From Logs to Agents: Reconstructing High-Level Creative Workflows from Low-Level Raw System Traces
🤖 AI Summary
Current AI creativity support tools generate low-level interaction logs—such as clicks and parameter adjustments—that poorly capture users’ creative intent, limiting agents’ understanding of the design process. This work proposes a novel approach that transforms raw, noisy logs into structured, high-level behavioral workflow graphs by abstracting semantic action tokens like MODIFY_Prompt and GENERATE_Image. For the first time, this method enables a meaningful mapping from low-level interactions to interpretable creative workflows. Through log parsing, behavioral abstraction, and sequence modeling, it produces a structured representation amenable to downstream mining and probabilistic reasoning. This representation lays the foundation for “process-aware agents” capable of offering design suggestions or explaining decisions grounded in users’ historical creative behavior.
Application Category
📝 Abstract
Current AI-based Creativity Support Tools (CSTs) generate massive amounts of low-level log data (e.g., clicks, parameter tweaks, metadata updates) that are hard to interpret as"creative intent". We argue that to enable future agentic systems to understand and assist users, we must first translate these noisy system traces into meaningful high-level user behavioral traces. We propose a method that parses raw csv/JSON logs into structured behavioral workflow graphs that map the provenance and flow of creative assets. By abstracting low-level system events into high-level behavioral tokens (e.g., MODIFY_Prompt, GENERATE_Image), this method enables downstream analyses like sequence mining and probabilistic modeling. We discuss how this structured workflow history is a prerequisite for"Process-Aware Agents"- systems capable of suggesting next design moves or explaining rationales based on a deeper understanding of the user's workflow patterns and history.
Problem
Research questions and friction points this paper is trying to address.
Creative Workflows
System Traces
Behavioral Abstraction
Creativity Support Tools
User Intent
Innovation
Methods, ideas, or system contributions that make the work stand out.
behavioral workflow reconstruction
creative intent inference
process-aware agents
system trace abstraction
structured workflow graph
🔎 Similar Papers
No similar papers found.
