AgentGit: A Version Control Framework for Reliable and Scalable LLM-Powered Multi-Agent Systems
With the rapid progress of large language models (LLMs), LLM-powered multi-agent systems (MAS) are drawing increasing interest across academia and industry. However, many current MAS frameworks struggle with reliability and scalability, especially on complex tasks. We present AgentGit, a framework that brings Git-like rollback and branching to MAS workflows. Built as an infrastructure layer on top of LangGraph, AgentGit supports state commit, revert, and branching, allowing agents to traverse, compare, and explore multiple trajectories efficiently. To evaluate AgentGit, we designed an experiment that optimizes target agents by selecting better prompts. We ran a multi-step A/B test against three baselines -- LangGraph, AutoGen, and Agno -- on a real-world task: retrieving and analyzing paper abstracts. Results show that AgentGit significantly reduces redundant computation, lowers runtime and token usage, and supports parallel exploration across multiple branches, enhancing both reliability and scalability in MAS development. This work offers a practical path to more robust MAS design and enables error recovery, safe exploration, iterative debugging, and A/B testing in collaborative AI systems.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Provable Speech Attributes Conversion via Latent Independence
While signal conversion and disentangled representation learning have shown promise for manipulating data attributes across domains such as audio, image, and multimodal generation, existing approaches, especially for spe…
Representation Learningmultimodal generationstable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation
World models are central to building agents that can reason, plan, and generalize beyond their training data. However, research on world models is currently fragmented, with disparate codebases, data pipelines, and evalu…
Dynamics Distillation for Efficient and Transferable Control Learning
Robust control policy learning for autonomous driving requires training environments to be both physically realistic and computationally scalable, properties that existing simulators provide only in isolation. We introdu…
Reinforcement LearningAutonomous DrivingDistributed-MPC with Data-Driven Estimation of Bus Admittance Matrix in Voltage Control
This article presents a distributed model-predictive control (MPC) design for real-time voltage control in power systems, including an online method to estimate the bus admittance matrix $\mathbf{Y}$ to let it be time-va…
Anomaly DetectionDistributed OptimizationModel Predictive ControlA Stable Combinatorial Particle Swarm Optimization for Scalable Feature Selection in Gene Expression Data
Evolutionary computation (EC) algorithms, such as discrete and multi-objective versions of particle swarm optimization (PSO), have been applied to solve the Feature selection (FS) problem, tackling the combinatorial expl…
DiagnosticDiversityfeature selectionGeneral Classification