14 papers
Naive Visual Memory is Not Enough: A Failure-Mode Study of GUI Agents
Seoyoung Choi, Minseok Ko, Hyunseok Lee +4
Graphical User Interface (GUI) agents are increasingly used to automate complex computer tasks across applications, websites, and operating systems. To improve their reliability, r…
IdleSpec: Exploiting Idle Time via Speculative Planning for LLM Agents
Daewon Choi, Kyunghyun Park, Woomin Song +4
Large language model (LLM)-based agents solve complex tasks by leveraging multi-step reasoning with iterative tool calls and environment interactions, which incur idle time while w…
ExComm: Exploration-Stage Communication for Error-Resilient Agentic Test-Time Scaling
Woomin Song, Beomjun Kim, Daewon Choi +4
A common failure mode in long-horizon agentic test-time scaling is error propagation, where factual errors or invalid deductions introduced at intermediate steps persist in the age…
Accelerated Test-Time Scaling with Model-Free Speculative Sampling
Woomin Song, Saket Dingliwal, Sai Muralidhar Jayanthi +4
Language models have demonstrated remarkable capabilities in reasoning tasks through test-time scaling techniques like best-of-N sampling and tree search. However, these approaches…
RedacBench: Can AI Erase Your Secrets?
Hyunjun Jeon, Kyuyoung Kim, Jinwoo Shin
Modern language models can readily extract sensitive information from unstructured text, making redaction -- the selective removal of such information -- critical for data security…
DS-STAR: Data Science Agent for Solving Diverse Tasks across Heterogeneous Formats and Open-Ended Queries
Jaehyun Nam, Jinsung Yoon, Jiefeng Chen +3
While large language models (LLMs) have shown promise in automating data science, existing agents often struggle with the complexity of real-world workflows that require exploring…