2 papers
cs.LG2026
A Bird's-Eye View of Iterative Reward Design
Logan Mondal Bhamidipaty, Lauren Robson, Linda Petrini +2
Designing effective reward functions in RL typically requires substantial expertise and trial and error. Recent work automates this process with LLM-based systems that generate and…
cs.AI2025
CTRL-ALT-DECEIT: Sabotage Evaluations for Automated AI R&D
Francis Rhys Ward, Teun van der Weij, Hanna Gábor +6
AI systems are increasingly able to autonomously conduct realistic software engineering tasks, and may soon be deployed to automate machine learning (ML) R&D itself. Frontier AI sy…