Agents in the Wild: Where Research Meets Deployment

Grace Hui Yang ,

Pranav N. Venkit ,

Hooman Sedghamiz ,

Enrico Santus ,

Victor Dibia ,

Ioana Baldini

LLM Other LLM Agent Agent Planning Multi-agent Collaboration Agent Eval Benchmarks Autonomous Workflows AI Safety / AI Ethics AVAR

以大语言模型（LLM）为基础的智能体系统——即具备推理、规划、执行能力，并能与工具及其他智能体协同工作的架构——正迅速从学术研究原型迈向软件工程、科学发现、金融等领域的规模化实际部署。尽管学界此前的研究重点集中于基准测试与算法创新，但实际部署却带来了关于系统鲁棒性、安全性与可靠性的全新挑战。本教程汇聚研究人员与一线实践者，共同探讨推理与规划、多智能体协同以及评估方法等方面的最新进展，并着重剖析源于真实部署经验所暴露的关键开放性问题。通过药物研发与金融系统两大应用案例研究，我们归纳出支撑智能体系统成功落地的通用设计范式，并针对典型失效模式（如验证流程缺失、缺乏降级机制、缺少人工监督环节等），提出切实可行的应对策略，包括构建分层验证流水线、设计自动降级与人工接管机制，以及引入“人在回路”（human-in-the-loop）的监督框架。参会者将全面把握该领域的发展现状与核心挑战，同时获得可直接复用的具体设计范式、评估检查清单及跨行业安全可靠部署的标准化模板。

Agentic systems large language model (LLM) based architectures capable of reasoning, planning, acting, and coordinating with tools and other agents are rapidly transitioning from research prototypes to production scale deployments across domains such as software engineering, scientific discovery, and finance. While academic work has emphasized benchmarks and algorithmic innovation, deployment raises new challenges around robustness, safety, and reliability. This tutorial brings together researchers and practitioners to explore advances in reasoning and planning, multi agent coordination, and evaluation, highlighting open challenges arising from deployment experience. Through applied case studies in pharmaceutical discovery and financial systems, we analyze common design patterns that make agentic systems successful, and discuss practical mitigation strategies for failure modes, such as verification pipelines, fallback mechanisms, and human in the loop supervision. Attendees will gain a comprehensive view of the field along with concrete design patterns, evaluation checklists, and templates for safe and reliable deployment across industries.

许愿