1 citations · 2 across the 11 of their papers we have counts for
6 papers · 1 filter
Instructions Are Evidence, Not Objectives: Measuring Outcome Alignment of Agents
Kaiming Liu, Yuxuan Liu, Jinrui Ju +4
Large language model agents can follow complex human instructions to solve real-world tasks. In practice, however, initial instructions are often incomplete. In our analysis of 100…
Benchmarking General Mobile Assistants in Challenging Real-World Scenarios
Yiqi Zhu, Feiyu Gao, Jiaxing Fan +7
Graphical user interfaces have emerged as an important environment for evaluating autonomous AI agents on multimodal interactive tasks. Existing benchmarks such as AndroidWorld and…
Illusion of Alignment: Detecting Hidden Disagreement in Collaborative Dialogue
Kaiming Liu, Fuwen Luo, Ziyue Wang +6
Collaborative dialogue can end with apparent agreement while participants still differ on goals, assumptions, or execution plans, creating an \textbf{illusion of alignment (IoA)}.…
Agent-Environment Alignment via Automated Interface Generation
Kaiming Liu, Xuanyu Lei, Ziyue Wang +2
Large language model (LLM) agents have shown impressive reasoning capabilities in interactive decision-making tasks. These agents interact with environment through intermediate int…
ReAct Meets ActRe: When Language Agents Enjoy Training Data Autonomy
Zonghan Yang, Peng Li, Ming Yan +3
Language agents have demonstrated autonomous decision-making abilities by reasoning with foundation models. Recently, efforts have been made to train language agents for performanc…
Budget-Constrained Tool Learning with Planning
Yuanhang Zheng, Peng Li, Ming Yan +3
Despite intensive efforts devoted to tool learning, the problem of budget-constrained tool learning, which focuses on resolving user queries within a specific budget constraint, ha…