Terminal Agents: A Survey of AI Agents in Command-Line Environments

2026-08-20

AI Summary

本文通过七个维度的终端能力概要，系统地研究了命令行环境中AI代理的行为，探讨了模型、接口等因素对行为的影响，并提出了统一的研究框架。

Abstract

Large language model agents increasingly act through terminals, yet existing surveys disperse terminal-mediated behavior across software engineering, tool use, and computer-use research. We regard terminal agents as systems whose dominant progress-bearing action--observation loop is mediated by terminal command execution, textual feedback, and stateful environment interaction. Using terminal-mediated execution as an organizing lens, this survey establishes workload-level boundaries and connects system architecture, competence acquisition, and evaluation through a seven-dimensional terminal competence profile. Our synthesis shows that realized behavior is jointly shaped by the model, interface, harness, runtime, and environment. Executable trajectories ground learning in action consequences, verification, and recovery, whereas prevailing evaluations emphasize final outcomes and expose process quality, recovery, and governance unevenly. Bounded fixed-condition diagnostics illustrate two implications: benchmark families expose different process signals, and matched system comparisons reveal benchmark-dependent performance and limits of component attribution. These findings motivate explicit reporting of system and runtime conditions, supported by replayable traces and process-level evidence. The framework provides a unified basis for studying terminal-mediated agency across software engineering and emerging application domains.

Problem

• terminal agents
• command-line environments
• large language models
• terminal-mediated behavior
• system architecture

Innovation

• terminal-mediated execution
• seven-dimensional terminal competence profile
• executable trajectories
• process-level evidence
• replayable traces