[论文解读] From Control to Foresight: Simulation as a New Paradigm for Human-Agent Collaboration

Gaole He, B. Lim|arXiv (Cornell University)|Mar 12, 2026

Human-Automation Interaction and Safety被引用 0

一句话总结

这篇论文主张在循环仿真中提供可预见的未来轨迹，以在人机大模型（LLM）代理协作中将干预从被动探索转变为主动探索.

ABSTRACT

Large Language Models (LLMs) are increasingly used to power autonomous agents for complex, multi-step tasks. However, human-agent interaction remains pointwise and reactive: users approve or correct individual actions to mitigate immediate risks, without visibility into subsequent consequences. This forces users to mentally simulate long-term effects, a cognitively demanding and often inaccurate process. Users have control over individual steps but lack the foresight to make informed decisions. We argue that effective collaboration requires foresight, not just control. We propose simulation-in-the-loop, an interaction paradigm that enables users and agents to explore simulated future trajectories before committing to decisions. Simulation transforms intervention from reactive guesswork into informed exploration, while helping users discover latent constraints and preferences along the way. This perspective paper characterizes the limitations of current paradigms, introduces a conceptual framework for simulation-based collaboration, and illustrates its potential through concrete human-agent collaboration scenarios.

研究动机与目标

• 识别当前点对点人机交互范式的局限性。
• 定义基于仿真的协作概念框架与设计空间。
• 演示仿真未来如何在多步任务中支持前瞻性思考，而不仅仅是计划。
• 强调实现巧合性与潜在约束发现的实际影响与权衡。

提出的方法

• 定义四个核心概念：agentic 工作流、行动空间、仿真、以及仿真影响。
• 描述仿真如何将内部未来探索外化以帮助认知整理。
• 提供一个带有多条未来路径和注释结果的城市多点出行场景示例。
• 勾勒一个设计空间，包含前瞻深度、探索广度与粒度等考虑。

Figure 1. Comparison of interaction paradigms at a decision point.

实验结果

研究问题

• RQ1 当前点对点交互范式如何限制长时间任务中的人机协作？
• RQ2 基于仿真的交互设计空间是什么，权衡如何影响推理与信任？
• RQ3 在循环仿真中是否能够实现主动的人机探索以及对潜在约束和需求的发现？

主要发现

• 循环仿真将干预从被动猜测转变为主动探索。
• 用户可以比较多条带注释结果的仿真未来，以在时间成本、延迟风险等权衡上做出知情选择。
• 仿真揭示传统范式下会错失的潜在约束与巧合性选项。
• 设计选择（前瞻深度、广度和粒度）对用户认知、信任和认知负荷有关键影响。