LLM Agent Workflow Optimization

LLM: Large Language Model

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

287 papers37 papers in the last four weeks, down 34% on the four weeks before. 0.3% of all new papers.

  1. Generalist Meets Specialists: An Evolving Multimodal Agent with Persistent Tool Orchestration for Traffic Scenario Understanding

    Nov 19, 2026Linjia Kang, Binhan Jiang, Juan Yang +6Tool-Using Vision-Language AgentsLLM Agent Workflow Optimization

  2. Learning to Coordinate: LLM-Guided Workflow Evolution for Token-Efficient Red Teaming

    Nov 18, 2026Xiaoyang Xing, Wenyu Dai, Xiaoliang Gong +2Automated Red TeamingLLM Agent Workflow Optimization

  3. Thinking Fast, Anywhere: One System-1 for the Decision Points of Any Agent Workflow

    Nov 18, 2026Rui Li, Liyang He, Zheng Zhang +2LLM Agent Workflow OptimizationLLM Agent Efficiency

  4. Agent-Native by Design: A Programming Language for Agentic Applications

    Nov 16, 2026Jayanaka Dantanarayana, Savini Kashmira, Xiaoyu Ma +4Agentic WorkflowsAI Agent Architecture

  5. Agent-Guided Configuration Tuning for SMT Solvers

    Nov 16, 2026Cong Wang, Qiaoyi Zheng, Zhaoguo Wang +1Satisfiability Modulo TheoriesLarge Language Model-Guided Optimization

  6. EfficientSkill: Learning Skills for Token-Efficient Multi-Turn Agents

    Nov 15, 2026Deep Shah, Sanket Badhe, Nehal Kathrotia +1LLM Agent Workflow OptimizationLLM Agent Skill Learning

  7. ReTrace: Distilling Tool-Using Agents into Planner-Free Workflows

    Nov 10, 2026Kaiyuan Hou, Yang Ping Kuo, Indranil Bhattacharya +6LLM Agent Workflow OptimizationWorkflow Automation

  8. More with Less: Efficient Parallel Scientific Code Translation via an Agent-Skill Workflow

    Nov 6, 2026Jianuo Shen, Pengyi Xu, Bo ZhangCode TranslationLLM Agent Workflow Optimization

  9. Rethinking Agent Trajectory Compression: A Workflow-Aware Perspective

    Nov 6, 2026Qijia Zhuang, Rui Liu, Wenqi Hu +1Context Compaction for LLM AgentsTask-Aware Compression

  10. Divide, Diagnose, and Compose: Optimizing Agentic Pipelines and Harnesses

    Nov 5, 2026Divij Handa, Christopher Tensmeyer, Jihyung Kil +1LLM Agent Workflow OptimizationAgent Harness Optimization

  11. The Last Mile to the Real World: Agent-Native Primitives as Reusable Building Blocks for Solving Real-World Tasks

    Nov 5, 2026Haibo Jin, Peng Kuang, Xiaopeng Yuan +11LLM Agent HarnessesLLM Agents

  12. Ask, Don't Equip: Question-Driven Coding Agents for Deep Kernel Optimization

    Nov 2, 2026Gabriele Oliaro, Jaeseong Lee, Zhaoyuan Su +3GPU Kernel OptimizationGPU Kernel Generation

  13. Self-Evolving Agentic Workflows via Semantic Decomposition of Complex Tasks

    Nov 1, 2026Zichuan Fu, Junjia Qi, Xian Wu +4Agentic WorkflowsLLM Agent Workflow Optimization

  14. A Self-Exploring and Self-Evolving Paradigm for Adaptive Edge AI Development

    Nov 1, 2026Leming Shen, Qiang Yang, Xinyu Huang +3AI Coding AgentsSelf-Evolving Agents

  15. When Should AI Agents Ask? Clarification Requests Under Limited Human Attention

    Oct 30, 2026Hanzhao Wang, Shengjie Liu, Zhengchao WangHuman-AI InteractionHuman-AI Decision Making

  16. Locating and Closing Information Gaps in Multi-Agent Systems

    Oct 29, 2026Yaxin Gong, Chongming Gao, Gangyi Zhang +7LLM Agent Workflow OptimizationMulti-Agent Systems

  17. Evolving Agent Teams

    Oct 27, 2026Shiyi Cao, Ziming Mao, Dacheng Li +2Multi-Agent CodingSelf-Evolving Agents

  18. RouteDRAG: Learning to Route and Control Agentic Execution for Multimodal Document RAG

    Oct 27, 2026Zekai Chen, Hao Zhu, Yu Liu +5Agentic RAGMultimodal RAG

  19. Work Agents: Systems, Capabilities, and Optimization

    Oct 26, 2026Zishan Xu, Enjun Du, Mingqi Gao +13LLM Agent ReliabilityLLM Agent Workflow Optimization

  20. AIPC: Evidence-Guided Agent Workflows for PyTorch Project Deployment

    Oct 26, 2026Zhanwei Wu, Jianhao Su, Brian Zhang +11AI Accelerator InferenceLLM Agent Workflow Optimization