl-tls-certificate-business Comments URL: https://news.ycombinator.com/item?id=50195110 Points: 1086 # Comments: 698

  40. The alien space of science: Coherent but cognitively unavailable directions
    USHacker News Front Page

    Article URL: https://arxiv.org/abs/2603.01092 Comments URL: https://news.ycombinator.com/item?id=50195002 Points: 179 # Comments: 69

  41. Crystal 1.22
    USHacker News Front Page

    Article URL: https://crystal-lang.org/2026/10/12/1.22.0-released/ Comments URL: https://news.ycombinator.com/item?id=50194938 Points: 147 # Comments: 70

  42. Woman faces six years in prison over Cash App account she never opened
    USHacker News Front Page

    Article URL: https://www.techspot.com/news/114296-woman-spends-three-nights-jail-faces-six-years.html Comments URL: https://news.ycombinator.com/item?id=50194833 Points: 510 # Comments: 530

  43. Tell your network to explain itself and then some
    USlobste.rs

    Comments

  44. jailbreaking the switch 2
    USlobste.rs

    Comments

  45. Amazon identifies Oct 17 PHP2Shell exploitation prior to public disclosure
    USHacker News Front Page

    Article URL: https://aws.amazon.com/blogs/security/amazon-threat-intelligence-identifies-php2shell-exploitation-prior-to-public-disclosure-in-madpot/ Comments URL: https://news.ycombinator.com/item?id=50194070 Points: 229 # Comments: 81

  46. Xbox wants you to pay 24 to 40 cents per hour to stream games you bought
    USHacker News Front Page

    Article URL: https://arstechnica.com/gaming/2026/10/xbox-wants-you-to-pay-24-to-40-cents-per-hour-to-stream-games-you-already-bought/ Comments URL: https://news.ycombinator.com/item?id=50194009 Points: 331 # Comments: 304

  47. There isn't an easy exploit for this PHP vulnerability
    USlobste.rs

    Comments

  48. How Japanese Dried Bonito Is Made
    USHacker News Front Page

    Article URL: https://kottke.org/26/10/how-japanese-dried-bonito-is-made Comments URL: https://news.ycombinator.com/item?id=50193936 Points: 180 # Comments: 49

  49. Create a Canarytoken. Deploy it somewhere
    USlobste.rs

    Comments

  50. Several Linux kernel vulnerabilities accidentally posted to public mailing list
    USHacker News Front Page

    Article URL: https://www.phoronix.com/news/LKML-New-Trend-Vulnerabilities Comments URL: https://news.ycombinator.com/item?id=50193804 Points: 217 # Comments: 68

  51. The Quake Fan who built the map editor everybody uses
    USHacker News Front Page

    Article URL: https://funcarena.com/articles/the-quake-fan-who-built-the-map-editor-everybody-uses Comments URL: https://news.ycombinator.com/item?id=50193677 Points: 140 # Comments: 17

  52. Three configurable prettyprinters (2023)
    USlobste.rs

    Comments

  53. Two Welsh organisations reprimanded after cyber-attack exposed children’s information
    USlobste.rs

    Comments

  54. Tell HN: I unknowingly broke the PHP RCE embargo. I am sorry.
    USHacker News Front Page

    I posted here about the then-upcoming PHP RCEs related to CVE-2026-109618 & CVE-2026-109619. I appreciate this has had considerable knock-on effects with the schedule for co-ordinated disclosure, and created additional workload. I am truly…

  55. Faster than earcut: triangulating 3.7M map polygons in 489 ms
    USHacker News Front Page

    Article URL: https://globus.software/blog/2026/10/16/cutting-map-polygons/ Comments URL: https://news.ycombinator.com/item?id=50193170 Points: 205 # Comments: 38

  56. CVE-2026-111943: Compromised Intermediate Certificate Authority
    USHacker News Front Page

    Article URL: https://nvd.nist.gov/vuln/detail/cve-2026-111943 Comments URL: https://news.ycombinator.com/item?id=50192900 Points: 276 # Comments: 86

  57. Garmin Revamps and Opens Up Connect Developer API Program
    USlobste.rs

    Not exactly related to programming, but as a Garmin user I've always wanted an API for personal access so I can make my own stuff on top of it. I also really like the fact that they have a tier specifically targeting personal use. My…

