LLM Agent Workflow Optimization

LLM: Large Language Model

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

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

SPIN: Structural LLM Planning via Iterative Navigation for Industrial Tasks
May 13, 2026Yusuke Ozaki, Dhaval PatelLLM Agent Workflow Optimization Tool-Use Planning
University at Albany · Kwansei Gakuin University · IBM, New York
FlowCompile: An Optimizing Compiler for Structured LLM Workflows
May 13, 2026Junyan Li, Zhang-Wei Hong, Maohao Shen +2LLM Agent Orchestration Cost-Aware Inference
UMass Amherst · MIT-IBM Watson AI Lab · MIT
CANTANTE: Optimizing Agentic Systems via Contrastive Credit Attribution
May 13, 2026Tom ZehleMulti-Agent LLM Systems Multi-Agent System Optimization
University of Freiburg · ELLIS Institute Tübingen
SkillSmith: Compiling Agent Skills into Boundary-Guided Runtime Interfaces
May 12, 2026Duling Xu, Zheng Chen, Zaifeng Pan +4LLM Agent Workflow Optimization LLM Agent Skill Retrieval
AetherHeart Tech Co., Ltd., Shanghai, China · Renmin University of China, Beijing, China · University of California San Diego, CA, USA
Agent-X: Full Pipeline Acceleration of On-device AI Agents
May 11, 2026Jinha Chung, Byeongjun Shin, Jiin Kim +1LLM Inference Efficiency On-Device Language Model Inference
KAIST Republic of Korea, Daejeon
AgentSlimming: Towards Efficient and Cost-Aware Multi-Agent Systems
May 9, 2026Yulang Chen, Haoxuan Peng, Jinyan Liu +3Multi-Agent LLM Systems Multi-Agent System Optimization
1Shanghai Jiao Tong University · 2Nanjing University · 3The University of Sydney +2
EvoMAS: Learning Execution-Time Workflows for Multi-Agent Systems
May 9, 2026Chengdong Xu, Kaiqiang Ke, Ziheng Liu +4Multi-Agent LLM Systems Multi-Agent System Optimization
Sun Yat-Sen University · ShanghaiTech University · Zhejiang University +1
FlashEvolve: Accelerating Agent Self-Evolution with Asynchronous Stage Orchestration
May 8, 2026Zhengding Hu, Mingge Lu, Zhen Wang +8LLM Agent Orchestration LLM Agent Workflow Optimization
University of California, San Diego · Georgia Institute of Technology
Efficient Serving for Dynamic Agent Workflows with Prediction-based KV-Cache Management
May 7, 2026Haoyu Zheng, Fangcheng Fu, Jia Wu +6LLM Inference Efficiency KV Caching
Wuhan University · Shanghai Jiao Tong University · Macquarie University +2
Uno-Orchestra: Parsimonious Agent Routing via Selective Delegation
May 6, 2026Zhiqing Cui, Haotong Xie, Jiahao Yuan +11Multi-Agent System Optimization Multi-Agent Orchestration
Project lead.
MemFlow: Intent-Driven Memory Orchestration for Small Language Model Agents
May 5, 2026Jiayi Chen, Yingcong Li, Guiling WangLLM Agent Workflow Optimization Persistent Memory for Language Models
New Jersey Institute of Technology, Newark, USA
Agent Capsules: Quality-Gated Granularity Control for Multi-Agent LLM Pipelines
May 1, 2026Aninda RayLLM Inference Efficiency Multi-Agent LLM Systems
FlowBot: Inducing LLM Workflows with Bilevel Optimization and Textual Gradients
Apr 29, 2026Hongyeon Yu, Young-Bum Kim, Yoon KimAgentic Workflows LLM Agent Workflow Optimization
Naver Search US · Massachusetts Institute of Technology
Pythia: Exploiting Workflow Predictability for Efficient Agent-Native LLM Serving
Apr 28, 2026Shan Yu, Junyi Shu, Yuanjiang Ni +14LLM Inference Efficiency Multi-Agent LLM Systems
UCLA · Alibaba Cloud Computing · Alibaba Group +6
Why Search When You Can Transfer? Amortized Agentic Workflow Design from Structural Priors
Apr 27, 2026Shiyi Du, Jiayuan Liu, Weihua Du +6Agentic Workflows LLM-Based Program Synthesis
Carnegie Mellon University · Foundations of Cooperative AI Lab (FOCAL) · University of Notre Dame
GraphPlanner: Graph Memory-Augmented Agentic Routing for Multi-Agent LLMs
Apr 26, 2026Tao Feng, Haozhen Zhang, Zijie Lei +2Multi-Agent LLM Systems LLM Agent Orchestration
Department of Computer Science University of Illinois Urbana-Champaign Urbana, IL, USA
The Last Harness You'll Ever Build
Apr 22, 2026Haebin Seong, Li Yin, Haoran Zhang +1Meta-Learning Agent Harness Optimization
Toward Reliable Design of LLM-Enabled Agentic Workflows: Optimizing Latency-Reliability-Cost Tradeoffs
Apr 21, 2026Ya-Ting Yang, Quanyan ZhuCost-Aware Inference Agentic Workflows
