AX·NEWS
Sign in

Software Engineering

Software Engineering news — Friday 09 October 2026

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

Open in the live feedRSS feedOn a TV

  1. Clinical trial of a prion disease drug candidate begins enrolling participants
    USHacker News Front Page

    Article URL: https://www.broadinstitute.org/news/clinical-trial-prion-disease-drug-candidate-begins-enrolling-participants Comments URL: https://news.ycombinator.com/item?id=50028027 Points: 128 # Comments: 31

  2. Compiling Rust to readable C with Eurydice
    USHacker News Front Page

    Article URL: https://lwn.net/Articles/1055211/ Comments URL: https://news.ycombinator.com/item?id=50027853 Points: 125 # Comments: 35

  3. Lifeguard: A static analyzer for Python lazy imports compatibility
    USlobste.rs

    Comments

  4. The importance of communities around software
    USlobste.rs

    Comments

  5. Cloudflare shutting down Deno is news, not just PR
    USlobste.rs

    Requesting the currently-removed post for https://deno.com/blog/cloudflare be restored. Thread: https://lobste.rs/s/8hauxs/deno_is_joining_cloudflare My reasoning: It isn't just PR, but significant tech news that Cloudflare is buying up…

  6. YouTuber Says Cops Visited Him After He Built a Flock-Style Camera to Track Cops
    USHacker News Front Page

    Article URL: https://gizmodo.com/youtuber-says-cops-paid-him-a-visit-after-he-built-flock-style-camera-to-track-cops-2000824306 Comments URL: https://news.ycombinator.com/item?id=50026555 Points: 599 # Comments: 325

  7. A Practical Guide to “Plug＆Pwn” for Pentesters and Defenders
    USlobste.rs

    Comments

  8. No Man Is an Island
    USHacker News Front Page

    Article URL: https://borretti.me/article/no-man-is-an-island Comments URL: https://news.ycombinator.com/item?id=50025935 Points: 212 # Comments: 114

  9. Branches in branch-free code
    USlobste.rs

    Comments

  10. How To Write Shared Libraries (2011)
    USlobste.rs

    Comments

  11. Microsoft-Decision-1, our model for fast decision-making
    USHacker News Front Page

    Article URL: https://commandline.microsoft.com/microsoft-decision-1-model-foundry/ Comments URL: https://news.ycombinator.com/item?id=50024913 Points: 157 # Comments: 56

  12. M7.6 Earthquake in Panama
    USHacker News Front Page

    Article URL: https://earthquake.usgs.gov/earthquakes/eventpage/us6000u18k/executive Comments URL: https://news.ycombinator.com/item?id=50024669 Points: 139 # Comments: 36

  13. Show HN: Carrier-Explode: iPhone, Pixel and Galaxy carrier settings decoded
    USHacker News Front Page

    Showing off carrier-explode, one of my side projects that continuously archives carrier settings for all major phone brands. carrier-explode also contains decoders and explanations for all the common baseband configurations, etc. There’s…

  14. Equality Saturation: An “Incomplete” Project
    USlobste.rs

    Comments

  15. Vectorized CLZ and CTZ
    USlobste.rs

    Comments

  16. What mathematicians should know about the Lean Theorem Prover: reliability ＆ AI
    USHacker News Front Page

    Article URL: https://terrytao.wordpress.com/2026/10/09/what-mathematicians-should-know-about-the-lean-theorem-proverquestions-of-reliability-and-ai/ Comments URL: https://news.ycombinator.com/item?id=50024090 Points: 165 # Comments: 43

  17. Show HN: The rarest tech books and docs you've probably never read
    USHacker News Front Page

    Article URL: https://readrare.com/ Comments URL: https://news.ycombinator.com/item?id=50024055 Points: 138 # Comments: 51

  18. Scam American companies are using to manipulate ingredient lists
    USHacker News Front Page

    Article URL: https://twitter.com/WallStreetApes/status/2108594998656807078 Comments URL: https://news.ycombinator.com/item?id=50023995 Points: 161 # Comments: 173

  19. Two Futures for LLMs in Mathematics
    USlobste.rs

    Comments

  20. Python 3.15.0
    USlobste.rs

    Comments

  21. Typesafe AI raises $870M at $7.5B
    USHacker News Front Page

    Article URL: https://typesafe.ai/blog/series-ai Comments URL: https://news.ycombinator.com/item?id=50023450 Points: 413 # Comments: 329

  22. Triple-A Minesweeper
    USHacker News Front Page

    Article URL: https://minesweeper.mikelacher.com/ Comments URL: https://news.ycombinator.com/item?id=50022292 Points: 1330 # Comments: 265

  23. Unison Cloud is now open source
    USlobste.rs

    Comments

  24. I guess I'm using WebP now?
    USHacker News Front Page

    Article URL: https://anderegg.ca/2026/10/08/i-guess-im-using-webp-now Comments URL: https://news.ycombinator.com/item?id=50021989 Points: 117 # Comments: 133

