Agent Loop

Follow this topic Ask about this topic

Momentum

13 papers in the last four weeks, up 63% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 83

All topics

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 +2Agent Loop Deterministic Replay
1Artificial Intelligence Research Center, Bengbu Medical University, Bengbu 233000, China. · 2CHARMMIRAEL Biotech Co., Ltd, Nanjing 210000, China.
Engineering Robustness into Personal Agents with the AI Workflow Store
May 11, 2026Roxana Geambasu, Mariana Raykova, Pierre Tholoniat +3Agentic Workflows Artificial Intelligence Agents
Columbia University and Google · Google
FlashEvolve: Accelerating Agent Self-Evolution with Asynchronous Stage Orchestration
May 8, 2026Zhengding Hu, Mingge Lu, Zhen Wang +8Self-Evolving Agents Alphaevolve
University of California, San Diego · Georgia Institute of Technology
Bridging Modalities, Spanning Time: Structured Memory for Ultra-Long Agentic Video Reasoning
May 8, 2026Jiazheng Li, Chi-Hao Wu, Yunze Liu +3Video Agent Multimodal Memory
University of Connecticut · Northwestern University · University of Virginia
From Agent Loops to Deterministic Graphs: Execution Lineage for Reproducible AI-Native Work
May 7, 2026Josh Rosen, Seth RosenAgent Loop Artificial Intelligence Systems
ThruWire, Inc.
VibeServe: Can AI Agents Build Bespoke LLM Serving Systems?
May 7, 2026Keisuke Kamahori, Shihang Li, Simon Peter +1Large Language Model Serving Large Language Model Agents
University of Washington
BALAR : A Bayesian Agentic Loop for Active Reasoning
May 6, 2026Aymen Echarghaoui, Dongxia Wu, Emily B. FoxLLM Reasoning Strategies Multi-Turn Interactions
Department of Statistics, Stanford University · Department of Computer Science, Stanford University
Hierarchical Visual Agent: Managing Contexts in Joint Image-Text Space for Advanced Chart Reasoning
May 5, 2026Qihua Dong, Ruozhen He, Junwen Chen +4Chart Visual Reasoning
1Northeastern University · 2Rice University · 3Amazon AGI
DataEvolver: Let Your Data Build and Improve Itself via Goal-Driven Loop Agents
May 3, 2026Qisong Zhang, Wenzhuo Wu, Zhuangzhuang Jia +7Alphaevolve Iterative Self-Correction
School of Artificial Intelligence, Beijing University of Posts and Telecommunications · Institute of Artificial Intelligence · Institute of Artificial Intelligence (TeleAI), China Telecom
Automated Interpretability and Feature Discovery in Language Models with Agents
May 2, 2026Arnau Marin-Llobet, Javier FerrandoMechanistic Interpretability Interpretability
Harvard University
ADEMA: A Knowledge-State Orchestration Architecture for Long-Horizon Knowledge Synthesis with LLMAgents
Apr 28, 2026Zhou Hanlin, Chan Huah YongLong-Horizon Agents Agent Loop
School of Computer Sciences, Universiti Sains Malaysia (USM), Penang, Malaysia · Xiamen Software Vocational & Technical College, Xiamen, China
FGDM: Reasoning Aware Multi-Agentic Framework for Software Bug Detection using Chain of Thought and Tree of Thought Prompting
Apr 27, 2026Srita Padmanabhuni, Bhargavi Karuturi, Jerusha Karen Indupalli +2Bug Detection Codebases
SRM University, Andhra Pradesh, Amaravati, India · Corresponding Author
Revisable by Design: A Theory of Streaming LLM Agent Execution
Apr 25, 2026Zhiyuan Zhai, Ming Li, Xin WangAgent Loop Rollback
Fudan University · Guangming Lab
Sovereign Agentic Loops: Decoupling AI Reasoning from Execution in Real-World Systems
Apr 24, 2026Jun He, Deying YuAgent Loop Deterministic Replay
VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation
Apr 23, 2026Qijun Han, Haoqin Tu, Zijun Wang +11Graphical User Interface Agents Agent Loop
UC Santa Cruz · CMU · UNC-Chapel Hill +2
A Multi-Agent Approach for Claim Verification from Tabular Data Documents
Apr 19, 2026Rudra Ranajee Saha, Laks V. S. Lakshmanan, Raymond T. NgAgent Loop Multi-Agent Communication
University of British Columbia
Complete Cyclic Subtask Graphs for Tool-Using LLM Agents: Flexibility, Cost, and Bottlenecks in Multi-Agent Workflows
Apr 17, 2026Luay Gharzeddine, Samer SaabMulti-Agent Workflows Agent Loop
1Dept of Computer Science, Lebanese American University. · 2*Dept of Electrical and Computer Engineering, Lebanese American University.
MM-WebAgent: A Hierarchical Multimodal Web Agent for Webpage Generation
Apr 16, 2026Yan Li, Zezi Zeng, Yifan Yang +12Web Agents Web
Shanghai Jiao Tong University · Xi’an Jiaotong University · Microsoft Corporation +1
AgentFoX: LLM Agent-Guided Fusion with eXplainability for AI-Generated Image Detection
Mar 24, 2026Yangxin Yu, Yue Zhou, Bin Li +4Ai-Generated Image Detection Digital Forensics
Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen Key Laboratory of Media Security, and SZU-AFS Joint Innovation Center for AI Technology, Shenzhen University, Shenzhen 518060, China · School of Cyber Science and Technology, Sun Yat-sen University, China · Smart City Research Institute of China Electronics Technology Group Corporation, Shenzhen, China
Replayable Financial Agents: A Determinism-Faithfulness Assurance Harness for Tool-Using LLM Agents
Jan 17, 2026Raffi KhatchadourianReproducibility Agent Loop
IBM Financial Services Market, New York, NY, USA
EndoCogniAgent: Closed-Loop Agentic Reasoning with Self-Consistency Validation for Endoscopic Diagnosis
Aug 10, 2025Yi Tang, Kai-Ni Wang, Liang-Peng Pu +3Colonoscopy Diagnosis
School of Biological Science and Medical Engineering, Southeast University, Nanjing 211189, China · Jiangsu Key Laboratory of Biomaterials and Devices, Southeast University, Nanjing 211189, China · State Key Laboratory of Digital Medical Engineering, Southeast University, Nanjing 211189, China +2
Retriever: Composing the Perception-Reasoning-Action Loop for Long-Horizon Manipulation
Date pendingLinfeng Zhao, Haojie Huang, Jiayuan Mao +3Agent Loop Deterministic Replay
Stanford University · Northeastern University · MIT +1
Hi-FLoop: Hierarchical State-Feedback Loops for Multi-Timescale World Modeling
Date pendingRx Fan, Z HanMicroscopic Traffic Simulations Long-Horizon Trajectories
School of Systems Science, Beijing Normal University