  58. Jailbreaking the Switch 2
    USHacker News Front Page

    Article URL: https://pepsipu.com/blog/2026-10-switch2-jailbreak-ns2jb/ Comments URL: https://news.ycombinator.com/item?id=50192536 Points: 729 # Comments: 253

  59. examining the macOS gcc binary
    USlobste.rs

    Comments

  60. Announcing DuckDB 2.0.0 LTS “Cinnamon Teal”
    USlobste.rs

    Comments

  61. OpenAI CLI
    USHacker News Front Page

    Article URL: https://github.com/openai/openai-cli Comments URL: https://news.ycombinator.com/item?id=50191507 Points: 184 # Comments: 87

  62. Extending concurrent separation logic to the hardware level to verify the xv6 OS kernel on RISC-V with AI agents
    USlobste.rs

    Comments

  63. Using a lookup-table to correct an approximation
    USlobste.rs

    Comments

  64. Who Verifies the Builder? Toward Independent Assurance for Agent-Produced Software
    USarXiv cs.SE (Software)

    arXiv:2610.28667v1 Announce Type: new Abstract: Coding agents can now implement a specification, write and run tests, repair failures, and declare the result ready for release. When the same agentic system produces both the software and…

  65. Validating Autoformalized Specifications via Contrapuntal Languages
    USarXiv cs.SE (Software)

    arXiv:2610.30059v1 Announce Type: new Abstract: Formal specifications can make AI-generated code mechanically checkable. Because user intent is typically expressed in natural language rather than formal logic, specifications must first be…

  66. When Agent Evaluation Becomes Unreliable: An Empirical Study of Oracle Failures and Configuration-Dependent Measurement in an LLM Agent Benchmark
    USarXiv cs.SE (Software)

    arXiv:2610.16067v2 Announce Type: replace Abstract: Agent evaluation harnesses are software: they run a test suite, drive a test input generator, and decide outcomes with a test oracle. We audit them for defects a score table cannot show…

  67. PCLA-Bridge: A Framework for Cross-Domain Deployment of CARLA Agents
    USarXiv cs.SE (Software)

    arXiv:2610.28696v1 Announce Type: new Abstract: Most high-performing end-to-end autonomous driving agents (ADAs) are developed for the CARLA Leaderboard, tightly coupling them to CARLA's APIs, sensor layouts, coordinate systems, and…

  68. Benchmarking the Quantum Leap: Auditing LLM Evaluation for Quantum Code Generation
    USarXiv cs.SE (Software)

    arXiv:2610.28678v1 Announce Type: new Abstract: Large language models (LLMs) can generate quantum programs, but reliable evaluation remains difficult because benchmarks differ in task composition, scoring, and failure handling. We evaluate…

  69. Runtime Semantic Discovery for Evolving Action Alphabets
    USarXiv cs.SE (Software)

    arXiv:2610.28682v1 Announce Type: new Abstract: Runtime Verification typically assumes a fixed alphabet of observable actions. This assumption becomes fragile in evolving software systems, where updates, reconfigurations, or architectural…

  70. VerifierBench: Benchmarking the Generation of Executable Verifiers for LLM Agents
    USarXiv cs.SE (Software)

    arXiv:2610.28679v1 Announce Type: new Abstract: Agents need reliable ways to validate their outputs, both when completing tasks and when filtering synthetic training data. We study verifier generation: from the instruction and environment…

  71. VERDICT: Multi-Agent Parallel Modular Verification
    USarXiv cs.SE (Software)

    arXiv:2610.29147v1 Announce Type: new Abstract: Deductive verification scales to large software systems through modular reasoning, where formal contracts summarize the behavior of individual functions and enable their independent…

  72. AI-Based End-to-End Automotive Design and Software Development for SDVs
    USarXiv cs.SE (Software)

    arXiv:2610.29160v1 Announce Type: new Abstract: This paper explores the potential of Artificial Intelligence (AI) to enable end-to-end automotive design and software development for Software-Defined Vehicles (SDVs). Based on our…