  25. Five months treating bugs like patients and coding agents like a medical team
    USHacker News Front Page

    Article URL: https://www.cockroachlabs.com/blog/experiment-running-hospital-code/ Comments URL: https://news.ycombinator.com/item?id=50021899 Points: 182 # Comments: 76

  26. Germany transforms former coal mines into Europe's largest lake landscape
    USHacker News Front Page

    Article URL: https://www.euronews.com/2026/04/14/almost-like-lake-como-germany-transforms-former-coal-mines-into-europes-largest-lake-lands Comments URL: https://news.ycombinator.com/item?id=50021540 Points: 169 # Comments: 94

  27. A Treatise on Model Oriented Programming Languages
    USStack Overflow Blog
  28. Can you use autoregressive diffusion to generate market data?
    USHacker News Front Page

    Article URL: https://blog.janestreet.com/can-you-use-autoregressive-diffusion-to-generate-market-data/ Comments URL: https://news.ycombinator.com/item?id=50021410 Points: 166 # Comments: 52

  29. Imposing Sanctions on the International Criminal Court
    USHacker News Front Page

    Article URL: https://www.state.gov/releases/office-of-the-spokesman/2026/10/imposing-sanctions-on-the-international-criminal-court/ Comments URL: https://news.ycombinator.com/item?id=50021403 Points: 122 # Comments: 121

  30. Python 3.15.0
    USHacker News Front Page

    Article URL: https://www.python.org/downloads/release/python-3150/ Comments URL: https://news.ycombinator.com/item?id=50021127 Points: 215 # Comments: 40

  31. US imposes sanctions on ICC hours after former judge wins Nobel Peace Prize
    USHacker News Front Page

    Article URL: https://www.reuters.com/world/us-imposes-sanctions-international-criminal-court-hours-after-former-judge-wins-2026-10-09/ Comments URL: https://news.ycombinator.com/item?id=50021066 Points: 308 # Comments: 159

  32. A tale of four theorem provers, or: A (reasonably) opinionated comparison of Isabelle/HOL, Lean, HOL4, and Agda
    USlobste.rs

    Comments

  33. Why Are Coding Agents So Dumb?
    USlobste.rs

    Comments

  34. Yandex Takes a Second Data Center Hit in 48 Hours
    USHacker News Front Page

    Article URL: https://united24media.com/war-in-ukraine/yandex-takes-a-second-data-center-hit-in-48-hours-now-its-biggest-russian-site-is-damaged-23277 Comments URL: https://news.ycombinator.com/item?id=50020927 Points: 167 # Comments: 164

  35. "Robot" Is A Social Construct: Why Your Dishwasher Is Not A Robot
    USlobste.rs

    Comments

  36. Deepthi Sigireddi from Supabase
    USlobste.rs

    Comments

  37. 'Wallace and Gromit,' 90% Alone
    USHacker News Front Page

    Article URL: https://animationobsessive.substack.com/p/wallace-and-gromit-90-alone Comments URL: https://news.ycombinator.com/item?id=50020533 Points: 248 # Comments: 38

  38. Spinlocks Considered Harmful (2020)
    USlobste.rs

    Comments

  39. Deno is joining Cloudflare
    USlobste.rs

    Comments

  40. Our $445M Series D
    USHacker News Front Page

    Article URL: https://oxide.computer/blog/our-445m-series-d Comments URL: https://news.ycombinator.com/item?id=50020014 Points: 675 # Comments: 303

  41. Deno Is Joining Cloudflare
    USHacker News Front Page

    Article URL: https://deno.com/blog/cloudflare Comments URL: https://news.ycombinator.com/item?id=50019911 Points: 1324 # Comments: 682

  42. HIP and ROCm as first-class citizens in Guix
    USlobste.rs

    Comments

  43. What are you doing this weekend?
    USlobste.rs

    Feel free to tell what you plan on doing this weekend and even ask for help or feedback. Please keep in mind it’s more than OK to do nothing at all too!

  44. Iranian campaign planted fake articles in real U.S. publications using ChatGPT
    USHacker News Front Page

    https://archive.is/EFOhL Comments URL: https://news.ycombinator.com/item?id=50019455 Points: 152 # Comments: 134

  45. A minimal kernel in Swift, running in QEMU
    USlobste.rs

    Comments

  46. There are many themes, but this one is yours
    USlobste.rs

    Comments

  47. Reverse Engineer Anything
    USlobste.rs

    One of the few positive side effects of the grand theft that is AI is that proprietary software will now become technically unviable. Comments

