Jae C. Oh
YOU?
Author Swipe
View article: LLM Agents for Bargaining with Utility-based Feedback
LLM Agents for Bargaining with Utility-based Feedback Open
Bargaining, a critical aspect of real-world interactions, presents challenges for large language models (LLMs) due to limitations in strategic depth and adaptation to complex human factors. Existing benchmarks often fail to capture this re…
View article: Social Network Based Reputation Computation and Document Classification
Social Network Based Reputation Computation and Document Classification Open
We develop two social network based algorithms that automatically com- pute author reputation from a collection of textual documents. We first extract keyword reference behaviors of the authors to construct a social network, which represen…
View article: Multi-target Extension for Beacon Foraging Methods
Multi-target Extension for Beacon Foraging Methods Open
Robotic foraging is a complex problem that encompasses both the problem of exploring an area and retrieval of targets. To solve this, biologically inspired algorithms have been proposed that handle the scenario when only one target exists,…
View article: Multi-Agent Sensor Data Collection with Attrition Risk
Multi-Agent Sensor Data Collection with Attrition Risk Open
We introduce a multi-agent route planning problem for col-lecting sensor data in hostile or dangerous environmentswhen communication is unavailable. Solutions must considerthe risk of losing robots as they travel through the environ-ment, …
View article: A Graph-based Bandit Algorithm for Maximum User Coverage in Online Recommendation Systems
A Graph-based Bandit Algorithm for Maximum User Coverage in Online Recommendation Systems Open
We study a type of recommendation systems problem, in which the system must be able to cover as many users’ tastes as possible while users’ tastes change over time. This problem can be viewed as a variation of the maximum coverage problem,…