A Workflow is a defined sequence of tasks, steps, or processes executed to accomplish a specific goal, with explicit rules governing the order of execution, dependencies, and conditions for progression. In computing and AI research, workflows formalize how data, models, and services interact across a pipeline, enabling reproducibility, automation, and systematic monitoring. Research applications include scientific computing, enterprise process automation, and the design of multi-step AI pipelines involving retrieval, reasoning, and action execution.

Posts

RunAgent: Interpreting Natural-Language Plans with Constraint-Guided Execution (IEEE)

/in /by

Humans solve problems by executing targeted plans, yet large language models (LLMs) remain unreliable for structured workflow execution. We propose RunAgent, a multiagent plan execution platform that interprets natural-language plans while enforcing stepwise execution through constraints and rubrics. RunAgent bridges the expressiveness of natural language and the determinism of programming languages via an agentic language with explicit control constructs (e.g., IF, GOTO, FORALL). It autonomously derives and verifies constraints at each step; dynamically selects among LLM reasoning, tool use, and Python execution; and integrates error correction to ensure correctness. Evaluations on Natural-plan and SciBench Datasets demonstrate that RunAgent outperforms baseline LLMs and state-of-the-art PlanGEN methods.

Read more