LLM Agent Workflow Optimization

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

21 papers in the last four weeks, up 91% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 119

All topics

Control-Data Flow Separation: Stable Prompt Optimization in Multi-Agent LLMs
Sep 1, 2026Wentao Zhang, Syed Shariyar Murtaza, Junaid Ahmad Bhatti +4LLM Agent Orchestration LLM Agent Workflow Optimization
University of Waterloo · Manulife
ProgRouter: Online Progress-Guided Orchestration for Multi-Agent LLM Workflows under Quality-Cost Tradeoffs
Aug 26, 2026Songyuan Li, Ahmed M. Abdelmoniem, Shiqiang WangLLM Inference Efficiency Multi-Agent Orchestration
Aston University, UK · Queen Mary University of London, UK · University of Exeter, UK
Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control
Aug 12, 2026Josef Liyanjun ChenLLM Agent Orchestration Agent Harness Optimization
Independent Researcher
MEGA: Self-Evolving Agent Optimization Infrastructure via Wisdom Graph
Aug 11, 2026Jung Hwan Lee, Kyu Ho Lee, Gwang Hoon YooMulti-Agent System Optimization Agent Harness Optimization
Mind AI Tech Report
FlowScout: From Execution Feedback to Reliable Tool-Using Agent Workflows
Aug 10, 2026Shuo Hao, You Lu, Bihuan Chen +1Agentic Workflows LLM Agent Workflow Optimization
College of Computer Science and Artificial Intelligence, Fudan University, China
The Optimizer Is the Agent: Reasoning-Driven Search across Prompts, Programs, and ML Workflows
Aug 7, 2026Junbo Li, Boyi Liu, Canwen Xu +5Large Language Model-Guided Optimization LLM Agent Workflow Optimization
The University of Texas at Austin · Snowflake
Online Monitoring and Corrective Steering of Programming Agents
Aug 7, 2026Shuyang Liu, Saman Dehghan, Ji Young Kim +3Software Engineering Agents LLM Agent Workflow Optimization
University of Illinois Urbana-Champaign, USA · IBM, USA
HarnessOpt-Bench: Evaluating LLMs at Harness Optimization
Aug 6, 2026Varun Ursekar, Apaar Shanker, Yash Maurya +4Large Language Model-Guided Optimization LLM Agent Evaluation
Scale AI
CodeGrep: An RL-Trained Retrieval Agent for LLM Coding Agents
Aug 6, 2026Wuya Chen, Yihao yang, Yang Cao +1AI Coding Agents LLM Agent Workflow Optimization
1Netease Guangzhou AI Lab · 2Independent Researcher
Global Optimization and Inference-Time Region Grafting for Agentic Workflows
Aug 3, 2026Donghyeok Koh, Gyuwan Kim, Jinyeong Bak +4Inference-Time Optimization Agentic Workflows
1HBNU · 2UCSB · 3SKKU +1
TraceCompiler: Skill-Guided Mining and Compilation of LLM Agent Traces into Mostly Deterministic Workflows
Aug 3, 2026Salma El Yadouni, Guanyi LiAgentic Workflows LLM-Based Program Synthesis
EPFL · EPFL, Lausanne, Switzerland · Binome Technologies +1
AiFlow: Token-Native Reactive Orchestration with Bounded Backpressure for Streaming LLM Applications
Aug 1, 2026Qunhui ZhangLLM Serving LLM Agent Orchestration
School of Software, Shanghai Jiao Tong University, Shanghai 200240, China
Learning Compositional Meta-Routing for Agentic Workflows: An Executable Benchmark
Jul 31, 2026Natan Vidra, Alina Kapanova, Arun Kanhai +1Agentic Workflows LLM Agent Workflow Optimization
1Anote AI · 2Cornell University · 3CUNY +1
Agent-UCT: Upper Confidence Bounds Applied to Trees for Agentic Workflow Optimization with Cost-Awareness
Jul 27, 2026Yang Li, Hai Liu, Dian Shao +8Retrieval-Augmented Generation Cost-Aware Inference
1The University of Hong Kong · School of Artificial Intelligence, Jiangxi Science and Technology Normal University · 3The Hong Kong University of Science and Technology +2
Focus Is All You Need: Adaptive Goal-aware Attention Orchestration for Multi-Agent Graph Systems
Jul 26, 2026Mingzhou Fan, Siyuan Xu, Mingxuan YuanMulti-Agent System Optimization LLM Agent Orchestration
Agent Team Work Zone: An Automated, Persistent Workspace for Long-Lived Claude Code Agent Teams
Jul 24, 2026Shouren WangLLM Agent Memory LLM Agent Workflow Optimization
Case Western Reserve University
Workflow-Localized Mechanism Learning: Attribution-Guided Repair and Knowledge Reuse for Structured Agent Skills
Jul 23, 2026Zibin Lin, Shengli Zhang, Taotao Wang +3LLM Agent Workflow Optimization LLM Agent Skill Learning
Shenzhen University, Shenzhen, China
Co-Harness: Co-Evolving Harnesses and Model Weights for LLM Agents
Jul 17, 2026Zhengyu Chen, Teng Xiao, Huaisheng Zhu +3Agent Harness Optimization LLM Agent Workflow Optimization
Meituan · Allen Institute for AI · Independent
Structured Feedback Improves Repair in an LLM Agent Loop
Jul 15, 2026Jaideep Ray, Ankit GoyalLLM Self-Correction LLM Agent Evaluation
Independent Researcher
Do AI Agents Know When a Task Is Simple? Toward Complexity-Aware Reasoning and Execution
Jul 14, 2026Junjie Yin, Xinyu FengSoftware Engineering Agents LLM Agent Evaluation
University of Tennessee, Knoxville, TN 37996, USA · Microsoft, Redmond, WA 98052, USA
TTHE: Test-Time Harness Evolution
Jul 9, 2026Jun Nie, Yonggang Zhang, Jun Song +5Test-Time Adaptation Agent Harness Optimization
Hong Kong Baptist University · University of Science and Technology of China · Hong Kong Generative AI Research & Development Center, The Hong Kong University of Science and Technology +1
Progressive Crystallization: Turning Agent Exploration into Deterministic, Lower-Cost Workflows in Production
Jul 8, 2026Arun MalikCost-Aware Inference Agentic Workflows
Microsoft Azure Networking
A Workflow-Aware Serving Layer for Agentic Applications
Jul 3, 2026Jiayi Qian, Zishen Wan, Hanchen Yang +3Cost-Aware Inference Agentic Workflows
Columbia University New York, NY, USA · Intel Los Angeles, CA, USA
Beyond Next-Token Prediction: An RLVR Proof of Concept for Tool-Use Agents on Atlassian Workflows
Jul 1, 2026Karthikeya Aditya Vissa, Sankalp Mane, Ananya Mantravadi +2Tool-Augmented Language Model Agents LLM Agent Workflow Optimization
Centific
SWE-Router: Routing in Multi-turn Agentic Software Engineering Tasks
Jun 30, 2026Seongho Son, Sangwoong Yoon, Jiahua Tang +3Software Engineering Agents LLM Agent Workflow Optimization
University College London, United Kingdom · Ulsan National Institute of Science and Technology, South Korea · PSL Research University, France +1
Contrastive Reflection for Iterative Prompt Optimization
Jun 29, 2026Derek Koh, Jinghui Mo, Benjamin H. Le +7LLM Self-Refinement LLM Agent Workflow Optimization
LinkedIn Sunnyvale, California, USA
Beyond Static Endpoints: Tool Programs as an Interface for Flexible Agentic Web Services
Jun 18, 2026Mugeng Liu, Shuoqi Li, Yixuan Zhang +1LLM Agent Orchestration Agentic Workflows
School of Computer Science, Peking University, Beijing, China · School of Software & Microelectronics, Peking University, Beijing, China · Institute for Artificial Intelligence, Peking University, Beijing, China
FAPO: Fully Automated Prompt Optimization of Multi-Step LLM Pipelines
Jun 17, 2026Paul Kassianik, Baturay Saglam, Huaibo Zhao +4Large Language Model-Guided Optimization LLM Agent Workflow Optimization
Foundation AI–Cisco Systems Inc. · Yale University
Recursive Self-Evolving Agents via Held-Out Selection
Jun 17, 2026Michael Nguyen, Quoc Nguyen, Paul VuongLLM Agent Evaluation LLM Agent Workflow Optimization
School of Information Technology Monash University Malaysia
DynAMO:Dynamic Asset Management Orchestration via Topological Multi-Agent Scheduling
Jun 14, 2026Kanishk Kushwaha, Vikrant Vinod Bansode, Harsh Vardhan +1LLM Inference Efficiency Multi-Agent Orchestration
Gati Shakti Vishwavidyalaya · IBM Research