New York University Brooklyn, NY, USA
GraSP: Graph-Structured Skill Compositions for LLM Agents
Apr 20, 2026Tianle Xia, Lingxiang Hu, Yiding Sun +5LLM Agent Orchestration LLM Agent Workflow Optimization
Tencent
Complete Cyclic Subtask Graphs for Tool-Using LLM Agents: Flexibility, Cost, and Bottlenecks in Multi-Agent Workflows
Apr 17, 2026Luay Gharzeddine, Samer SaabMulti-Agent Coordination Multi-Agent Orchestration
1Dept of Computer Science, Lebanese American University. · 2*Dept of Electrical and Computer Engineering, Lebanese American University.
Scepsy: Serving Agentic Workflows Using Aggregate LLM Pipelines
Apr 16, 2026Otto White, Marcel Wagenländer, Britannio Jarrett +7LLM Inference LLM Inference Scheduling
Imperial College London · Independent Researcher
Local-Splitter: A Measurement Study of Seven Tactics for Reducing Cloud LLM Token Usage on Coding-Agent Workloads
Apr 14, 2026Justice Owusu Agyemang, Jerry John Kponyo, Elliot Amponsah +2LLM Agent Workflow Optimization LLM Inference Efficiency
Sperix Labs · VIA Cybersecurity Lab, KNUST · Quantum and Assistive Technologies Lab, KNUST
Three Roles, One Model: Role Orchestration at Inference Time to Close the Performance Gap Between Small and Large Agents
Apr 13, 2026S. Aaron McClendon, Jorge Gallego-Feliciano, Stavros Zervoudakis +1Tool-Using Language Agents LLM Agent Workflow Optimization
Aimpoint Digital Labs, Atlanta, GA, USA · New York University, New York, NY, USA
VineLM: Trie-Based Fine-Grained Control for Agentic Workflows
Apr 9, 2026Nikos Pagonas, Matthew Lou, Tianyi Peng +2LLM Agent Workflow Optimization Agentic Workflows
Columbia University
B-PASTE: Beam-Aware Pattern-Guided Speculative Execution for Resource-Constrained LLM Agents
Apr 9, 2026Yanfei SongLLM Agent Workflow Optimization LLM Inference Scheduling
Independent Researcher
Beyond Human-Readable: Rethinking Software Engineering Conventions for the Agentic Development Era
Apr 8, 2026Dmytro UstynovSoftware Engineering Agents LLM Agent Workflow Optimization
Military Institute of Telecommunications and Information Technologies (MITIT)
Agentic Compilation: Mitigating the LLM Rerun Crisis for Minimized-Inference-Cost Web Automation
Apr 8, 2026Jagadeesh ChundruWeb Agents LLM Agent Workflow Optimization
Selfotix
Select-then-Solve: Paradigm Routing as Inference-Time Optimization for LLM Agents
Apr 8, 2026Heng Zhou, Zelin Tan, Zhemeng Zhang +15LLM Agent Workflow Optimization LLM Agents
Design First, Code Later: Aesthetically Pleasing Template-Free Slides Generation
Apr 8, 2026Zhiyao Cui, Chenxu Wang, Shuyue Hu +4LLM Agent Workflow Optimization
School of Cybersecurity, Northwestern Polytechnical University · Shanghai Artificial Intelligence Laboratory · Shanghai Innovation Institution +1
AgentOpt v0.1 Technical Report: Client-Side Optimization for LLM-Based Agent
Apr 7, 2026Wenyue Hua, Sripad Karne, Qian Xie +4LLM Agent Workflow Optimization LLM Agent Efficiency
Microsoft Research, AI Frontiers · Columbia University · Cornell University

May 13, 2026J/K move · Enter open · S save

SPIN: Structural LLM Planning via Iterative Navigation for Industrial Tasks

Yusuke Ozaki, Dhaval Patel

University at Albany · Kwansei Gakuin University · IBM, New York

LLM Agent Workflow Optimization Tool-Use Planning Graph-Based Planning LLM Agent Planning

Open paper AskPDF arXiv

Industrial LLM agent systems often separate planning from execution, yet LLM planners frequently produce structurally invalid or unnecessarily long workflows, leading to brittle failures and avoidable tool and API cost. We propose SPIN, a planning wrapper that combines validated Directed Acyclic Graph (DAG) planning with prefix based execution control. SPIN enforces a strict DAG contract through \_validate\_plan\_text and repair prompting, producing executable plans before downstream execution, and then evaluates DAG prefixes incrementally to stop when the current prefix is sufficient to answer the query. On AssetOpsBench, across 261 scenarios, SPIN reduces executed tasks from 1061 to 623 and improves Accomplished from 0.638 to 0.706, while reducing tool calls from 11.81 to 6.82 per run. On MCP Bench, the same wrapper improves planning, grounding, and dependency related scores for both GPT OSS1 and Llama 4 Maverick.