  48. The making of a very fast SPI flasher
    USlobste.rs

    Comments

  49. Pointing AI at archives found a forgotten meteorite, lost rhinos, and more
    USHacker News Front Page

    Article URL: https://jessewaites.com/blog/post/i-pointed-ai-at-400-years-of-archives/ Comments URL: https://news.ycombinator.com/item?id=50019056 Points: 165 # Comments: 83

  50. Programming Isn’t Special
    USlobste.rs

    Comments

  51. Let your AI agents paint big arrows, boxes and text on your screen
    USHacker News Front Page

    Article URL: https://github.com/franzenzenhofer/big-arrow-on-the-screen Comments URL: https://news.ycombinator.com/item?id=50018817 Points: 385 # Comments: 169

  52. Nobel Peace Prize for 2026 to Navanethem "NAVI" Pillay
    USHacker News Front Page

    Article URL: https://www.nobelprize.org/prizes/peace/2026/press-release/ Comments URL: https://news.ycombinator.com/item?id=50018420 Points: 416 # Comments: 215

  53. OpenAI fires three safety researchers for "mishandling research information"
    USHacker News Front Page

    Later: https://www.cnbc.com/2026/10/09/openai-fired-researchers-ai-... Comments URL: https://news.ycombinator.com/item?id=50018350 Points: 299 # Comments: 197

  54. I'm in a Meeting
    USHacker News Front Page

    Article URL: https://iminafleeting.com/ Comments URL: https://news.ycombinator.com/item?id=50018088 Points: 930 # Comments: 260

  55. Programming Isn't Special
    USHacker News Front Page

    Article URL: https://blog.glyph.im/2026/10/programming-isnt-special.html Comments URL: https://news.ycombinator.com/item?id=50017357 Points: 201 # Comments: 229

  56. Taking a look under your agent’s hood
    USStack Overflow Blog

    Ryan is joined by Yanbing Li, Chief Product Officer at Datadog, to talk about applying observability to non-deterministic AI agents, blurring the boundaries between software development and production workflows, and navigating emerging…

  57. en-html.org is a Scam Site
    USlobste.rs

    Comments

  58. Nix wrote half of my debugger
    USHacker News Front Page

    Article URL: https://fzakaria.com/2026/10/07/nix-wrote-half-of-my-debugger Comments URL: https://news.ycombinator.com/item?id=50017247 Points: 223 # Comments: 53

  59. Mxc: Microsoft Execution Containers version 1.0.0
    USHacker News Front Page

    Article URL: https://blogs.windows.com/windowsdeveloper/2026/10/07/microsoft-execution-containers-policy-driven-containment-for-ai-agents/ Comments URL: https://news.ycombinator.com/item?id=50016956 Points: 215 # Comments: 61

  60. Deeper dive: Keyboard differences between Windows and Macs
    USlobste.rs

    Comments

  61. MXC - a sandboxed code execution system
    USHacker News Front Page

    Article URL: https://github.com/microsoft/mxc Comments URL: https://news.ycombinator.com/item?id=50016489 Points: 172 # Comments: 78

  62. Reducing undefined behavior in the C language
    USlobste.rs

    Comments

  63. Show HN: Quake ported to safe Rust, playable in browser
    USHacker News Front Page

    Article URL: https://quake-srp.pages.dev/ Comments URL: https://news.ycombinator.com/item?id=50016312 Points: 196 # Comments: 156

  64. Efficient and Scalable Provenance Tracking for LLM-Generated Code Snippets
    USarXiv cs.SE (Software)

    arXiv:2605.28510v3 Announce Type: replace Abstract: Large language models (LLMs) for code completion and generation are increasingly used in software development, yet they may reproduce training examples verbatim and without authorship…

  65. Governed Human-AI Prioritization Under Uncertainty: Adaptive Estimation and Dependency-Constrained Portfolio Selection
    USarXiv cs.SE (Software)

    arXiv:2609.10648v2 Announce Type: replace Abstract: AI-native software engineering increasingly combines human judgment, historical analogy, parametric estimation, and AI-generated forecasts in the same prioritization decision. We study…

  66. Understanding the Hierarchical Structure and Functional Landscape of the Model Context Protocol Ecosystem
    USarXiv cs.SE (Software)

    arXiv:2610.05319v2 Announce Type: replace Abstract: AI agents increasingly rely on tools exposed through the Model Context Protocol (MCP) to complete user tasks. Hundreds of thousands of MCP servers are listed across marketplaces, yet they…

  67. Neural Network Verification for Deep Joint Source-Channel Coding
    USarXiv cs.SE (Software)

    arXiv:2610.11994v1 Announce Type: new Abstract: Deep joint source-channel coding (DeepJSCC) transmits data end-to-end over wireless channels using a neural encoder-decoder, but reconstruction quality can degrade sharply under adversarial…

  68. Forms of LLM-Integrated Applications from LLM-Chats to Autonomous AI Agent System
    USarXiv cs.SE (Software)

    arXiv:2610.11899v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly embedded as components in software systems, marketed under labels such as chatbot, copilot, retrieval-augmented generation, workflow, coding…

