23 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…
FactorDrive: Adaptive Multi-Step Reasoning Driven by Planning-Critical Factors for End-to-End Autonomous Driving
Guolei Huang, Tengfei She, Yuxuan Lu +3
Vision-language models (VLMs) have advanced scene understanding and enabled explicit reasoning in end-to-end autonomous driving. However, existing methods insufficiently integrate…
Scale Up Strategically: Learning Compositional Generalization via Bias-Aware Evaluation and Data Collection for Robotic Manipulation
Yu Qi, Zhang Ye, Xinyi Xu +6
Compositional generalization is essential for robot to follow diverse instructions. However, pretrained policies are known to take shortcuts, deferring to salient cues rather than…
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…
CollabSim: A CSCW-Grounded Methodology for Investigating Collaborative Competence of LLM Agents through Controlled Multi-Agent Experiments
Jiaju Chen, Bo Sun, Yuxuan Lu +3
Multi-agent systems (MAS) built on large language models have shown growing promise, with their effectiveness resting on agents' ability to coordinate through text-based channels m…