An important emerging application of coding agents is agent harness optimization: the iterative improvement of a target agent by editing and evaluating its code. Despite its relevance, the community lacks a systematic understanding of coding agent performance on this task. Harness optimization differs from conventional software engineering: agent harnesses interleave deterministic code with stochastic LLM completions, requiring structured capture of both intermediate execution traces and downstream outcomes. To address these challenges, we introduce (1) VeRO (Versioning, Rewards, and Observations), an outer harness that provides versioned snapshots, budget-controlled evaluation, and structured execution traces of target harnesses, and (2) VeRO-Bench, a benchmark suite of target agents and tasks with reference evaluation procedures. Using VeRO, we conduct an empirical study comparing optimizers across tasks and analyzing which modifications reliably improve target agent harnesses. We release VeRO to support research on agent optimization as a core capability for coding agents. Code is available at https://github.com/scaleapi/vero.
HarnessForge: Joint Harness and Policy Evolution for Adaptive Agent Systems
Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing, School of Artificial Intelligence, Beihang University（北京未来区块链与隐私计算先进创新中心，人工智能学院，北京航空航天大学）；Tsinghua University（清华大学）
Vero: Can AI Agents Build Formally Verified Software Repositories?
University of Chicago（芝加哥大学）；California Institute of Technology（加州理工学院）；Stanford University（斯坦福大学）；UC Berkeley（加州大学伯克利分校）；Amazon Web Services（亚马逊云计算服务）；Apodex
VideoHarness-SRSI: Structured Recursive Self-Improvement for Video Understanding Harness
University of California, Davis（加州大学戴维斯分校）；Meta MRS Research（Meta MRS 研究）；Duke University（杜克大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Cornell University（康奈尔大学）；Purdue University（普渡大学）
Grow the Harness, Not the Context: From Strategy-Free Scaffolds to Reusable Specialist Agents
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；University of Chinese Academy of Sciences（中国科学院大学）；Shenzhen University of Advanced Technology（深圳理工大学）；University of Macau（澳门大学）
MetaCaster: Meta-Harness-Optimized Agent for End-to-End Few-Shot Learning of Lightweight Time Series Forecasters
University of Houston（休斯顿大学）；NEC Labs（NEC实验室）；University of Waterloo（滑铁卢大学）；University of Connecticut（康涅狄格大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Singapore Management University（新加坡管理大学）
AI-based Framework for Robust Model-Based Connector Mating in Robotic Wire Harness Installation
IAS Lab, Computer Science Department, TU Darmstadt（德累斯顿技术大学计算机科学系IAS实验室）；AICOR Institute for Artificial Intelligence, University of Bremen（不莱梅大学人工智能研究所）；Institute for Material Handling and Logistics (IFL), Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院物流与物料搬运研究所）；ArtiMinds Robotics（ArtiMinds机器人技术公司）
提出融合力控制、多模态 transformer 与自动数据优化的 AI 框架，实现机器人线束连接器插接，并在中控台任务中显著提升速度与鲁棒性。
GUI-HARVEST: Self-Improving GUI Agents through Evidence-Driven Harness Evolution
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Tianjin University（天津大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；East China Normal University（华东师范大学）；Shenzhen Research Institute of Big Data（深圳市大数据研究院）
AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design
Meituan（美团）；MBZUAI（Mohamed bin Zayed University of Artificial Intelligence）；Huazhong University of Science and Technology（华中科技大学）；Peking University（北京大学）；Tsinghua University（清华大学）；The Chinese University of Hong Kong（香港中文大学）；Shanghai Jiao Tong University（上海交通大学）
