9 papers
Alignment Is Local: A Paired Diagnostic for GUI Agents under User-Side Persuasion
Haoxin An, Yunpeng Song, Zihao Bai +6
Trustworthy deployment of GUI agents in ubiquitous computing settings requires alignment that survives dynamic interaction and precise threat conditions, not just single-turn refus…
Social Networks of LLM Agents
Kaixuan Liu, Guojun Xiong, Weinan Zhang +1
Large language model (LLM) agents are increasingly deployed in interacting populations, raising the question of what such populations come to believe collectively. Whether a popula…
Autoregressive Diffusion World Models for Off-Policy Evaluation of LLM Agents
Kaixuan Liu, Guojun Xiong, Weinan Zhang +1
Evaluating large language model (LLM) agents in multi-turn interactive environments is expensive and risky, as it requires online environment interaction. We propose ADWM (Autoregr…
Health Facility Location in Ethiopia: Leveraging LLMs to Integrate Expert Knowledge into Algorithmic Planning
Yohai Trabelsi, Guojun Xiong, Fentabil Getnet +2
Ethiopia's Ministry of Health is upgrading health posts to improve access to essential services, particularly in rural areas. Limited resources, however, require careful prioritiza…
Composite Flow Matching for Reinforcement Learning with Shifted-Dynamics Data
Lingkai Kong, Haichuan Wang, Tonghan Wang +2
Incorporating pre-collected offline data can substantially improve the sample efficiency of reinforcement learning (RL), but its benefits can break down when the transition dynamic…
VORTEX: Aligning Task Utility and Human Preferences through LLM-Guided Reward Shaping
Guojun Xiong, Milind Tambe
In social impact optimization, AI decision systems often rely on solvers that optimize well-calibrated mathematical objectives. However, these solvers cannot directly accommodate e…