From the 1 of 53 linked papers with an AI index.
53 papers
Retry, Switch, or Abstain? Learning Strategy-Aware Tool-Use Policies via Controlled Error Injection
Chaoran Chen, Vy Nguyen, Ziji Zhang +7
Tool-using LLM agents are commonly trained and evaluated in environments where tool calls succeed reliably, yet deployed tools can fail transiently, persistently, or silently. Robu…
PADFormer: Pose-agnostic Anomaly Detection from Sparse View Images
Ruiqi Wang, Yiming Qian, Fenggen Yu +4
Pose-agnostic Anomaly Detection (PAD) remains challenging as anomalies can appear under arbitrary viewpoints, requiring methods to handle significant pose variations. Existing appr…
Seeing Through the Forecast Clutter: Communicating Climate Forecast Distributions with Weighted Multiple Forecast Visualizations
Ruishi Zou, Siyi Wu, Racquel Fygenson +3
Forecasts often diverge because different models make varying assumptions to account for underlying uncertainty. Readers who consume forecasts may wish to survey the shape and spre…
Toward Metaphor-Fluid Conversation Design for Voice User Interfaces
Smit Desai, Jessie Chin, Dakuo Wang +2
The paper proposes Metaphor-Fluid Design, a method that dynamically changes metaphorical representations in voice user interfaces to match different conversational contexts, and sh…
SpanUQ: Span-Level Uncertainty Quantification for Large Language Model Generation
Yimeng Zhang, Yingying Zhuang, Ziyi Wang +12
Uncertainty estimation is essential not only for the trustworthy deployment of large language models (LLMs) but also as a foundation for self-refinement in LLM generation. However,…
SENTINEL: Failure-Driven Reinforcement Learning for Training Tool-Using Language Model Agents
Ziyi Wang, Yuxuan Lu, Yimeng Zhang +8
Language model agents are increasingly effective in solving realistic tasks through multi-turn tool use. However, training reliable tool-using agents remains challenging in practic…