Dynamic Intent-to-Workflow Orchestration: A Comprehensive Experimental Evaluation of AI-Generated Workflow Systems

From Natural Language to Executable Optimization Workflows: A Knowledge-Graph-Driven Framework for Multidisciplinary Optimization

Early-stage engineering design requires balancing competing performance, cost, and feasibility criteria across interacting disciplinary models. However, deploying multidisciplinary optimization (MDO) frameworks remains difficult because translating high-level requirements into executable optimization workflows often re...

From Review to Reuse: How Post-Task Workflow Can Support Human-AI Agent Interaction

This work investigated post-task workflows: editable, graph-based representations of an agent's completed execution that improve their understanding and error detection over a prompt-only condition, and found that validation succeeded mainly when users cross-checked across multiple evidence sources.

FlowScout: From Execution Feedback to Reliable Tool-Using Agent Workflows

Agentic workflows have become an important abstraction for building reliable LLM-based automation systems by organizing large language models (LLMs), tools, and control logic into explicit execution structures. However, constructing high-quality agentic workflows remains largely manual and requires substantial domain e...

StartupBench: Benchmarking General-Purpose Agents on Market-Validated End-to-End Workflows

This work systematically study AI products with demonstrated adoption, together with their product workflows and users, to identify real-world tasks for which AI has established practical demand across diverse professional domains and establishes StartupBench as an empirical measure of progress toward E2E completions o...

Generic Engine for Module Software Task Orchestration and Negotiation (GEMSTONe): A Multi-Stage Workflow System for Orchestrating Virtual Imaging Trials.

Avatar: Toward Autonomous End-to-End Orchestration of Scientific Workflows using LLMs

This work presents Avatar, an actor-based architecture comprising an orchestrator, an executor, and a provenance monitor, and observes that Avatar's rule mode reproduces native execution, with a single unchanged core running all three.