  69. PropGen: Automated Property Generation for Property-Based Testing of Mobile Apps
    USarXiv cs.SE (Software)

    arXiv:2604.13463v2 Announce Type: replace Abstract: Mobile apps often suffer from functional bugs that do not cause crashes but instead manifest as incorrect behaviors under specific user interactions. Such bugs are difficult to detect by…

  70. Imperative Interference: Social Register Shapes Instruction Topology in Large Language Models
    USarXiv cs.SE (Software)

    arXiv:2603.25015v2 Announce Type: replace-cross Abstract: System prompt instructions that cooperate in English compete in Spanish, with the same semantic content, but opposite interaction topology. We present instruction-level ablation…

  71. IRONPROOF: COBOL-to-Python Transpilation with SMT-Based Equivalence Checking
    USarXiv cs.SE (Software)

    arXiv:2610.11073v1 Announce Type: new Abstract: Translating COBOL to a modern language can change what a program computes, and LLM translations carry no guarantee of equivalence. We present IRONPROOF, which parses COBOL into an…

  72. SoK: Are LLMs Reliable at Source Code Recovery? A Taxonomy and Empirical Evaluation
    USarXiv cs.SE (Software)

    arXiv:2610.11556v1 Announce Type: cross Abstract: Effective source recovery is critical to security applications such as malware analysis, vulnerability assessment, and legacy maintenance. Large Language Models (LLMs) are reshaping this…

  73. ObliVul: Alert-Conditioned Safety Obligation Modeling and Bidirectional Counterfactual Validation for Code Vulnerability Detection
    USarXiv cs.SE (Software)

    arXiv:2610.11801v1 Announce Type: new Abstract: In real-world software development, the primary challenge in vulnerability detection is often not finding suspicious code, but identifying which alerts among the large number of candidate…

  74. Chronos Enables Code Agents to Reason over Software Evolution
    USarXiv cs.SE (Software)

    arXiv:2610.11578v1 Announce Type: new Abstract: Historical pull requests record the design decisions, compatibility constraints, and implementation patterns behind a codebase's current state. Experience relevant to a new task can span…

  75. Agent4RE: A Self-Refining Multi-agent Framework for End-to-End Software Requirements Engineering and Benchmarking
    USarXiv cs.SE (Software)

    arXiv:2610.10628v1 Announce Type: new Abstract: Existing LLM-based approaches for software Requirements Engineering (RE) typically rely on basic prompting strategies or rudimentary agent collaboration, under-utilizing the full potential of…

  76. NosRacer: Dynamic Detection of Race Conditions in On-Device Network Operating Systems
    USarXiv cs.SE (Software)

    arXiv:2610.11875v1 Announce Type: cross Abstract: Commercial on-device network operating systems (NOSes) run complex control planes in production routers and switches, where configuration update tasks are executed by multiple loosely…

  77. Runnable Commit Untangling for Coding Agents
    USarXiv cs.SE (Software)

    arXiv:2610.11593v1 Announce Type: new Abstract: Coding agents produce large, tangled patches that mix multiple development purposes, making the code hard to review and maintain. Commit untangling offers the promise of organizing such large…

  78. PyCache Trap: The Inspection-Execution Gap in Agent Skill Scanners
    USarXiv cs.SE (Software)

    arXiv:2610.10612v1 Announce Type: cross Abstract: Agent skills combine instructions with executable resources, giving third-party packages access to an agent's runtime. Existing skill scanners inspect documentation and visible source, but…

  79. SWE-Journey: Towards More Realistic Evaluation of Coding Assistants through Long-Horizon, Multi-Turn Interaction
    USarXiv cs.SE (Software)

    arXiv:2610.11559v1 Announce Type: cross Abstract: Coding assistants such as Claude Code and Codex have become a major application of LLM agents, yet existing benchmarks remain far from real-world use, particularly in task horizon and…

  80. PolyCodeEval: Benchmarking Multilingual Code Generation from Functions to Repositories
    USarXiv cs.SE (Software)

    arXiv:2610.11618v1 Announce Type: new Abstract: As large language models increasingly move toward repository-level software engineering, existing code-generation benchmarks remain fragmented across language coverage, task granularity, and…

  81. PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
    USarXiv cs.SE (Software)

    arXiv:2602.20717v2 Announce Type: replace Abstract: As Large Language Models (LLMs) are increasingly integrated into software development workflows, their trustworthiness has become a critical concern. However, in dependency recommendation…

  82. Where Do the Tokens Go? Understanding and Reducing Costs in LLM Agents for Vulnerability Discovery
    USarXiv cs.SE (Software)

    arXiv:2610.11602v1 Announce Type: cross Abstract: LLM agents can spend millions of tokens during vulnerability discovery without producing a working proof of concept (PoC). What consumes that budget, and why does it fail to produce…

