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

2026-09-09

AI Summary

研究解决了科学工作流管理系统中固定规则编排的问题，通过引入基于LLM的Avatar架构，实现更自主的编排，减少计算浪费和GPU繁忙时间。

Abstract

Scientific workflow management (WMSs) systems automate execution, yet orchestrate using fixed, hand-tuned rules. LLM agents promise more autonomous orchestration, but it remains unclear where to introduce agentic reasoning, how to bound its risk, and when it actually helps. We present Avatar, an actor-based architecture comprising an orchestrator, an executor, and a provenance monitor. Each actor's decision policy is pluggable (rule-based or LLM-backed) via a single adapter-validated action catalog, so conventional and agentic control run on the same core across different WMSs. We present an implementation using the Academy framework and evaluate Avatar across three workloads. We observe that Avatar's rule mode reproduces native execution, with a single unchanged core running all three. Moreover, LLM-backed Avatar reports a reduction of compute wastage by $55\%$ and cuts GPU-busy time by $40\%$. Overall, we envision Avatar as a step toward workflow systems that reason about their own orchestration rather than follow pre-fixed rules.

Problem

• Scientific Workflows
• Autonomous Orchestration
• LLMs
• Fixed Rules
• Agentic Reasoning

Innovation

• LLM agents
• pluggable decision policy
• autonomous orchestration