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.

HyperTool: Beyond Step-Wise Tool Calls for Tool-Augmented Agents
Jun 11, 2026Yaxin Du, Yifan Zhou, Yujie Ge +7Tool-Augmented Language Model Agents LLM Agent Workflow Optimization
Shanghai Jiao Tong University · IQuest Research · Beijing University of Aeronautics and Astronautics
EvoFlux: Inference-Time Evolution of Executable Tool Workflows for Compact Agents
Jun 10, 2026Kushal Raj Bhandari, Ling Yue, Ching-Yun Ko +4Inference-Time Search LLM Agent Workflow Optimization
Rensselaer Polytechnic Institute, Troy, NY 12180 USA · IBM Research, Yorktown Heights, NY 10598 USA
INFRAMIND: Infrastructure-Aware Multi-Agent Orchestration
Jun 9, 2026Ahasan Kabir, Mengxin Zheng, Qian LouMulti-Agent System Optimization Multi-Agent Orchestration
University of Central Florida
FlowBank: Query-Adaptive Agentic Workflows Optimization through Precompute-and-Reuse
Jun 9, 2026Lingzhi Yuan, Chenghao Deng, Fangxu Yu +3Multi-Agent LLM Systems Multi-Agent System Optimization
University of Maryland, College Park · Amazon
Less Context, Better Agents: Efficient Context Engineering for Long-Horizon Tool-Using LLM Agents
Jun 8, 2026Abhilasha Lodha, Mahsa Pahlavikhah Varnosfaderani, Abir Chakraborty +1LLM Inference Efficiency Tool-Augmented Language Model Agents
Microsoft
Bayesian-Agent: Posterior-Guided Skill Evolution for LLM Agent Harnesses
Jun 6, 2026Xiaojun Wu, Cehao Yang, Honghao Liu +7Agent Harness Optimization LLM Agent Workflow Optimization
1IDEA Research · 2The Hong Kong University of Science and Technology (Guangzhou) · 3DataArcTech Ltd.
Cost-Aware Speculative Execution for LLM-Agent Workflows: An Integrated Five-Dimension Method
Jun 5, 2026Faisal FareedLLM Agent Orchestration Cost-Aware Inference
AWS
Declarative Skills for AI Agents in Knowledge-Grounded Tool-Use Workflows
Jun 5, 2026M. Danish Lim, I. Danial Bin Sharudin, Wen Han Chen +2LLM Agent Orchestration LLM Agent Workflow Optimization
School of Computing and Information Systems Singapore Management University Singapore
Streaming Communication in Multi-Agent Reasoning
Jun 3, 2026Zhen Yang, Xiaogang Xu, Wen Wang +3Multi-Agent LLM Systems Multi-Agent System Optimization
HKUST(GZ) · ZJU · Alibaba Group +1
MOSAIC: Efficient Mixture-of-Agent Scheduling via Adaptive Aggregation and Inference Concurrency
Jun 2, 2026Saptarshi Mitra, Yifan Zhang, Rachid Karami +5LLM Inference Efficiency Multi-Agent System Optimization
University of California, Irvine, USA · University of Southern California, Los Angeles, USA · Intel, USA
Learning to Construct Practical Agentic Systems
May 29, 2026Aditya Kumar, Zhihan Lei, Jerry Yan +6LLM Agent Orchestration Agentic Workflows
Carnegie Mellon University · Dept. of Computer Science Emory University
Specialize Roles, Mix Deployments: Pushing the Cost-Accuracy Frontier of LLM Agent Teams
May 28, 2026Yinsicheng Jiang, Liang Cheng, Yeqi Huang +6Multi-Agent LLM Systems LLM Agent Evaluation
University of Edinburgh · 2Microsoft Research
Natural Language Query to Configuration for Retrieval Agents
May 26, 2026Melissa Z. Pan, Negar Arabzadeh, Mathew Jacob +3Retrieval-Augmented Generation Cost-Aware Inference
UC Berkeley · University of Washington · Microsoft Azure Research - Systems
UnityMAS-O: A General RL Optimization Framework for LLM-Based Multi-Agent Systems
May 26, 2026Yiqun Chen, Wei Yang, Erhan Zhang +14Multi-Agent LLM Systems Multi-Agent System Optimization
Renmin University of China · Xiaohongshu Inc.
Stateful Inference for Low-Latency Multi-Agent Tool Calling
May 25, 2026Victor NorgrenLLM Inference Efficiency Multi-Agent LLM Systems
LayerScale, Inc.
DarkForest: Less Talk, Higher Accuracy for Multi-Agent LLMs
May 24, 2026Yi Li, Songtao Wei, Dongming Jiang +3Multi-Agent LLM Systems Multi-Agent System Optimization
University of Texas at Dallas · Independent Researcher · University of California, Davis
PANDO: Efficient Multimodal AI Agents via Online Skill Distillation
May 24, 2026Yubo Li, Yidi Miao, Yuntian Shen +1LLM Agent Workflow Optimization LLM Agent Skill Learning
When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs
May 22, 2026Yifan Zeng, Yiran Wu, Yaolun Zhang +4Multi-Agent LLM Systems LLM Agent Workflow Optimization
1Oregon State University · 2Pennsylvania State University · 3Adobe Inc. +1
Parallel Context Compaction for Long-Horizon LLM Agent Serving
May 22, 2026Musa Cim, Burak Topcu, Chita Das +1LLM Inference Efficiency LLM Agent Workflow Optimization
The Pennsylvania State University
PACE: Two-Timescale Self-Evolution for Small Language Model Agents
May 21, 2026Chen Ling, Pei Chen, Albert Guan +4Small Language Models LLM Agent Workflow Optimization
Amazon
GraphFlow: A Graph-Based Workflow Management for Efficient LLM-Agent Serving
May 21, 2026Ao Li, Shangpeng Yang, Fahao Chen +3LLM Agent Orchestration Agentic Workflows
School of Cyber Science and Engineering, Xi’an Jiaotong University, Xi’an, China · School of Artificial Intelligence, Shandong University, Jinan, China · 3Shanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai, China.
Compiling Agentic Workflows into LLM Weights: Near-Frontier Quality at Two Orders of Magnitude Less Cost
May 21, 2026Simon Dennis, Rivaan Patil, Kevin Shabahang +1LLM Agent Orchestration Agentic Workflows
i14, University of Melbourne · i14
Agent JIT Compilation for Latency-Optimizing Web Agent Planning and Scheduling
May 20, 2026Caleb Winston, Ron Yifeng Wang, Azalia Mirhoseini +1Computer-Use Agents LLM Agent Orchestration
Stanford University, Stanford, CA, USA.
ZEBRA: Zero-shot Budgeted Resource Allocation for LLM Orchestration
May 19, 2026May Hamri, Inbal Talgam-CohenLLM Agent Orchestration Cost-Aware Inference
1Tel Aviv University
PROTEA: Offline Evaluation and Iterative Refinement for Multi-Agent LLM Workflows
May 18, 2026Kazuki Kawamura, Satoshi Waki, Kei TatenoMulti-Agent LLM Systems LLM Agent Evaluation
Sony Group Corporation
R2V Agent: Teaching SLMs When to Ask for Help
May 15, 2026Raghu Vamshi Hemadri, Humaira Firdowse Mohammed, Rishabh Maheshwary +5AI Agent Reliability Tool-Augmented Language Model Agents
New York University Tandon School of Engineering · University of California, San Diego · ServiceNow Research +3
Skim: Speculative Execution for Fast and Efficient Web Agents
May 15, 2026Mike Wong, Kevin Hsieh, Suman Nath +1LLM Inference Efficiency LLM Agent Workflow Optimization
Princeton University · Princeton, USA · Microsoft Research +1
Harnesses for Inference-Time Alignment over Execution Trajectories
May 15, 2026Boyuan Wang, Bochao Li, Minghan Wang +2LLM Planning Agent Harness Optimization
Southern University of Science and Technology
COLLATOR: Compositional Multi-Agent Orchestration with Counterfactual Reinforcement Learning
May 14, 2026Xudong Chen, Yixin Liu, Hua Wei +1Multi-Agent System Optimization Multi-Agent Orchestration
Good to Go: The LOOP Skill Engine That Hits 99% Success and Slashes Token Usage by 99% via One-Shot Recording and Deterministic Replay
May 14, 2026Xiaohua Wang, Kai Yu, XuXiao Liang +2LLM Inference Efficiency AI Agent Reliability
1Artificial Intelligence Research Center, Bengbu Medical University, Bengbu 233000, China. · 2CHARMMIRAEL Biotech Co., Ltd, Nanjing 210000, China.

