arXiv cs.MA· Lingxiao Zhou, Di Chen, Jia Li·· 11 小时前AI 评分29
理解混合自动驾驶交通中基于 LLM 的驾驶智能体议价行为
Understanding LLM-Based Bargaining of Driving Agents in Mixed-Autonomy Traffic
AI 导读
一项研究构建框架，刻画并理解混合自动驾驶交通中自动驾驶汽车（AV）与人类驾驶汽车（HV）智能体基于 LLM 的群体级道路空间议价。通过改变交通密度、智能体目标和交通领域知识的受控实验，研究发现不同条件下达成一致的比例存在差异，并提出联合刻画数值出价动作与沟通态度的行为分类法。结果显示，达成一致的试验中建设性互惠更多，破裂试验中冲突升级更频繁，且即使数值出价不变，私下与公开沟通态度也常不同。
正文 · 原文
Abstract:Large Language Models (LLMs) offer a flexible computational approach for modeling social interactions among heterogeneous agents. This paper develops a novel framework towards characterizing and understanding LLM-based population-level bargaining of shared road space between autonomous vehicle (AV) and human-driven vehicle (HV) agents in mixed-autonomy traffic. Through controlled experiments varying traffic density, agent objectives, and traffic-domain knowledge, we first characterize bargaining outcomes and observe heterogeneous agreement rates across different experimental conditions. To understand how the bargaining process shapes the outcomes, we introduce a behavioral taxonomy that jointly characterizes numerical bidding actions and communicative attitudes. We examine two complementary aspects of social interaction: inter-agent bargaining dynamics and private-to-public behavioral transformation. Results reveal distinct interaction patterns associated with agreement and breakdown, including greater constructive reciprocity in agreement trials and more frequent conflict escalation in breakdown trials. Furthermore, private and public communicative attitudes often differ even when numerical bids remain unchanged. These findings illustrate how LLM-based bargaining simulations can support a structured analysis of social interaction behaviors in mixed-autonomy traffic.
| Subjects: | Physics and Society (physics.soc-ph); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2610.41239 [physics.soc-ph] |
| (or arXiv:2610.41239v1 [physics.soc-ph] for this version) | |
| https://doi.org/10.48550/arXiv.2610.41239 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jia Li [view email]
[v1]
Fri, 30 Oct 2026 04:30:08 UTC (1,356 KB)
来源：arXiv cs.MA · arxiv.org