  83. SoK: Failure Modes in Common Criteria Product Evaluation - A Taxonomy and Design-for-Evaluability Guidance
    USarXiv cs.SE (Software)

    arXiv:2610.10644v1 Announce Type: cross Abstract: The Common Criteria (CC; ISO/IEC 15408) is the principal international framework for evaluating the security of IT products, and its certificates gate procurement across government…

  84. WorldBench: Evaluating LLMs on Three.js Voxel World Generation
    USarXiv cs.SE (Software)

    arXiv:2610.10622v1 Announce Type: cross Abstract: Large language models can now write complete, interactive 3D worlds as code, but grading those worlds automatically is unreliable. Existing judges take one view of the output: a…

  85. Has LLM Screening Performance Stalled in Software Engineering Systematic Reviews?
    USarXiv cs.SE (Software)

    arXiv:2610.10633v1 Announce Type: new Abstract: Screening in systematic reviews (SRs) is manual and time-consuming. Prior work has explored large language models (LLMs) for automating this step, but LLMs are evolving rapidly, so earlier…

  86. Trajectory-Guided Fault Localization for Agent Skill Evolution
    USarXiv cs.SE (Software)

    arXiv:2610.11858v1 Announce Type: new Abstract: Agent skills provide reusable guidance for code agents, but incomplete or unsuitable guidance can impair task execution. To reduce the manual effort of skill refinement, recent approaches use…

  87. Traceable World State: A Provenance-Aware State Representation and Deterministic Replay Framework for Robotic Systems
    USarXiv cs.SE (Software)

    arXiv:2610.12033v1 Announce Type: cross Abstract: Robotic systems operating over extended tasks must maintain a world state assembled from observations arriving at different times, with varying confidence and potential revisions…

  88. Cyclic Graphs and Memoization in Pure $\lambda$-Calculus
    USarXiv cs.PL (Programming)

    arXiv:2606.22908v4 Announce Type: replace Abstract: Purely functional programming makes immutability and non-strict evaluation its defaults; we push further, making interning and memoization the defaults of computation. In prior…

  89. Can LLMs Simulate Novice Programmers' Misconceptions?
    USarXiv cs.PL (Programming)

    arXiv:2610.10656v1 Announce Type: cross Abstract: We evaluate 13 LLMs on generating, solving, simulating, and diagnosing novice programming misconceptions on code-tracing problems. While frontier models reliably perform these tasks, small…

  90. The Program Hypergraph: Multi-Way Relational Structure for Geometric Algebra, Spatial Compute, and Physics-Aware Compilation
    USarXiv cs.PL (Programming)

    arXiv:2603.17627v5 Announce Type: replace Abstract: Source code organizes a program as expressions and declarations, which a compiler can represent as an abstract syntax tree (AST). Some compilers introduce a further abstraction of the…

  91. Decidable By Construction: Design-Time Verification for Truly Fearless Systems
    USarXiv cs.PL (Programming)

    arXiv:2603.25414v5 Announce Type: replace Abstract: Concurrency, parallelism and distributed execution become truly fearless when the compiler tracks wait-for edges, proves multi-threaded work is sound and preserves distributed boundary…

  92. TestJack: Should you trust the results in coding benchmarks? Agentic Coding Benchmarks Auditing via Evaluator Evolution
    USarXiv cs.SE (Software)

    arXiv:2610.10619v1 Announce Type: new Abstract: Large language model (LLM) agents are rapidly reshaping software engineering, accompanied by an explosion of new code benchmarks. Yet nearly all existing benchmarks still rely on the same…

  93. Ruleless Digital Twins: Toward Declarative Decision-Making Through Standardized Frameworks and Technologies
    USarXiv cs.SE (Software)

    arXiv:2610.10631v1 Announce Type: new Abstract: Digital twins (DTs) can be thought of as digital counterparts of physical objects, or more generally, twinning targets (TTs). To enact changes on and optimize for properties of their TTs, DTs…

  94. Can LLMs Simulate Novice Programmers' Misconceptions?
    USarXiv cs.SE (Software)

    arXiv:2610.10656v1 Announce Type: new Abstract: We evaluate 13 LLMs on generating, solving, simulating, and diagnosing novice programming misconceptions on code-tracing problems. While frontier models reliably perform these tasks, small…

  95. Following Breadcrumbs in Code: What Accidentally Committed Ad-Hoc Logs Reveal about Developer Comprehension
    USarXiv cs.SE (Software)

    arXiv:2610.11041v1 Announce Type: new Abstract: Developers frequently insert temporary print or log statements, known as **ad-hoc logs**, to better understand program behavior at runtime, particularly when facing unexpected issues or…