Jun 11, 2026J/K move · Enter open · S save

HyperTool: Beyond Step-Wise Tool Calls for Tool-Augmented Agents

Yaxin Du, Yifan Zhou, Yujie Ge, Jiajun Wang+6

Shanghai Jiao Tong University · IQuest Research · Beijing University of Aeronautics and Astronautics

Tool-Augmented Language Model Agents LLM Agent Workflow Optimization LLM Tool Use LLM Agent Training Tool Use

Open paper AskPDF arXiv

Tool-augmented LLM agents commonly rely on step-wise atomic tool calls, where each invocation, observation, and value transfer is exposed in the main reasoning trace. This creates an execution-granularity mismatch: locally deterministic tool workflows are unfolded into repeated model-visible decisions, consuming context and forcing the model to manage low-level dataflow in the trace. We introduce HyperTool, a unified executable MCP-style tool interface that changes the model-visible unit of tool execution. A model invokes HyperTool with a code block that can call existing tools through their original schemas, manipulate returned values, and pass intermediate results locally, folding deterministic tool subroutines into a single outer call. To train models to use this interface, we synthesize HyperTool-format trajectories from cross-tool compositional tasks and verify them in real MCP environments. On MCP-Universe, HyperTool improves average accuracy from 15.69% to 35.29% on Qwen3-32B and from 9.93% to 33.33% on Qwen3-8B, and surpass GPT-OSS and Kimi-k2.5 on average accuracy, showing that our HyperTool can substantially improve multi-step tool use.