  73. RegoMender: A Multi-agent Framework for Automated Rego Policy Repair
    USarXiv cs.SE (Software)

    arXiv:2610.29456v1 Announce Type: new Abstract: Policy-as-Code (PaC) has emerged as a foundational paradigm in cloud-native systems. However, repairing Rego policies remains challenging due to their strict syntax, declarative semantics…

  74. Behavior Beyond Text: Evaluating Refusal Transfer Failure in LLM Agents
    USarXiv cs.SE (Software)

    arXiv:2610.28982v1 Announce Type: cross Abstract: While large language models are increasingly deployed as tool-calling agents, their safety evaluations still focus primarily on their ability to refuse harmful requests in text. We…

  75. Back Up Before You Regret: Measuring Backup Awareness and Automating Backup in Coding Agents
    USarXiv cs.SE (Software)

    arXiv:2610.28934v1 Announce Type: cross Abstract: Coding agents now complete tasks autonomously, modifying real-world state such as artifacts, software environments, and configurations along the way. Yet they show limited backup awareness…

  76. Compilation Is Not Correctness: Scan-by-Scan Evaluation of LLM-Generated PLC Programs
    USarXiv cs.SE (Software)

    arXiv:2610.28675v1 Announce Type: new Abstract: Programmable logic controllers (PLCs) automate industrial processes through repeated scans, each reading inputs, executing control logic, and updating outputs. Engineers write this logic in…

  77. VeeReview: Measuring Build-Verify Pairs in Agent-Authored Pull Requests from a V-Model Perspective
    USarXiv cs.SE (Software)

    arXiv:2610.29143v1 Announce Type: new Abstract: Context: Reviewing a pull request requires verification evidence that addresses the proposed change. Coding agent benchmarks and studies of pull request outcomes do not directly assess this…

  78. Where Should a Stuck Agent Spend Its Next Tokens? Causal Attribution of Inference-Time Resources
    USarXiv cs.SE (Software)

    arXiv:2610.28834v1 Announce Type: new Abstract: Inference-time scaling is often treated as a token-budget problem, but a failed coding agent can seek qualitatively different resources: computation, information, or feedback. We introduce…

  79. Motivation and Contribution in Open Source Software: A Meta-Analytic Investigation
    USarXiv cs.SE (Software)

    arXiv:2610.29199v1 Announce Type: cross Abstract: Research on why people contribute to open source software (OSS) and related open collaboration platforms spans more than two decades, but its findings conflict, and studies often treat the…

  80. Sign Here: Attributing a Source for a More Trustworthy Software Supply Chain
    USarXiv cs.SE (Software)

    arXiv:2610.28794v1 Announce Type: cross Abstract: Software supply chain attacks continue to be on the rise, exploiting the trust that helps open source ecosystems thrive. Recent incidents like the Shai-Hulud worm and the Axios compromise…

  81. Deciding Scale Placement in MXFP4 Dot Products with Integer Arithmetic
    USarXiv cs.PL (Programming)

    arXiv:2610.29445v1 Announce Type: cross Abstract: The Open Compute Project's microscaling (MX) family includes MXFP4, which stores 32 four-bit elements with a shared power-of-two scale. When lowering a dot-product reduction, a compiler can…

  82. Operon: Incremental Construction of Ragged Data via Named Dimensions
    USarXiv cs.PL (Programming)

    arXiv:2511.16080v3 Announce Type: replace Abstract: Modern data processing workflows frequently encounter ragged data: multidimensional collections whose inner lengths vary and are revealed only at runtime. Ragged data is prevalent in…

  83. Benchmarking Coding Agents for System-Level Performance Optimization
    USarXiv cs.SE (Software)

    arXiv:2610.29695v1 Announce Type: new Abstract: Coding agents are becoming an increasingly important paradigm for automating software engineering tasks. However, existing coding benchmarks primarily evaluate agents at the function or…

  84. From Natural Language Intent to Executable Control: Hierarchical Feedback-Guided LLM Planning for Multi-component Cyber-Physical Systems
    USarXiv cs.SE (Software)

    arXiv:2610.22441v1 Announce Type: cross Abstract: Large language models (LLMs) provide a convenient interface for translating natural language commands into task plans for cyber-physical systems (CPSs). However, two gaps hinder their use…

