[Paper Review] From Human Negotiation to Agent Negotiation: Personal Mobility Agents in Automated Traffic

Pascal Jansen|arXiv (Cornell University)|Mar 1, 2026

Human-Automation Interaction and Safety0 citations

TL;DR

The paper proposes personal mobility agents that act as proxies for users in automated traffic, handling real-time negotiations on their behalf and shifting interaction from moment-by-moment control to high-level delegation and policy oversight.

ABSTRACT

Conflicts between user preferences and automated system behavior already shape the experience of automated mobility. For example, a passenger may prefer assertive driving, yet the vehicle slows down early to follow a conservative policy or yield to other actors. Similar conflicts arise at merges, crossings, or right-of-way situations, where users must accept opaque decisions or attempt to negotiate through interfaces not designed for continuous, multi-actor relationships. This position paper argues that such approaches do not scale as mobility becomes more heterogeneous and automated. Instead, it proposes personal mobility agents that act as proxies for users, encode preferences such as comfort and safety margins, and negotiate traffic behavior with other agents under shared safety rules. The central idea is a shift from moment-to-moment user negotiation interfaces to delegation and oversight interfaces, in which proxy agents manage real-time conflicts while users can shape high-level policies and preferences.

Motivation & Objective

• Motivate scalable interaction in heterogeneous automated traffic where direct user negotiation becomes impractical.
• Introduce personal mobility agents that encode user preferences and delegation policies.
• Outline a proxy-based negotiation model that operates under shared safety rules.
• Discuss design tensions, safety, transparency, and accountability in proxy-mediated interactions.

Proposed method

• Describe technological foundations for personal mobility agents including learning user preferences and agentic AI capabilities.
• Define core functional components: preference modeling, traffic negotiation, and interface management.
• Outline the agent lifecycle: setup, online adaptation, and long-term policy updates.
• Identify design tensions: preference alignment under safety constraints, manipulation risk, mixed-traffic scaling, and transparency.

Experimental results

Research questions

• RQ1 What design considerations and mechanisms are needed to realize proxy-based negotiations in automated traffic?
• RQ2 How should personal mobility agents model user preferences and delegation policies while respecting safety and legal constraints?
• RQ3 How can agent–agent and agent–human interactions be designed to remain understandable, trustworthy, and accountable?
• RQ4 What are the challenges of scaling proxy negotiation in mixed traffic and attributing responsibility for outcomes?
• RQ5 How should delegation and transparency be balanced to maintain user agency and acceptance?

Key findings

• Proxy-based negotiation could reduce cognitive load and potentially improve acceptance of automated mobility by handling interactions autonomously.
• There are significant design tensions around aligning preferences with safety/legal constraints, maintaining user agency, and ensuring transparency and accountability.
• Persistent proxies raise governance challenges such as potential manipulation, delegation reliability, and attribution of responsibility in multi-agent negotiations.
• In mixed-traffic environments, proxies must degrade gracefully to behavior-based inferences when other actors lack agents.
• Transparency strategies (minimal disclosure vs. reflective transparency) impact user trust, understanding, and long-term calibration of trust.