511 citations · 3.5k across the 98 of their papers we have counts for
100 papers
Shared and structured inputs undermine collective random choice by reasoning AI agents
Takahiro Ezaki, Naoto Imura, Katsuhiro Nishinari
Random selection is widely used in resource allocation and auditing, making reliable implementation essential for AI-agent systems. Behavioural tests across six reasoning models un…
Warned alike, AI agents avoid the less-crowded road while people take it
Takahiro Ezaki, Naoto Imura, Katsuhiro Nishinari
AI agents built on a few shared models increasingly act for many people. A shared forecast about others can align their choices and change how scarce capacity is allocated. We test…
ETA Coordination at UAM Corridor Merging Points Using Worst-Case and Stochastic Trajectory Bounds
Sasinee Pruekprasert, Shinji Nakadai, Katsuhiro Nishinari
We study an Estimated Time of Arrival (ETA)-based traffic-coordination framework for Urban Air Mobility corridors with merging at constrained waypoints (CWPs), where approved ETAs…
How a shared state is described determines whether AI agents synchronize
Takahiro Ezaki, Naoto Imura, Katsuhiro Nishinari
Language-model agents increasingly act in populations, where the outcome that matters is collective: whether they align, split or fail to coordinate. Each acts not on the world but…
From Visual to Digital: Coordination Scheduling and Its Effect on Safety and Efficiency in UAM Corridors
Akihiro Fujita, Sasinee Pruekprasert, Katsuhiro Nishinari +1
This paper explores scalable coordination strategies for urban air mobility (UAM) corridors by comparing two representative approaches. The first, inspired by visual flight rules (…
Safety-Assured Arrival Scheduling in Sequential UAM Corridor Sections under Speed and Separation Constraints
Sasinee Pruekprasert, Shinji Nakadai, Katsuhiro Nishinari
This paper presents a safety-assured arrival-scheduling framework for Urban Air Mobility (UAM) corridor operations. We propose an analytical method to compute a sufficient ETA gap…