  85. Symmetry-Oriented Testing Framework for Variational Quantum Algorithms
    USarXiv cs.SE (Software)

    arXiv:2610.29053v1 Announce Type: new Abstract: Testing quantum software is challenging because quantum states cannot be directly inspected. Variational quantum algorithms (VQAs) are a particularly important target as they are among the…

  86. CertMoE: Robustness Certification for Mixture-of-Experts LLMs via Routing-Aware Smoothing
    USarXiv cs.SE (Software)

    arXiv:2610.29395v1 Announce Type: cross Abstract: Provable robustness is a cornerstone of trustworthy machine learning, aiming to guarantee model predictions under adversarial perturbations. Existing certification frameworks, inspired by…

  87. How Much Does the Harness Matter, and for Whom? A Multi-Model Study of Context in LLM-Driven Vulnerability Discovery
    USarXiv cs.SE (Software)

    arXiv:2610.28802v1 Announce Type: cross Abstract: How much does an agent harness affect vulnerability discovery, and does its value depend on the model? We study 24 model-runner configurations using an open-source harness on a production…

  88. CloudIR-Bench: A Benchmark for Root Cause Analysis and Mitigation of Cloud Incidents
    USarXiv cs.SE (Software)

    arXiv:2610.29185v1 Announce Type: new Abstract: Root cause analysis (RCA) and mitigation prediction are essential for incident management, enabling the identification of underlying causes of failures and ensuring the reliability of complex…

  89. Metamodel-Guided LLM Decoding for Consistent DSL Generation
    USarXiv cs.SE (Software)

    arXiv:2610.29749v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to generate software engineering artifacts written in domain-specific languages (DSLs). Correct DSL instances usually must comply with not…

  90. TopoMap: A Feature-based Discriminator of the Topographical Regions in the Test Input Space
    USarXiv cs.SE (Software)

    arXiv:2509.03242v3 Announce Type: replace-cross Abstract: Testing Deep Learning (DL)-based systems is an open challenge. Although it is relatively easy to find inputs that cause a DL model to misbehave, the grouping of such inputs by…

  91. Engineering Requirements for Generative AI Agents: The BARD Process Theory
    USarXiv cs.SE (Software)

    arXiv:2610.29741v1 Announce Type: new Abstract: How teams engineer requirements for systems built around Generative AI (GenAI) Agents remains empirically uncharted. Existing Requirements Engineering (RE) research mainly addresses AI and…

  92. On the Effectiveness of Snapshot Testing: An Empirical Study
    USarXiv cs.SE (Software)

    arXiv:2610.29549v1 Announce Type: new Abstract: Software testing is essential for ensuring quality, yet testing complex front-end user interfaces is often time-consuming and difficult. Snapshot testing has emerged as a low-cost regression…

  93. HiddenLens: A Multi-Layer LLM Framework for Detecting and Resolving Hidden Assumptions in Software Requirements
    USarXiv cs.SE (Software)

    arXiv:2610.29996v1 Announce Type: new Abstract: Natural-language software requirements often omit assumptions about performance, operating conditions, user behaviour, and domain constraints, affecting architecture, testing, and deployment…

  94. WEAVE: Weaving Real-World Code Evolution into Dependency-Structured Tasks for Benchmarking and Training Code Agents
    USarXiv cs.SE (Software)

    arXiv:2610.22039v3 Announce Type: replace Abstract: Real-world software engineering rarely consists of isolated changes. Features, migrations, and systematic fixes often unfold across multiple pull requests (PRs), requiring coordinated…

  95. FaultGene: LLM-Assisted Fault-Augmented Test Generation for Hardware-in-the-Loop Validation of Autonomous Driving Systems
    USarXiv cs.SE (Software)

    arXiv:2610.29969v1 Announce Type: new Abstract: Reliable validation of autonomous driving cyber-physical systems requires testing not only nominal driving behavior but also failures arising from faults in sensing and embedded computation…

  96. Do Coding Agents Understand Why Systems Crash---and Why They Don't?
    USarXiv cs.SE (Software)

    arXiv:2610.29332v1 Announce Type: new Abstract: Coding agents are increasingly capable of fixing real-world bugs, yet they still struggle with large systems codebases such as the Linux kernel. To understand why, we test how agents reason…