  96. On the Risks of using LLM-Generated Tests for Regression Testing
    USarXiv cs.SE (Software)

    arXiv:2610.11835v1 Announce Type: new Abstract: Software is under constant evolution: developers continuously add features, fix bugs, and refactor code, and any of these changes may break existing functionality. Regression testing guards…

  97. ShannonProver: Towards Automating Formal Cryptographic Proofs
    USarXiv cs.PL (Programming)

    arXiv:2607.02847v4 Announce Type: replace-cross Abstract: Cryptographic proofs are produced at a scale that increasingly exceeds the community's ability to verify them manually. Machine-checked proofs offer a path toward scalable proof…

  98. Can LLMs Fix It Without Code? Toward Automated Verification of No-Code Bug Fixes
    USarXiv cs.SE (Software)

    arXiv:2610.11963v1 Announce Type: new Abstract: A no-code fix resolves an invalid bug report by directing the user to change a setting, update to a version where the problem is already fixed, or adjust their workflow. Manually verifying…

  99. Multicategorical Semantics for Untyped Effects
    USarXiv cs.PL (Programming)

    arXiv:2605.21337v2 Announce Type: replace Abstract: Completeness proofs in categorical semantics usually proceed by building a syntactic category whose composition is given by substitution. For untyped effectful Call-by-Value languages…

  100. Code Understanding is a Bottleneck for Coding Agents
    USarXiv cs.PL (Programming)

    arXiv:2610.10610v1 Announce Type: cross Abstract: Repository benchmarks (e.g., SWE-bench) for coding agents often assume that lines of code edited can predict task difficulty, but such datasets' poor control over code and task types makes…

  101. DITTO: A Context-aware Pickle-based Pre-Trained Model Scanner for Effective Security Audits
    USarXiv cs.SE (Software)

    arXiv:2610.10735v1 Announce Type: cross Abstract: Pre-trained models (PTMs) are widely distributed as serialized binaries, but their reuse often exposes software supply chains to deserialization attacks. Despite the emergence of safer…

  102. Beyond Component Testing: Validating Agentic AI Systems
    USarXiv cs.SE (Software)

    arXiv:2607.29405v2 Announce Type: replace-cross Abstract: Agentic AI systems act through multi-step trajectories that combine planning, tool use, memory, interaction, and adaptation. This behavior stretches validation practice beyond…

  103. Cross-Provider Review as a Runtime Contract for Coding Agents: A Controlled Pilot and Fault-Injection Study
    USarXiv cs.SE (Software)

    arXiv:2610.10961v1 Announce Type: new Abstract: Coding agents increasingly share a workstation while drawing on separate providers and subscription allowances. A second agent can inspect a completed answer, but the call spends another pool…

  104. TestPrism: Rethinking Test Evaluation Beyond a Single Reference
    USarXiv cs.SE (Software)

    arXiv:2610.12289v1 Announce Type: new Abstract: Large language model (LLM) coding agents have advanced test generation across diverse programming tasks. However, the common practice of evaluating tests against a single reference solution…

  105. A Survey on LLM-Integrated Hardware Design Verification
    USarXiv cs.SE (Software)

    arXiv:2610.10580v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly being integrated into hardware verification to automate specification interpretation, verification-artifact generation, debugging, formal…

  106. Skill-Adaptive Imitation Learning for UI Test Reuse
    USarXiv cs.SE (Software)

    arXiv:2409.13311v2 Announce Type: replace Abstract: To alleviate the substantial cost of manually crafting user interface (UI) test cases, UI test migration aims to automatically generate test cases for a target mobile application (app) by…

  107. CAF\'E: Causal Black-Box Testing of Machine Unlearning
    USarXiv cs.SE (Software)

    arXiv:2509.16525v2 Announce Type: replace Abstract: Machine learning models are increasingly deployed as software components that must evolve as requirements change. When specific training records or features must no longer influence a…

  108. Applying Security by Design at the Point of Execution: How Governed Security Requirements Affect the Security of AI-Generated Code
    USarXiv cs.SE (Software)

    arXiv:2610.10659v1 Announce Type: new Abstract: Security by design asks that security requirements are defined before code is written. Secure-code benchmarks typically measure the opposite situation: the agent receives the task without…

  109. Retromorphic Testing of Quantum Compiler Passes
    USarXiv cs.SE (Software)

    arXiv:2610.11195v1 Announce Type: cross Abstract: Quantum compilers play a critical role in transforming high-level quantum programs into optimized, hardware-compatible circuits. However, verifying the correctness of compiler passes…

  110. Fixed-Point Scaffolding in the Clef Programming Language
    USarXiv cs.PL (Programming)

    arXiv:2606.02854v3 Announce Type: replace Abstract: Native compilation changes how a program represents values and performs operations from processor to processor. In our view, proofs that justify source-level decisions must remain…

