AI圈报
论文研究普通

GHAgentCI: A Dataset of Coding-Agent Invocations in CI Workflow Histories

信息来源：arXiv·

内容摘要

Coding agents are increasingly integrated into GitHub Actions to review pull requests, triage issues and modify code. Identifying these integrations is challenging because agentic workflows often resemble ordinary CI files, with evidence appearing in action references, shell commands and workflow conventions. We present GHAgentCI, a dataset of 15K+ workflow histories from 6K+ of 196K+ mined GitHub repositories, comprising 159K+ revisions and 205K+ agent-evidence records linked to workflow triggers and declared execution constraints. Our open-source extractor, cai-miner, detects agent-related evidence using an extensible catalogue. Manual validation of 576 stratified records confirmed 96.1% of dedicated-action matches and 98.8% of GitHub Agentic Workflow matches, with lower rates for other evidence kinds. Exploratory analyses reveal a shift toward command-line and GitHub Agentic Workflow integrations, differences in declared safeguards, and frequent removal of detected agentic workflows. GHAgentCI supports longitudinal studies of coding-agent integration into CI.
内容分类AI 论文与研究
内容层级普通情报
发布时间（北京时间）
本站收录时间（北京时间）
信息来源arXiv
站内情报编号intel-fbd6966c2507a7fe95eb956b
阅读原始信息 ↗查看数据来源更多论文研究

相关推荐

综合分类、实体标签与信息来源匹配

论文研究普通
Learning a calibrated decision head from logged bandit feedback
A decision head reads a state and a list of options and returns a probability per option in one forward pass. Once deployed, it usually observes only whether the option it chose was right: logged bandit feedback. We adapt such a head, LoRA…
信息来源：arXiv · Qwen
论文研究普通
TraceKV: Policy-Preserving Low-Rank KV Cache Compression for Reasoning Vision-Language Models
Reasoning vision-language models (VLMs) impose substantial KV cache demands from both large multimodal contexts and growing reasoning traces. Low-rank KV compression has emerged as a promising paradigm that stores low-dimensional latents o…
信息来源：arXiv
论文研究普通
Can We Make an LLM Dumber, or Is It Just Playing Dumb? An Empirical Study of Believable Performance Throttling
A benchmark score is commonly read as a proxy for model capability. We study the inverse problem: can a model be driven to a target score, and do its failures resemble those of a naturally weaker model? We operationalize believable perform…
信息来源：arXiv · Qwen / Llama
论文研究普通
Observations Drift, Structures Remain: Structural Pretraining with Time Alignment for Electromagnetic Signals
Electromagnetic signal modeling is increasingly moving toward self-supervised pretraining on heterogeneous I/Q observations. However, an observed waveform is jointly shaped by signal generation, propagation environments, and acquisition pr…
信息来源：arXiv
论文研究普通
What Conformal Selection Can Certify in CRISPR Off-Target Design:Benchmark Leakage, Free Baselines, and a Finite-Sample Cohort Requirement
Conformal selection promises distribution-free, finite-sample control of the error rate of a decision, and has been proposed as a safety layer for machine-learning CRISPR guide design. We ask whether such a certificate is attainable from t…
信息来源：arXiv
论文研究普通
Testing Conversation Preservation Across LLM APIs: A Rule-Based Oracle for Detecting Silent Information Loss
LLM applications increasingly rely on translators and compatibility layers to move conversations across APIs. Yet a translated request can be accepted by the target API while silently losing information about instruction roles, tool intera…
信息来源：arXiv · OpenAI
论文研究普通
Faithful in Steps: Improving Generalization and Citation in RAG via Query Decomposition
Retrieval-augment generation is a prevalent strategy to mitigate hallucinations of LLMs. The attributable RAG (RAGQ) generates quotes for its answers. The quotes indicate which input contexts support the RAG to derive the answers, enhancin…
信息来源：arXiv · Gemini
论文研究普通
Analysis choices decide whether untrained networks beat trained ones at V1: a multiverse analysis of model-brain RSA
Untrained convolutional networks have been reported to rival trained networks as models of visual cortex, and we had reported an untrained-network advantage over backpropagation at V1 in THINGS fMRI, together with a dependence on evaluatio…
信息来源：arXiv
论文研究普通
MAGIC: Modality-Aware Gini Inspection for Clinical Hallucination Detection in LMMs
Recent advances in medical large multimodal models (LMMs) have brought promising progress to clinical decision support, yet hallucination, the generation of confident but clinically unverifiable outputs, poses a critical threat to the reli…
信息来源：arXiv
论文研究普通
One Hierarchy, Many Sports: Hierarchy-Aligned Multi-Task Learning for Next-Shot Prediction
Next-shot prediction in racket sports requires learning from event data with different match structures, recorded attributes, and label vocabularies. Table tennis, badminton, and tennis nevertheless share a hierarchy in which shots form ra…
信息来源：arXiv