  97. ORSMT: Unleashing the Potential of Satisfiability Modulo Theories for Semantic Verification and Repair in LLM-Based Optimization
    USarXiv cs.SE (Software)

    arXiv:2610.29145v1 Announce Type: cross Abstract: Large language models increasingly automate optimization modeling from natural language problems, producing written mathematics, solver code and a returned report. Verifying one…

  98. Structure-Aware Equivalence for Evaluating Autoformalized Statements
    USarXiv cs.PL (Programming)

    arXiv:2610.25018v2 Announce Type: replace Abstract: Evaluating autoformalized mathematical statements requires determining whether a candidate preserves the mathematical claim intended by a trusted reference. Existing methods approach this…

  99. Who Approved This? Coding Agents, Human Accounts, and Merge-Gate Evidence at a Fintech Startup
    USarXiv cs.SE (Software)

    arXiv:2610.28683v1 Announce Type: new Abstract: From 3 October, every non-bot merge into our main branch passed a non-author review gate, yet 71 of those 263 merges (27%) rested only on an approval that a coding agent had submitted through…

  100. Learning from Repair Experience: Self-Evolving Agents for Automated Vulnerability Repair
    USarXiv cs.SE (Software)

    arXiv:2605.30105v3 Announce Type: replace Abstract: Large Language Models (LLMs) have shown promise for automated vulnerability repair (AVR), but they still face several limitations, including the lack of intra-vulnerability experience…

  101. Bridging Foundational and Agentic Capabilities of LLMs
    USarXiv cs.SE (Software)

    arXiv:2610.29751v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as agents, yet it remains unclear how their foundational capabilities translate into agentic capabilities. End-to-end scores leave…

  102. ALIAS: Evaluating Performance and Memorization in LLM-Written TLA+ Specifications
    USarXiv cs.SE (Software)

    arXiv:2610.29767v1 Announce Type: cross Abstract: Memorization inflates the benchmark scores of large language models (LLMs), since a model can reproduce answers it saw in training. Researchers test for it with consistent identifier…

  103. Stack Trace-Based Crash Deduplication with Transformer Adaptation
    USarXiv cs.SE (Software)

    arXiv:2508.19449v3 Announce Type: replace Abstract: Automated crash reporting systems generate large volumes of duplicate reports, overwhelming issue-tracking systems and increasing developer workload. Traditional stack trace-based…

  104. The Best Programming Language for Tokenmaxxing: An Investigation of Coding Agent Behavior Across Programming Languages
    USarXiv cs.SE (Software)

    arXiv:2607.22807v2 Announce Type: replace Abstract: Although coding agents are now very effective in a variety of programming languages, this paper first shows that the cost (in tokens) can very significantly by programming language. We…

  105. MockingBird: Context-aware Repository-level Code Translation with Isolated Validation
    USarXiv cs.SE (Software)

    arXiv:2511.21878v3 Announce Type: replace Abstract: Despite advances in repository-level code translation, automated type resolution across differing type systems and translation validation (functional-equivalence checking) remain…

  106. Generating Mitigations for Downstream Projects to Neutralize Upstream Library Vulnerability
    USarXiv cs.SE (Software)

    arXiv:2503.24273v2 Announce Type: replace Abstract: Third-party libraries are essential in software development as they prevent the need for developers to recreate existing functionalities. However, vulnerabilities within these libraries…

  107. SWE-DIVE: Multi-Turn Coding Agent Evaluation with Dynamic User Simulation
    USarXiv cs.SE (Software)

    arXiv:2610.30047v1 Announce Type: new Abstract: Coding agents are typically evaluated using one-shot, well-formulated prompts. Benchmarks such as SWE-bench use existing GitHub issues as input for a coding agent and evaluate whether the…

  108. PAUSE: Search-Free Steering of Coding Agents Before Their First Source-Code Edit
    USarXiv cs.SE (Software)

    arXiv:2610.29870v1 Announce Type: new Abstract: Coding agents can invest substantial effort in repository exploration and testing yet still produce unsuccessful patches. Existing online steering methods review trajectories periodically or…