  111. VISTA: An End-to-End Benchmark for Visual Spec-to-Web-App Coding Agents
    USarXiv cs.SE (Software)

    arXiv:2605.26144v4 Announce Type: replace Abstract: Coding agents can now build applications from design mockups, but a screen that looks right is not an application that works. Existing benchmarks either score visual reconstruction…

  112. Probabilistic Sensing, Deterministic Authority: Admitting Model-Produced Observations into Sufficiency-Checked Governance Contracts
    USarXiv cs.SE (Software)

    arXiv:2610.10978v1 Announce Type: new Abstract: When a field that an authority contract needs exists only in unstructured evidence, a model can sense it. We admit the model's output only as an observation record with a score. An admission…

  113. Closed-loop evaluation of LLM agents for embedded software development
    USarXiv cs.SE (Software)

    arXiv:2610.11447v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as coding agents that edit files, run builds and tests, inspect execution results, and repair software iteratively. Embedded firmware is…

  114. MAP4CS: A Multi-dimensional Data Pruning Framework for Efficient Code Retriever Fine-tuning
    USarXiv cs.SE (Software)

    arXiv:2610.11727v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) has become a cornerstone in software engineering for enhancing Large Language Models (LLMs) with domain-specific knowledge. However, adapting retrievers…

  115. Cadence: Strategic Guidance for Coding Agents
    USarXiv cs.SE (Software)

    arXiv:2610.12269v1 Announce Type: new Abstract: Runtime monitors are increasingly used to improve the reliability of LLM-based coding agents by inspecting execution trajectories and delivering corrective guidance upon detecting…

  116. Beyond Type-checking: Towards Holistic Evaluation of Formal Specification Generation
    USarXiv cs.SE (Software)

    arXiv:2610.10604v1 Announce Type: new Abstract: When generating verifiable code, natural language requirements are mapped to machine checked code using LLMs and agentic workflows. A crucial component of this pipeline is specification…

  117. Code Understanding is a Bottleneck for Coding Agents
    USarXiv cs.SE (Software)

    arXiv:2610.10610v1 Announce Type: new Abstract: Repository benchmarks (e.g., SWE-bench) for coding agents often assume that lines of code edited can predict task difficulty, but such datasets' poor control over code and task types makes it…

  118. Skill Constellations: Tracing the Supply Chain of Agent Skills on GitHub
    USarXiv cs.SE (Software)

    arXiv:2610.11169v1 Announce Type: new Abstract: Agent skills are SKILL.md instructions and scripts that AI coding agents such as Claude Code and Codex run with the permissions of their user. Developers share skills by copying them between…

  119. When Flaws Cascade: Understanding Vulnerabilities and Exploitation Chains in JavaScript Engines
    USarXiv cs.SE (Software)

    arXiv:2610.10844v1 Announce Type: cross Abstract: JavaScript engines are pivotal to modern web browsers, enabling the execution of dynamic and interactive web applications. However, their complexity and widespread adoption make them prime…

  120. Protecting CPU AI On Edge TEEs: WebAssembly's Promise and Practical Challenges
    USarXiv cs.SE (Software)

    arXiv:2610.12050v1 Announce Type: cross Abstract: AI models on edge hardware contain important intellectual property (IP), but an adversary can steal it when they achieve root access. Trusted Execution Environments (TEE) like Arm TrustZone…

  121. Arbiter: Detecting Interference in LLM Agent System Prompts
    USarXiv cs.SE (Software)

    arXiv:2603.08993v2 Announce Type: replace Abstract: System prompts for LLM-based coding agents are software artifacts that govern agent behavior, yet lack the testing infrastructure applied to conventional software. We present Arbiter, a…

  122. ParanoiaEval: Benchmarking Unnecessary Defensive Work in Agentic Coding
    USarXiv cs.SE (Software)

    arXiv:2610.08662v2 Announce Type: replace-cross Abstract: As coding agents increasingly undertake real-world work autonomously, judging whether their risk treatments are warranted has become important. Existing work evaluates related agent…

  123. Characterizing Overconfident Failure in LLM-Based Code Generation
    USarXiv cs.SE (Software)

    arXiv:2610.11300v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for automated code generation, but generated programs can appear syntactically plausible while still failing execution-based correctness…

  124. Quantitative Verification of Infinite-State Networks
    USarXiv cs.PL (Programming)

    arXiv:2610.11991v1 Announce Type: cross Abstract: Many network protocols and distributed systems combine recursion, unbounded local state, and quantitative behaviour such as cost, latency, or reliability. Existing decidability results for…

  125. One Skill Too Many: How Co-Installed Skills Conflict in Coding Agents
    USarXiv cs.SE (Software)

    arXiv:2610.11647v1 Announce Type: new Abstract: Coding agents are extended with agent skills, directories whose SKILL.md tells the model when and how to perform a task. Because skills come from independent sources (teams, developers…

