From Review to Reuse: How Post-Task Workflow Can Support Human-AI Agent Interaction
cs.HC
Submitted: 2026-09-11
Updated: 2026-11-01
Terminology
Sources
- AgentRx: Diagnosing AI Agent Failures from Execution Trajectories
- ALLOY: Generating Reusable Agent Workflows from User Demonstration
- FlowMind: Execute-Summarize for Structured Workflow Generation from LLM Reasoning
- Magentic-UI: Towards Human-in-the-loop Agentic Systems
- Agent Workflow Memory
- AgentTrails: Towards Trust and Reuse for Agentic Tasks
- Chat2Workflow: A Benchmark for Generating Executable Visual Workflows with Natural Language
Related papers
- EmoPhone: A Multi-Wave Dataset for In-the-Wild Mobile and Wearable Affect Sensing
- Tasteply: Externalizing Stable and Situational Preference as Manipulable Spatial Objects
- Shielded Trajectory Sampling for Personalized Relational Safety in Conversational AI
- Reconstruction and Reflection of Positive Experiences through Resurfacing Laughter-indexed Everyday Moments
- LLM-Assisted Reranking to Operationalize Nuanced Objectives in Recommender Systems
- Explainable Iterative Data Visualization Refinement via an LLM Agent