collaborators

23 papers

cs.AI2026

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…

cs.RO2026

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…

cs.RO2026

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…

cs.CL2026

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,…

cs.CL2026

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…

cs.CL2026

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…