9 papers
Safety, or Just Capability? A Validity Audit of Agent-Safety Benchmarks
Youting Wang, Xiao Han, Dingyan Shang +2
Agent-safety benchmarks measure different behaviors, and their scores get quoted interchangeably as an agent's safety. We treat four of them (R-Judge, InjecAgent, AgentHarm, AgentD…
Context-Masked Truncated Reasoning Audits for Answer-Key Dependence in LLM Tutors
Bonan Shen, Dingyan Shang, Youting Wang +2
Large language model (LLM) tutors may have access to teacher notes, answer keys, rubrics, or retrieved solutions while producing student-facing explanations. We study whether trunc…
EvoRubric: Self-Evolving Rubric-Driven RL for Open-Ended Generation
Xin Guan, Xiaomeng Hu, Shen Huang +6
Reinforcement Learning (RL) has significantly advanced Large Language Models (LLMs) in verifiable domains, but aligning models for open-ended generation remains profoundly challeng…
When LLM Reward Design Fails: Diagnostic-Driven Refinement for Sparse Structured RL
Youting Wang, Yuan Tang, Bowen Liu +2
For sparse, structured reinforcement-learning tasks with semantic reward-function interfaces, LLM-generated reward shaping is better framed as debugging than one-shot generation. W…
CP-Agent: A Calibrated Risk-Controlled Agent for Feedback-Driven Competitive Programming
Peisong Wang, Bowen Liu, Zehua Li +4
Large language models still struggle with contest-level programming, while many agentic remedies rely on massive inference-time sampling or expensive multi-stage post-training. We…
CollabSkill: Evaluating Human-Agent Collaboration On Real-World Tasks
Yijia Shao, Zora Zhiruo Wang, Neel Ahuja +3
AI agents are reshaping the workspace, leading to drastic change of how humans work. Despite the considerable potential of human-agent collaboration both in preserving human agency…