  126. Evaluating Exact Output and Checkpoint-State Prediction in Real Programs
    USarXiv cs.SE (Software)

    arXiv:2610.11889v1 Announce Type: new Abstract: We present a benchmark for predicting final output and checkpoint state from source and input alone. It extends CRUXEval-style output prediction with paired shorter- and longer-trace inputs…

  127. Visible Reasoning Is Not a Universal Optimizer: Persona- and Thinking-Dependent Effects in Analytics Code Generation
    USarXiv cs.SE (Software)

    arXiv:2610.10639v1 Announce Type: cross Abstract: Visible Chain-of-Thought (CoT) is often treated as a broadly useful reasoning instruction, yet analytics code generation combines natural-language ambiguity, schema grounding…

  128. ReCodeAgent: A Multi-agent Workflow for Language-Agnostic Translation and Validation of Large-Scale Repositories
    USarXiv cs.SE (Software)

    arXiv:2604.07341v4 Announce Type: replace Abstract: Most repository-level code translation and validation techniques have been evaluated on a single source-target programming language (PL) pair, owing to the complex engineering effort…

  129. Implementing the Spec Growth Engine: Preventing Spec-Code Divergence, and Growing the Spec with Agents
    USarXiv cs.SE (Software)

    arXiv:2610.11725v1 Announce Type: new Abstract: The Spec Growth Engine anchors AI-assisted software development in a graph of specifications that the code is coupled to. This paper describes its implementation, which serves two tasks and…

  130. Who Pays the Review Cost? Triage, Fairness, and Accountability in AI-authored Pull Requests
    USarXiv cs.SE (Software)

    arXiv:2610.11179v1 Announce Type: new Abstract: AI coding agents are moving from local code assistance into pull-based workflows, where generated contributions must be reviewed, explained, and maintained within existing project norms…

  131. Bayes Rule for Conditioning Probabilistic Programs
    USarXiv cs.PL (Programming)

    arXiv:2610.10792v1 Announce Type: new Abstract: Probabilistic programs provide a rigorous programming-language foundation for expressing rich probabilistic models and offer language-level support for solving challenging statistical…

  132. Arbiter: Detecting Interference in LLM Agent System Prompts
    USarXiv cs.PL (Programming)

    arXiv:2603.08993v2 Announce Type: replace-cross Abstract: System prompts for LLM-based coding agents are software artifacts that govern agent behavior, yet lack the testing infrastructure applied to conventional software. We present…

  133. Evaluating Local Language Model Agents for Reproducible Data Engineering: An Empirical Software Engineering Study of Mobility Workflows
    USarXiv cs.SE (Software)

    arXiv:2610.11482v1 Announce Type: new Abstract: Context: Large language model (LLM) agents are increasingly used as software and data-engineering assistants, yet evidence about locally deployable open-weight agents remains limited…

  134. MRCert: Towards Post-deployment Patch Robustness Certification for Adversarially Patched Samples via Type-specific Masking
    USarXiv cs.SE (Software)

    arXiv:2610.10617v1 Announce Type: cross Abstract: In post-deployment time, inputs to deep learning models may or may not be adversarially patched. Patch robustness certification on such inputs within a patch bound can verify their label…

  135. Reliability Characterization for N-version Object Detection
    USarXiv cs.SE (Software)

    arXiv:2610.12149v1 Announce Type: new Abstract: N-version object detection (OD) is an approach to diversifying detection results using multiple models or input frames and reducing detection errors by aggregating individual results…

  136. SSCBench: Evaluating the Evidential Validity of Fault-Injection Tests for Tool-Using LLM Agents
    USarXiv cs.SE (Software)

    arXiv:2610.11514v1 Announce Type: new Abstract: Fault injection is increasingly used to evaluate the reliability of tool-using LLM agents. However, there has been limited study of how fault-adoption results should be interpreted when the…

  137. DLCB: Ahead-of-Time Compilation for Dynamic Deep Learning
    USarXiv cs.PL (Programming)

    arXiv:2610.10547v1 Announce Type: new Abstract: Deep learning workloads are increasingly deployed in settings where tensor shapes are not fully known at compile time. Batch sizes vary across requests, sequence lengths differ between…

  138. Keyboard differences between Windows and Macs
    USHacker News Front Page

    Article URL: https://unsung.aresluna.org/deeper-dive-keyboard-differences-between-windows-and-macs/ Comments URL: https://news.ycombinator.com/item?id=50015515 Points: 315 # Comments: 255

  139. What should we tell our students?
    USHacker News Front Page

    Article URL: https://terrytao.wordpress.com/2026/10/08/what-should-we-tell-our-students/ Comments URL: https://news.ycombinator.com/item?id=50015236 Points: 130 # Comments: 180

  140. B-Trees Are Back: Engineering Fast and Pageable Node Layouts
    USlobste.rs

    Comments