6 papers
Skill Use or Skill Theater? Evaluating the Reasoning Backroom in Skill-Augmented Language Agents
Jinwei Hu, Yi Qi, Xinmiao Huang +3
Reusable skills are becoming a standard interface for extending language agents with task procedures. Yet evaluators usually infer skill use from visible reasoning or the agent's o…
Responsible Agentic AI Requires Explicit Provenance
Jinwei Hu, Xinmiao Huang, Qisong He +3
Agentic AI is rapidly proliferating across diverse real-world domains such as software engineering, yet public trust has not kept pace. The central reason is that responsibility, d…
Safety-Constrained Reinforcement Learning with Post-Training Reachability Verification for Robot Navigation
Qisong He, Xinmiao Huang, Jinwei Hu +4
Safe navigation for mobile robots demands policies that remain reliable under the high-consequence perception uncertainty of cluttered environments. Yet most existing safe reinforc…
PrefixGuard: From LLM-Agent Traces to Online Failure-Warning Monitors
Xinmiao Huang, Jinwei Hu, Rajarshi Roy +3
Large language model (LLM) agents now execute long, tool-using tasks where final outcome checks can arrive too late for intervention. Online warning requires lightweight prefix mon…
Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage
Jinwei Hu, Xinmiao Huang, Youcheng Sun +2
As large language models (LLMs) transition to autonomous agents synthesizing real-time information, their reasoning capabilities introduce an unexpected attack surface. This paper…
Spatial-DISE: A Unified Benchmark for Evaluating Spatial Reasoning in Vision-Language Models
Xinmiao Huang, Qisong He, Zhenglin Huang +5
Spatial reasoning ability is crucial for Vision Language Models (VLMs) to support real-world applications in diverse domains including robotics, augmented reality, and autonomous n…