arxiv:2504.08942
Alejandra Zambrano
alzambranolu
AI & ML interests
NLP
Recent Activity
new activity
15 days ago
McGill-NLP/safearena:Relax evaluation for tasks involving new code files
new activity
15 days ago
McGill-NLP/safearena:fix-eval
authored
a paper
23 days ago
AgentRewardBench: Evaluating Automatic Evaluations of Web Agent
Trajectories
Organizations
None yet