  109. RegoMender: A Multi-agent Framework for Automated Rego Policy Repair
    USarXiv cs.PL (Programming)

    arXiv:2610.29456v1 Announce Type: cross Abstract: Policy-as-Code (PaC) has emerged as a foundational paradigm in cloud-native systems. However, repairing Rego policies remains challenging due to their strict syntax, declarative semantics…

  110. AssureCode: Structured Justification for Trustworthy Agentic Coding
    USarXiv cs.SE (Software)

    arXiv:2610.29758v1 Announce Type: new Abstract: The use of AI-based tools in software development is rapidly changing how software is produced, enabling large volumes of code to be generated with limited human implementation effort…

  111. SANE: Automated Scorer-Specific Metamorphic Testing for LLM Judges
    USarXiv cs.SE (Software)

    arXiv:2610.28886v1 Announce Type: cross Abstract: LLM judges increasingly mediate benchmark evaluation, model selection, data curation, and training. Their decisions are useful only when each judge responds reliably to changes affecting…

  112. Lean4Agent: Formal Modeling and Verification for Agent Workflow and Trajectory
    USarXiv cs.SE (Software)

    arXiv:2606.06523v3 Announce Type: replace-cross Abstract: Equipping Large Language Models (LLMs) to execute reliable multi-step workflows has become a central challenge in artificial intelligence. Despite recent advances in LLMs' agentic…

  113. Who Verifies the Agent's Success Claim? Self-Report Leakage in GUI-Agent Completion Judging
    USarXiv cs.SE (Software)

    arXiv:2610.29609v1 Announce Type: new Abstract: In automation pipelines, a GUI agent's confident success report can let downstream stages proceed even when the recorded execution trace does not show that the agent produced the requested…

  114. PatchRisk: Forecasting Future Vulnerability Exposure in Open-Source Dependency Networks
    USarXiv cs.SE (Software)

    arXiv:2609.13719v2 Announce Type: replace-cross Abstract: Open-source software ecosystems are web-scale dependency networks. A downstream package can become exposed to security risk not because its own source code changes, but because one…

  115. Multi-agent LLMs on the Cloud-Edge-IoT Continuum: A Systematic Mapping Study on Architectures, Deployment, and Evaluation
    USarXiv cs.SE (Software)

    arXiv:2610.28702v1 Announce Type: new Abstract: LLM applications are increasingly built as systems of cooperating components rather than as single prompt-response pipelines. IoT applications add constraints of their own, because sensing…

  116. MockingBird: Context-aware Repository-level Code Translation with Isolated Validation
    USarXiv cs.PL (Programming)

    arXiv:2511.21878v3 Announce Type: replace-cross Abstract: Despite advances in repository-level code translation, automated type resolution across differing type systems and translation validation (functional-equivalence checking) remain…

  117. VeruSteer: Learning What to Repair Next in Verus
    USarXiv cs.SE (Software)

    arXiv:2610.29755v1 Announce Type: new Abstract: LLM-based verification systems repair Rust proofs by revising programs in response to Verus diagnostics. When several error types are reported, pipelines such as AutoVerus and VeruSAGE select…

  118. Turning Quantum Compiler Configuration Selection Upside Down: A Top-Down Paradigm
    USarXiv cs.SE (Software)

    arXiv:2610.29170v1 Announce Type: cross Abstract: Selecting an effective quantum compiler configuration requires coordinated decisions over both hardware targets and compiler settings, with the ultimate goal of improving circuit execution…

  119. Properties with Holes: Meta-Property-Based Testing of Data-Intensive Computing Frameworks
    USarXiv cs.SE (Software)

    arXiv:2606.11132v2 Announce Type: replace Abstract: Data-intensive computing frameworks such as Apache Spark and Flink keep expanding their APIs with new data types, expressions, and operators. Their most damaging bugs return silently…

  120. Runtime Semantic Discovery for Evolving Action Alphabets
    USarXiv cs.PL (Programming)

    arXiv:2610.28682v1 Announce Type: cross Abstract: Runtime Verification typically assumes a fixed alphabet of observable actions. This assumption becomes fragile in evolving software systems, where updates, reconfigurations, or…

