24 citations · 26 across the 20 of their papers we have counts for
12 papers · 1 filter
Bench2Robust: Scenario-Controlled Recovery for Tool-Using Agents
Chaoran Chen, Vy Nguyen, Ziji Zhang +7
Tool-using LLM agents are typically developed and post-trained in controlled environments with reliable tools, but deployment exposes them to tool failures, API and schema drift, a…
Humans' ALMANAC: A Human Collaboration Dataset of Action-Level Mental Model Annotations for Agent Collaboration
Jiaju Chen, Yuxuan Lu, Jiayi Su +10
Recent advances in LLM agents have enabled complex cognitive capabilities, such as multi-step reasoning, planning, and tool use, that increasingly position these agents as human co…
ORCE: Order-Aware Alignment of Verbalized Confidence in Large Language Models
Chen Li, Xiaoling Hu, Songzhu Zheng +2
Large language models (LLMs) often produce answers with high certainty even when they are incorrect, making reliable confidence estimation essential for deployment in real-world sc…
NARRA-Gym for Evaluating Interactive Narrative Agents
Yue Huang, Yuchen Ma, Jiayi Ye +14
Interactive narrative tasks require LLMs to sustain a coherent, evolving story while adapting to a user over multiple turns. However, suitable benchmarks for this setting are limit…
Stayin' Aligned Over Time: Towards Longitudinal Human-LLM Alignment via Contextual Reflection and Privacy-Preserving Behavioral Data
Simret Araya Gebreegziabher, Allison E Sproul, Yinuo Yang +3
Current human-AI alignment and evaluation methods for large language models (LLMs) often rely on preference signals collected immediately after an interaction. This practice implic…
How Coding Agents Fail Their Users: A Large-Scale Analysis of Developer-Agent Misalignment in 20,574 Real-World Sessions
Ningzhi Tang, Chaoran Chen, Gelei Xu +5
AI coding agents increasingly act directly within software environments, yet existing analyses of their failures rely on benchmark trajectories that miss how developers actually ex…
Comparing Human Oversight Strategies for Computer-Use Agents
Chaoran Chen, Zhiping Zhang, Zeya Chen +9
LLM-powered computer-use agents (CUAs) shift users from direct manipulation to supervising an unfolding action sequence, yet existing oversight research mostly evaluates static dec…
Behavioral Canaries: Auditing Private Retrieved Context Usage in RL Fine-Tuning
Chaoran Chen, Dayu Yuan, Peter Kairouz
In agentic workflows, LLMs frequently process retrieved contexts that are legally protected from further training. However, auditors currently lack a reliable way to verify if a pr…
Programming by Chat: A Large-Scale Behavioral Analysis of 11,579 Real-World AI-Assisted IDE Sessions
Ningzhi Tang, Chaoran Chen, Zihan Fang +6
IDE-integrated AI coding assistants, which operate conversationally within developers' working codebases with access to project context and multi-file editing, are rapidly reshapin…
From Human-Human Collaboration to Human-Agent Collaboration: A Vision, Design Philosophy, and an Empirical Framework for Achieving Successful Partnerships Between Humans and LLM Agents
Bingsheng Yao, Chaoran Chen, April Yi Wang +3
The emergence of Large Language Model (LLM) agents enables us to build agent-based intelligent systems that move beyond the role of a "tool" to become genuine collaborators with hu…
PriviSense: A Frida-Based Framework for Multi-Sensor Spoofing on Android
Ibrahim Khalilov, Chaoran Chen, Ziang Xiao +3
Mobile apps increasingly rely on real-time sensor and system data to adapt their behavior to user context. While emulators and instrumented builds offer partial solutions, they oft…
The Behavioral Fabric of LLM-Powered GUI Agents: Human Values and Interaction Outcomes
Simret Araya Gebreegziabher, Yukun Yang, Charles Chiang +7
Large Language Model (LLM)-powered web GUI agents are increasingly automating everyday online tasks. Despite their popularity, little is known about how users' preferences and valu…