LLM Agent Workflow Optimization

LLM: Large Language Model

Ask about this topic

Overview

This field studies how to organize language models, tools, memory, and decision steps so agents can complete multi-step tasks effectively and efficiently. Approaches include fixed workflows and DAGs, query-level model routing, reinforcement learning and evolutionary search, and trace-guided prompt or harness refinement; they are tested in settings such as coding, web use, retrieval, and scientific research. Systems work also optimizes execution through caching, scheduling, parallelism, and compiling repeated behavior into deterministic workflows. A central tension is whether adaptive workflows improve on reusable fixed designs enough to justify their added cost and complexity, while maintaining reliability and generalizing beyond the tasks used for optimization.

Latest papers

CardsList

262 papers59 papers in the last four weeks, up 69% on the four weeks before. 0.3% of all new papers.

  1. Spec Kit Agents: Context-Grounded Agentic Workflows

    Apr 7, 2026Pardis Taghavi, Santosh BhavaniSoftware EngineeringAI Coding Agents

  2. Compiled AI: Deterministic Code Generation for LLM-Based Workflow Automation

    Apr 6, 2026Geert Trooskens, Aaron Karlsberg, Anmol Sharma +6Code GenerationLLM Code Generation

    XY.AI Labs, Palo Alto, CA · Stanford University School of Medicine, Stanford, CA · Cornell University, Ithaca, NY +3

  3. Profile-Then-Reason: Bounded Semantic Complexity for Tool-Augmented Language Agents

    Apr 5, 2026Paulo Akira F. EnabeTool-Using Language AgentsLLM Agents

    Escola Politénica, University of São Paulo

  4. AeroTherm-GPT: A Verification-Centered LLM Framework for Thermal Protection System Engineering Workflows

    Apr 2, 2026Chuhan Qiao, Jinglai Zheng, Jie Huang +3LLM Agent Workflow OptimizationConstrained Generative Modeling

    School of Civil Engineering, Beijing Jiaotong University, Beijing, 100044, China · Beijing Research Institute of Telemetry, Beijing, 100076, China

  5. Experience as a Compass: Multi-agent RAG with Evolving Orchestration and Agent Prompts

    Apr 1, 2026Sha Li, Naren RamakrishnanRetrieval-Augmented GenerationMulti-Agent Orchestration

    Virginia Tech

  6. Mimosa Framework: Toward Evolving Multi-Agent Systems for Scientific Research

    Mar 30, 2026Martin Legrand, Tao Jiang, Matthieu Feraud +5Autonomous Research AgentsMulti-Agent Systems

    Université Côte d’Azur, CNRS, ICN, Nice, France · Interdisciplinary Institute for Artificial Intelligence (3iA) Côte d’Azur, Sophia-Antipolis, France · Inria, Université Côte d’Azur, CNRS, I3S, France

  7. Self-evolving AI agents for protein discovery and directed evolution

    Mar 28, 2026Yang Tan, Lingrong Zhang, Mingchen Li +5Autonomous Research AgentsSelf-Evolving Agents

    Shanghai National Center for Applied Mathematics (SJTU Center) & Institute of Natural Sciences, Shanghai Jiao Tong University, Shanghai, 200240, China. · Shanghai Innovation Institute, Shanghai, 200231, China. · School of Computer Science, Shanghai Jiao Tong University, Shanghai, 200240, China. +1

  8. Simulating Human Cognition: Heartbeat-Driven Autonomous Thinking Activity Scheduling for LLM-based AI systems

    Mar 28, 2026Hong SuLLM Agent Workflow OptimizationCognitive Architectures for AI Agents

    School of Computer Science, Chengdu University of Information Technology, Chengdu, China

  9. AgentCollab: A Self-Evaluation-Driven Collaboration Paradigm for Efficient LLM Agents

    Mar 27, 2026Wenbo Gao, Renxi Liu, Xian Wang +8LLM AgentsLLM Agent Workflow Optimization

    Huawei · Hong Kong Polytechnic University

  10. UCAgent: An End-to-End Agent for Block-Level Functional Verification

    Mar 26, 2026Junyue Wang, Zhicheng Yao, Yan Pi +6LLM Agent VerificationAutomated Test Generation

    State Key Lab of Processors, Institute of Computing Technology, CAS · University of Chinese Academy of Sciences · Beijing Institute of Open Source Chip

  11. Supervising Ralph Wiggum: Exploring a Metacognitive Co-Regulation Agentic AI Loop for Engineering Design

    Mar 25, 2026Zeda Xu, Nikolas Martelaro, Christopher McCombLLM Agent Workflow OptimizationMetacognition in Language Models

    Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, PA 15213 · Human-Computer Interaction Institute, Carnegie Mellon University, Pittsburgh, PA, 15213 · Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, PA, 15213

  12. From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents

    Mar 23, 2026Ling Yue, Kushal Raj Bhandari, Ching-Yun Ko +6LLM Agent Workflow OptimizationAgentic Workflows

    Department of Computer Science, Rensselaer Polytechnic Institute, Troy, NY 12180 USA · IBM Research, Yorktown Heights, NY 10598 USA · Department of Mechanical, Aerospace, and Nuclear Engineering, Rensselaer Polytechnic Institute, Troy, NY 12180 USA

