Workflows
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs
Announce Type: replace Abstract: Multi-agent LLM workflows route inference through specialized roles to lift end-task accuracy, but jointly training those roles with reinforcement learning is unstable in ways that are poorly understood. We study when end-to-end RL training of multi-agent LLM workflows improves over their base models, comparing Shared-Policy training, where all roles update one policy, with Isolated-Policy training, where each role has its own parameters. Our experimental...
Workflow-to-Skill: Skill Creation via Routing-Workflow-Semantics-Attachments Decomposition
arXiv:2606.06893v1 Announce Type: new Abstract: Large language model agents increasingly rely on Skills to encode procedural knowledge, yet high-quality Skills remain costly to hand-write. This paper studies automatic Skill construction from heterogeneous interaction evidence, including demonstrations, agent trajectories, tool traces, and execution logs. We argue that trace-to-skill construction is not simple summarization tasks, because traces are fragmented, redundant, and may miss rare...
Do More Agents Help? Controlled and Protocol-Aligned Evaluation of LLM Agent Workflows
arXiv:2606.05670v1 Announce Type: new Abstract: Does adding more agents help an LLM workflow once compared systems share the same benchmark loader, tool access, answer contract, usage accounting, and trajectory logging? We introduce BenchAgent, an evaluation framework that places single-agent, fixed multi-agent (MAS), and evolving MAS workflows under one normalized execution and logging protocol. BenchAgent evaluates these substrate-internal workflows across ten reasoning, coding, and...
Unifying von-Neumann HPC and Neuromorphic Acceleration via the EBRAINS Research Infrastructure: A Framework for High-Performance Workflows
Announce Type: new Abstract: Modern scientific workflows increasingly span diverse computing architectures, yet executing a single computational model across disparate systems often forces researchers to maintain fragmented, site-specific pipelines. In this paper, we address this challenge within the domain of computational neuroscience by presenting a unified, cloud-based workflow orchestrated via EBRAINS JupyterLab. This workflow enables users to transparently execute spiking neural...
SQLite is all you need for durable workflows
Here is the summary: SQLite is a powerful and versatile database that can be used for durable workflows. It is a self-contained, serverless, and zero-configuration database that can be easily embedded into applications. SQLite is also highly reliable and can handle large amounts of data. It is a great choice for applications that require durable workflows, such as data processing, analytics, and machine learning. SQLite is also easy to use and can be integrated with other technologies, such as Python and JavaScript. With its powerful features and ease of use, SQLite is an ideal choice for durable workflows. ## Welcome to [Stack Overflow](https://stackoverflow.com/) This is a Q&A forum for computer programming. The [automatic community-generated FAQ](https://meta.stackexchange.com/questions/7931/faq-proposed-faq-for-stack-exchange-sites) has answers to many common questions. Read the [tour](https://stackoverflow.com/tour) to learn more about us. Some questions to help you get started: * [What is Stack Overflow?](https://meta.stackexchange.com/questions/92107/what-is-stack-overflow) * [How do I ask a good question?](https://stackoverflow.com/help/how-to-ask) * [How to create a Minimal, Complete, and Verifiable example
Trust-Calibrated Code Review: A Participatory Design Study of Review Workflows for LLM-Generated Multi-File Changes
Announce Type: new Abstract: Background: Developers increasingly review multi-file code changes generated by LLM-based agents, yet no validated end-to-end workflow or IDE tooling design exists for this scenario. Aims: We investigate (RQ1) the challenges developers face when reviewing LLM-generated multi-file changes and (RQ2) how developers envision effective workflows for this task.
KBase Research Agent: Automated Multi-Agent Workflow Construction for Reproducible Genome Analysis
Constructing multi-step bioinformatics workflows, from read quality control through genome assembly to functional annotation, requires expertise in both biology and computational tool selection, creating a bottleneck for scalable and reproducible analysis. We present the KBase Research Agent, a multi-agent system for automating such workflows within the DOE Systems Biology Knowledgebase (KBase). Given a set of sequencing reads and a research objective, the agent constructs an analysis plan...
Deft Scheduling of Dynamic Cloud Workflows with Varying Deadlines via Mixture-of-Experts
arXiv:2606.01162v1 Announce Type: new Abstract: Workflow scheduling in cloud computing demands the intelligent allocation of dynamically arriving, graph-structured workflows with varying deadlines onto ever-changing virtual machine resources. However, existing deep reinforcement learning (DRL) schedulers remain limited by rigid, single-path inference architectures that struggle to handle diverse scheduling scenarios. We introduce \textbf{DEFT} (\textbf{D}eadline-p\textbf{E}rceptive...
Deft Scheduling of Dynamic Cloud Workflows with Varying Deadlines via Mixture-of-Experts
arXiv:2606.01162v2 Announce Type: replace Abstract: Workflow scheduling in cloud computing demands the intelligent allocation of dynamically arriving, graph-structured workflows with varying deadlines onto ever-changing virtual machine resources. However, existing deep reinforcement learning (DRL) schedulers remain limited by rigid, single-path inference architectures that struggle to handle diverse scheduling scenarios. We introduce $\textbf{DEFT}$ ($\textbf{D}$eadline-p$\textbf{E}$rceptive...
Lean4Agent: Formal Modeling and Verification for Agent Workflow and Trajectory
arXiv:2606.06523v1 Announce Type: new Abstract: Equipping Large Language Models (LLMs) to execute reliable multi-step workflows has become a central challenge in artificial intelligence. Despite recent advances in LLMs' agentic capabilities, most agent systems still lack formal methods for specifying, verifying, and debugging their workflow and execution trajectories. This challenge mirrors a long-standing problem in mathematics, where the ambiguity of natural languages (NLs) motivates the...