2 papers
cs.AI2026
When Does Exercise-Specific Joint Selection Help? An Audit of Evaluation and Control Design
Haotian Chen, Jingkun Yu, Yuning Zhang +1
Exercise-specific joint selection can improve skeleton-based correctness classification, but what does that gain establish? We audit 1,057 repetitions from ten REHAB24-6 subjects,…
cs.AI2026
Auditing Action Settlement in LLM Agent Environments: Order, Progress, and Replay
Haotian Chen, Bowen Ye, Yuning Zhang +1
Concurrent actions in large language model (LLM) agent environments require arbitration even when each proposal is individually valid. We implement a typed snapshot-settlement cont…