Sep 1, 2026, cs.AIJ/K move · Enter open · S save

Control-Data Flow Separation: Stable Prompt Optimization in Multi-Agent LLMs

Wentao Zhang, Syed Shariyar Murtaza, Junaid Ahmad Bhatti, Utkarsh Soni+3

University of Waterloo · Manulife

LLM Agent Orchestration LLM Agent Workflow Optimization Prompt Optimization Multi-Agent Communication Multi-Agent LLMs

Open paper AskPDF arXiv

Prompt optimization can improve multi-agent LLM systems, but the prompts being optimized often serve two entangled roles: generating task-relevant content and specifying execution-critical protocols, such as message routing, output formatting, and termination signals, on which the underlying code relies. As a result, a prompt edit intended to improve content generation can inadvertently corrupt the protocol and cause the entire agent pipeline to fail. Our key observation is that these two roles have different representations: execution protocols are typically structured, while task-relevant content is usually expressed in unstructured language. Based on this, we propose control-data flow separation, where execution-critical control is represented as typed, validated program objects, while task-relevant language remains the optimizable data flow for agent communication. This design allows optimizers to improve multi-agent behavior without exposing the routing or formatting interface to prompt drift. Across synthetic reasoning, collaborative review generation, and insurance rating workflows, our framework empirically achieves 100% eventual protocol validity while consistently improving task performance.

Momentum

Related topics

Latest papers 119