Code as Agent Harness
Xuying Ning,Katherine Tieu,Dongqi Fu,Tianxin Wei,Zihao Li,Yuanchen Bei,Jiaru Zou,Mengting Ai,Zhining Liu,Ting-Wei Li,Lingjie Chen,Yanjun Zhao,Ke Yang,Bingxuan Li,Cheng Qian,Gaotang Li,Xiao Lin,Zhichen Zeng,Ruizhong Qiu,Sirui Chen,Yifan Sun,Xiyuan Yang,Ruida Wang,Rui Pan

TL;DR
This paper introduces the concept of code as an agent harness, framing code as the core infrastructure for agent reasoning, action, and coordination across various applications and system scales.
Contribution
It provides a unified framework and survey of methods, mechanisms, and applications for using code as the foundational harness in agent systems.
Findings
Organized the survey around three layers: interface, mechanisms, and multi-agent scaling.
Summarized methods and applications across diverse domains like automation, scientific discovery, and enterprise workflows.
Outlined open challenges including verification, safety, and multimodal extension.
Abstract
Recent large language models (LLMs) have demonstrated strong capabilities in understanding and generating code, from competitive programming to repository-level software engineering. In emerging agentic systems, code is no longer only a target output. It increasingly serves as an operational substrate for agent reasoning, acting, environment modeling, and execution-based verification. We frame this shift through the lens of agent harnesses and introduce code as agent harness: a unified view that centers code as the basis for agent infrastructure. To systematically study this perspective, we organize the survey around three connected layers. First, we study the harness interface, where code connects agents to reasoning, action, and environment modeling. Second, we examine harness mechanisms: planning, memory, and tool use for long-horizon execution, together with feedback-driven control…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
