GH-AWTrace: A Large-Scale Dataset of GitHub Agentic Workflow Execution Logs
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
Community
A dataset (https://huggingface.co/datasets/jaykay9999/GHAWTrace) containing agent trajectories from real-world agentic workflows in software projects. You can use the dataset to study:
- single-agent vs. multi-agent
- memory
- collaboration & communication
- cost
- ...
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- GHAgentCI: A Dataset of Coding-Agent Invocations in CI Workflow Histories (2026)
- Specifying and Maintaining Agentic Workflows: An Empirical Study of GitHub Agentic Workflows (2026)
- AgentTorrent: A Dataset of Context and Harness Engineering Artifacts on GitHub (2026)
- Why Agentic Workflows Fail: A Taxonomy Derived from Literature and Empirical Data (2026)
- AgentXploit: Autonomous Repository-to-Runtime Red-Teaming for AI Agents (2026)
- SkillLifeBench: Benchmarking Security Across the Lifecycle of Agent Skills (2026)
- ControlScope: Workflow Revision and Reliability in LLM Agents (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend
Get this paper in your agent:
hf papers read 2611.06866 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 0
No model linking this paper
Datasets citing this paper 1
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper