Open Source
GH-AWTrace: A Large-Scale Dataset of GitHub Agentic Workflow Execution Logs
arXiv cs.SE0 views
arXiv:2611.06866v1 Announce Type: new Abstract: Agentic workflows enable AI agents to perform recurring repository tasks on schedules or in response to repository events. Existing studies examine workflow definitions and outputs, but provide limited evidence of what happens during execution. We present GH-AWTrace, a dataset linking 25,014 verified GitHub Agentic Workflows across 5,051 repositories to 4,112,526 run records and 562,877 nonempty execution log archives. The dataset preserves execution evidence subject to GitHub's log-retention limits and links it to repository metadata and generated workflow configurations. Illustrative cases show how the logs expose tool denials, provider failures, changes in an agent's approach, and delegation among agents. These observations enable research on execution failures, tool use, and the relationship between reported run outcomes and visible task progress. Coverage varies across workflows, and the logs provide partial observations rather than complete agent trajectories. Video: https://youtu.be/KIlfmZhHxtA
Source：https://arxiv.org/abs/2611.06866PreviousRethinking Access Control for AI Agents: Recent Advances and Open ChallengesNextItem Representations Matter: Bridging Hard Semantic IDs and Soft Prototype Mixtures for Generative Retrieval
Related posts
Data-Driven Likelihood-Ratio Construction for Radar Detection via Bernstein Induction Operators
0arXiv eess.SP
Continuous Wideband Multicarrier Rydberg Atomic Quantum Receiver
0arXiv eess.SP
Space efficient implementation of hypergraph dualization in the D-basis algorithm
0arXiv cs.IR
SciToT: Multimodal Tip-of-the-Tongue Retrieval for Scientific Papers
0arXiv cs.IR
Confucius4-R2T2: A Stable-Prefix Streaming ASR Model for Real Real-Time Transcription
0arXiv cs.SD
CAST-Bench: Tracing Every Sound to Its Source in Multi-Shot Audio-Video Generation
0arXiv cs.SD