7 papers
KNOWPLAN: Knowledge-Driven AI Agents for Smart Degree Pathway Planning
Shuheng Cao, Weijia Zhang, Jiaqi Wu +4
Planning a degree from official university sources requires solving two problems in order. The institution's curriculum must first be reconstructed from catalogs, departmental page…
CUADebug: Diagnosing and Repairing Computer-Use Agent Failures
Weijia Zhang, Kunlun Zhu, Zeyi Liu +8
Computer-use agents (CUAs) operate real desktop and web interfaces through screenshots, mouse and keyboard actions, and stateful UI feedback, yet their failures remain difficult to…
AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents
Kunlun Zhu, Xuyan Ye, Zhiguang Han +9
LLM agent failures are difficult to debug because the step where an error surfaces is often not the one that caused it. Existing observability tools replay execution traces but pro…
VSPO: Vector-Steered Policy Optimization for Behavioral Control
Xuechen Zhang, Zijian Huang, Kai Yang +3
Modern language models often need to optimize a primary accuracy objective while also accommodating secondary behavioral preferences, such as verbosity, agreeableness, or the level…
Justified or Just Convincing? Error Verifiability as a Dimension of LLM Quality
Xiaoyuan Zhu, Kimberly Le Truong, Riccardo Fogliato +8
As LLMs are deployed in high-stakes settings, users must judge the correctness of individual responses, often relying on model-generated justifications such as reasoning chains or…
SeeingEye: Agentic Information Flow Unlocks Multimodal Reasoning In Text-only LLMs
Weijia Zhang, Zijia Liu, Haoru Li +2
Recent advances in text-only large language models (LLMs), such as DeepSeek-R1, demonstrate remarkable reasoning ability. However, these models remain fragile or entirely incapable…