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.
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.
This paper proposes an architecture for a Python-native orchestration platform that borrows the operational role of a traditional RPA "control tower" while adopting the engineering practices of modern workflow-orchestration systems such as Temporal and Prefect, and is presented in four layers — presentation, orchestrat...
Aryanjeet Singh, S. Rathod, Pradnya Suryawanshi· International Journal For Mu...· 0 citations
This demo presents SAGE as a pipeline-native runtime system and demonstrates it through an OPC-facing control plane and includes a compact distributed comparison against a LangChain RPC baseline over a shared 15-workload RAG suite, where SAGE nearly doubles full-RAG throughput under matched 8-node settings.
Jun Liu, Shu-Hao Zhang· Workshop Proceedings of the...· 0 citations
AI agents are emerging as a practical way to run multi-step scientific workflows that interleave reasoning, tool use, and verification. Scaling such agentic science remains difficult because workflows are hard to observe and reproduce, many scientific tools and laboratory systems are not agent-ready, and execution trac...
Lin-Feng Zhang, Si-Heng Chen, Yu-Zhu Cai et al.· AI Plus· 0 citations
The proliferation of large language model (LLM)-based autonomous agents has created a new class of distributed system: the multi-agent LLM network. While significant research focuses on the intelligence of individual agents, comparatively little work addresses the software architectural concerns that govern how fleets...
Ketankumar Savajiyani· 2026 International Conferenc...· 0 citations
The transition from single-shot generative models to autonomous, goal-directed agents represents a structural departure from fixed-pipeline automation. Low-code orchestration platforms such as n8n increasingly supply the operational substrate for this transition, handling function invocation, state persistence, and int...
Swapnil Mohan Gaikwad, Sourav Saha, Ranjit Kumar Reddy Ponugoti et al.· 2026 International Conferenc...· 0 citations
A two-week trace of 11.7 million requests from a large-scale production platform for general-purpose agents, backed by inference infrastructure comprising over 10k GPUs is analyzed to characterize the platform at three connected levels: task-level initiation semantics, workflow-level execution patterns, and infrastruct...
Yi-Hao Zheng, Jing-Zhe Jiang, De-Jiang Zhu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