  121. TileCas: Cascading Kernel Development Across Programming Abstractions
    USarXiv cs.SE (Software)

    arXiv:2610.14740v2 Announce Type: replace Abstract: Programming abstractions have traditionally been designed for humans, but code generation is increasingly performed by models and autonomous agents. We investigate abstractions for…

  122. VeriEvolve: Evaluator-First Evolution for Tool-Using Agents
    USarXiv cs.SE (Software)

    arXiv:2610.29005v1 Announce Type: new Abstract: A central obstacle to self-improving agents is the absence of a reliable fitness signal for realistic stateful tasks. We introduce \textsc{VeriEvolve}, an evaluator-first evolution framework…

  123. The Hitchhiker's Guide to Program Analysis, Part III: Mostly Harmless LLMs
    USarXiv cs.SE (Software)

    arXiv:2606.15122v2 Announce Type: replace Abstract: Filtering out a static-analysis warning asserts that no feasible execution can trigger the reported error, whereas confirming a bug requires only one that does. Recent work uses LLMs to…

  124. Code Comprehensor: Hierarchical Documentation and Cross-Modal Retrieval for Large Repositories
    USarXiv cs.SE (Software)

    arXiv:2610.30016v1 Announce Type: new Abstract: Understanding large, complex, and rapidly evolving code bases remains a core challenge for software engineering at scale, hindering onboarding, maintenance, refactoring, and impact analysis…

  125. Multiobjective Preexpectation Reasoning for Probabilistic Programs
    USarXiv cs.PL (Programming)

    arXiv:2608.13268v2 Announce Type: replace Abstract: Probabilistic programs with nondeterminism model planning problems in which a strategy typically resolves the nondeterminism to meet a specification. We study the multiobjective setting…

  126. Reference Manual of MEDiml
    USarXiv cs.SE (Software)

    arXiv:2610.29666v1 Announce Type: new Abstract: Radiomics is the high-throughput extraction of quantitative features (e.g., tumor shape, intensity distributions, and texture) from medical images to characterize tissues and uncover disease…

  127. Controlling Variability in~Neuroimaging Analysis Pipelines with~Software Product Lines
    USarXiv cs.SE (Software)

    arXiv:2610.29821v1 Announce Type: new Abstract: Magnetic resonance imaging (MRI) is an acquisition technique used for medical diagnosis. It is notably used for structural and functional MRI (or fMRI) image analysis. MRI data is known to be…

  128. SAKURA: Serving Attention Key-Value State Under Rate Adaptation for Private Image Editing on Phones
    USarXiv cs.SE (Software)

    arXiv:2610.29733v1 Announce Type: new Abstract: Diffusion transformers are widely used in image-editing services. To preserve both efficiency and privacy, existing systems commonly rely on cloud-device collaboration. Keeping…

  129. DynaCI: Generating GitHub Actions Workflows via Dynamic Analysis
    USarXiv cs.SE (Software)

    arXiv:2610.29890v1 Announce Type: new Abstract: Continuous Integration (CI) is an essential practice that automatically validates code changes through builds and tests. However, configuring CI workflows remains challenging, as modern…

  130. The recently proposed o(n log n) integer multiplication algorithm [pdf]
    USHacker News Front Page

    Article URL: https://web.maths.unsw.edu.au/~davidharvey/research/subnlogn.pdf Comments URL: https://news.ycombinator.com/item?id=50190455 Points: 293 # Comments: 251

  131. WorldTUI: I trained a 360M model to pretend to be a terminal
    USHacker News Front Page

    Article URL: https://simedw.com/2026/10/21/world-model-terminal/ Comments URL: https://news.ycombinator.com/item?id=50190363 Points: 613 # Comments: 183

  132. Turning IPv6 tunnels into programmable delay lines for pulsing DoS
    USlobste.rs

    Comments

  133. Epic Games Inc v Apple Inc
    USHacker News Front Page

    Article URL: https://www.judgments.fedcourt.gov.au/judgments/Judgments/fca/single/2026/2026fca1552 Comments URL: https://news.ycombinator.com/item?id=50190168 Points: 112 # Comments: 64