AI Slop and the Software Commons
arXiv:2604.16754v4 Announce Type: replace Abstract: We argue that AI slop in software development is creating a tragedy of the commons. Slop is cheap to generat…
EnglisharXiv cs.SE
最新资讯
言栖资讯收录 138179 篇 AI、开发与建站文章（English），按发布时间排序，支持搜索与按语言筛选。
QDiff: Differential Testing of Quantum Software Stacks
arXiv:2611.08220v1 Announce Type: cross Abstract: Over the past few years, several quantum software stacks (QSS) have been developed in response to rapid hardwa…
EnglisharXiv cs.SE
Detecting Silent Faults at the Environment-Trainer Boundary in Reinforcement Learning
arXiv:2611.08144v1 Announce Type: cross Abstract: Robot reinforcement learning increasingly runs environments outside the trainer: in another process, on anothe…
EnglisharXiv cs.SE
Symmetry-Aware Surrogate-Assisted Testing of UAVs
arXiv:2611.08012v1 Announce Type: cross Abstract: We investigate a symmetry-aware surrogate-assisted testing approach for UAV autopilots. The proposed approach …
EnglisharXiv cs.SE
tok: a textual concrete syntax of BPMN and DMN for humans and AI agents
arXiv:2611.07945v1 Announce Type: cross Abstract: tok is a plain-text notation for Business Process Model and Notation (BPMN) 2.0.2 process models and Decision …
EnglisharXiv cs.SE
Don't Prompt Your Agents. Equip Them: Skillware as a Modular Standard for Sovereign, Auditable, and Deterministic Capability Execution for Logical Systems
arXiv:2611.07652v1 Announce Type: cross Abstract: Current autonomous logical systems rely on a fragile assumption: that language models should dynamically write…
EnglisharXiv cs.SE
Rule-Guided and Trajectory-Aware Repair for LLM-Based HLS Generation
arXiv:2611.07324v1 Announce Type: cross Abstract: Large language models (LLMs) offer a promising path for directly generating functionally correct and synthesiz…
EnglisharXiv cs.SE
Code, Commits, and Complexity in the GenAI Era: A Longitudinal Study of Team-Based Capstone Projects
arXiv:2611.07297v1 Announce Type: cross Abstract: Generative AI tools are now widely available to students, but little is known about how team-based project cod…
EnglisharXiv cs.SE
Follow the Policy, Fail the Benchmark: Auditing and Revising Policy-Based Decision Benchmarks
arXiv:2611.07042v1 Announce Type: cross Abstract: Policy-based decision benchmarks evaluate whether systems apply written rules to financial and operational cas…
EnglisharXiv cs.SE
Replay Is a Family of Assertions: Fork-Safety in Event-Sourced Agent Runtimes
arXiv:2611.06924v1 Announce Type: cross Abstract: Event-sourced agent runtimes commonly claim deterministic replay, cheap forking, and lineage. These are famili…
EnglisharXiv cs.SE
Cognitive Tours: Making Understanding a Deliverable in AI-Assisted Development
arXiv:2611.08456v1 Announce Type: new Abstract: Generative AI and agentic coding are accelerating software development, leading to concerns about technical debt…
EnglisharXiv cs.SE
Hard Issue, Weak Model, or Bad Run? Rethinking Failure Prediction for Coding Agents
arXiv:2611.08285v1 Announce Type: new Abstract: Trajectory-based failure predictors for software engineering (SE) agents read the partial trajectory of a run to…
EnglisharXiv cs.SE
Accepted but Wrong: Silent Failures of LLM Code Repairs after API Migrations
arXiv:2611.08269v1 Announce Type: new Abstract: After a runtime or API migration, an LLM-repaired procedure can run cleanly yet return wrong results, and a rele…
EnglisharXiv cs.SE
RouteAlign: Aligning Task Requirements with Model Profiles for LLM Service Selection
arXiv:2611.08162v1 Announce Type: new Abstract: LLM service selection requires performance evidence that reflects the demands of the current task. Aggregate sco…
EnglisharXiv cs.SE
Information Loss Is All You Need: $TC^0$ Pseudorandomness from Worst-Case Lattices
arXiv:2611.05136v2 Announce Type: replace-cross Abstract: Can deterministic information loss yield post-quantum pseudorandomness with $TC^0$ evaluation? We show…
EnglisharXiv cs.CR
Backdoor Purification for LoRA-Tuned LLMs via Null-Space Projection
arXiv:2610.00685v2 Announce Type: replace-cross Abstract: With the rapid adoption of large language models (LLMs) and parameter-efficient fine-tuning (PEFT) met…
EnglisharXiv cs.CR
Backdoor Containment via Expert Quarantine and Shutdown in LLMs
arXiv:2610.00663v2 Announce Type: replace-cross Abstract: Backdoored large language models (LLMs) can behave normally on benign inputs while producing attacker-…
EnglisharXiv cs.CR
Generic Number-of-Copies Amplification for Pseudorandom States
arXiv:2606.29325v2 Announce Type: replace-cross Abstract: We show that any quantum pseudorandom state that is secure against single-copy distinguishers, i.e. a …
EnglisharXiv cs.CR
Persona-Model Collapse in Emergent Misalignment
arXiv:2605.12850v3 Announce Type: replace-cross Abstract: Fine-tuning large language models on narrow data with harmful content produces broadly misaligned beha…
EnglisharXiv cs.CR
Analysis of LLM Vulnerability to GPU Soft Errors: An Instruction-Level Fault Injection Study
arXiv:2601.19912v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are highly compute- and memory-intensive, posing significant demands on h…
EnglisharXiv cs.CR