May 14, 2026, cs.AIJ/K move · Enter open · S save

Good to Go: The LOOP Skill Engine That Hits 99% Success and Slashes Token Usage by 99% via One-Shot Recording and Deterministic Replay

Xiaohua Wang, Kai Yu, XuXiao Liang, Liang Wang+1

1Artificial Intelligence Research Center, Bengbu Medical University, Bengbu 233000, China. · 2CHARMMIRAEL Biotech Co., Ltd, Nanjing 210000, China.

Agent Loop Deterministic Replay Skills

Open paper AskPDF arXiv

Deploying AI agents for repetitive periodic tasks exposes a critical tension: Large Language Models (LLMs) offer unmatched flexibility in tool orchestration, yet their inherent stochasticity causes unpredictable failures, and repeated invocations incur prohibitive token costs. We present the LOOP SKILL ENGINE, a system that achieves a combined 99% success rate and 99% token reduction for periodic agent tasks through a one-shot recording, deterministic replay paradigm. On its first run, the agent executes the task with full LLM reasoning while the system transparently intercepts and records the complete tool-call trajectory. A greedy length-descending template extraction algorithm then converts this recording into a parameterized, branch-free Loop Skill -- a deterministic execution plan that captures the task's functional intent while parameterizing time-dependent and result-dependent variables. All subsequent executions bypass the LLM entirely: the engine resolves template variables against real-time values and replays the tool sequence deterministically. We prove two theorems: (1) Replay Determinism -- the step sequence of a validated Loop Skill is invariant across all future executions; (2) Write Safety -- concurrent access to persistent configuration is serialized through reentrant locks and atomic file replacement. Across a benchmark of periodic agent tasks spanning intervals from 5 minutes to 24 hours, the Loop Skill Engine reduces monthly token consumption by 93.3%--99.98% and cuts execution latency by 8.7x while eliminating output non-determinism. A multi-layer degradation strategy guarantees that tasks never stall. We release the engine as part of the buddyMe open-source agent framework.

Momentum

Related topics

Latest papers 83