  13. Chimera: Latency- and Performance-Aware Multi-agent Serving for Heterogeneous LLMs

    Mar 23, 2026Kangqi Ni, Wenyue Hua, Xiaoxiang Shi +3LLM ServingLLM Inference Scheduling

    University of North Carolina, Chapel Hill · Microsoft · Carnegie Mellon University +2

  14. LLM-Powered Workflow Optimization for Multidisciplinary Software Development: An Automotive Industry Case Study

    Mar 22, 2026Shuai Wang, Yinan Yu, Earl Barr +1Workflow AutomationSoftware Engineering

    Chalmers University of Technology Gothenburg, Sweden · University College London London, United Kingdom · Volvo Group Gothenburg, Sweden

  15. WorkflowGen:an adaptive workflow generation mechanism driven by trajectory experience

    Mar 22, 2026Ruocan Wei, Shufeng Wang, Ziwei ShiAgentic WorkflowsLLM Agent Workflow Optimization

    China Telecom Cloud, Beijing, China

  16. Utility-Guided Agent Orchestration for Efficient LLM Tool Use

    Mar 20, 2026Boyan Liu, Gongming Zhao, Hongli XuLLM Agent OrchestrationLLM Tool Use

    University of Science and Technology of China, Hefei, Anhui, China · Suzhou Institute for Advanced Research, University of Science and Technology of China

  17. HyEvo: Self-Evolving Hybrid Agentic Workflows for Efficient Reasoning

    Mar 20, 2026Beibei Xu, Yutong Ye, Chuyun Shen +3Agentic WorkflowsLLM Agent Workflow Optimization

    East China Normal University · Beihang University · Shanghai University of International Business and Economics +1

  18. Efficient LLM Serving for Agentic Workflows: A Data Systems Perspective

    Mar 17, 2026Noppanat Wadlom, Junyi Shen, Yao LuLLM ServingLLM Agent Workflow Optimization

    National University of Singapore Singapore

  19. POLCA: Stochastic Generative Optimization with LLM

    Mar 16, 2026Xuanfei Ren, Allen Nie, Tengyang Xie +1Large Language Model-Guided OptimizationStochastic Optimization

    University of Wisconsin-Madison, Madison, WI · Google DeepMind, Mountain View, CA · Google Research, Kirkland, WA

  20. Orla: A Library for Serving LLM-Based Multi-Agent Systems

    Mar 13, 2026Rana Shahout, Hayder Tirmazi, Minlan Yu +1LLM Agent OrchestrationLLM Agent Serving

    Harvard University MA, USA · Boston University MA, USA

  21. NormCode Canvas: Making LLM Agentic Workflows Development Sustainable via Case-Based Reasoning

    Mar 13, 2026Xin Guan, Yunshan Li, Ze WangAgentic WorkflowsLLM Agent Orchestration

    Psylens AI, China · Shenzhen University, China · University College London, United Kingdom

  22. Separating Intelligence from Execution: A Workflow Engine for the Model Context Protocol

    Mar 13, 2026Abhinav Singh ParmarLLM Agent Tool GenerationLLM Agent Orchestration

    A Preprint

  23. One Supervisor, Many Modalities: Adaptive Tool Orchestration for Autonomous Queries

    Mar 12, 2026Mayank Saini, Arit Kumar BishwasMultimodal AgentsLLM Agent Orchestration

    PwC US

  24. EPOCH: An Agentic Protocol for Multi-Round System Optimization

    Mar 10, 2026Zhanlin Liu, Yitao Li, Munirathnam SrikanthLLM Agent Workflow OptimizationSelf-Improving Agents

  25. Ares: Adaptive Reasoning Effort Selection for Efficient LLM Agents

    Mar 9, 2026Jingbo Yang, Bairu Hou, Wei Wei +2Efficient Language Model ReasoningLLM Inference Efficiency

    Department of Computer Science, University of California, Santa Barbara · Center for Advanced AI, Accenture

  26. Evolving Medical Imaging Agents via Experience-driven Self-skill Discovery

    Mar 6, 2026Lin Fan, Pengyu Dai, Zhipeng Deng +4Self-Evolving AgentsLLM Agent Skill Learning

    Southwest Jiaotong University, China · The University of Tokyo, Japan · RIKEN, Japan +2

  27. CodeScout: Contextual Problem Statement Enhancement for Software Agents

    Mar 5, 2026Manan Suri, Xiangci Li, Mehdi Shojaie +5Software Engineering AgentsLLM Agent Workflow Optimization

    University of Maryland, College Park · Amazon Web Services (AWS) · Databricks

  28. DOVA: Deliberation-First Multi-Agent Orchestration for Autonomous Research Automation

    Mar 4, 2026Aaron Shen, Alfred ShenMulti-Agent OrchestrationAutonomous Research Agents

    University of California, Berkeley, USA · Amazon Web Services, USA

  29. ChatNeuroSim: An LLM Agent Framework for Automated Compute-in-Memory Accelerator Deployment and Optimization

    Mar 4, 2026Ming-Yen Lee, Shimeng YuCompute-in-MemoryElectronic Design Automation

    Georgia Institute of Technology, Atlanta, Georgia, USA

  30. stratum: A System Infrastructure for Massive Agent-Centric ML Workloads

    Mar 3, 2026Arnab Phani, Elias Strauss, Sebastian SchelterLLM Agent Workflow Optimization

    BIFOLD & TU Berlin