2 papers
cs.AI2026
When Terminal-Agent Training Stalls: Demystifying Data Generation and Verification Challenge
Xi Qin, Isabel Kurth, Xin Cui +3
Using a frontier model like Claude Opus as a meta-agent to generate terminal tasks and verifiers for RL training is increasingly common. Yet a runnable Docker image and executable…
cs.AI2025
Smaller Models, Smarter Rewards: A Two-Sided Approach to Process and Outcome Rewards
Jan Niklas Groeneveld, Xi Qin, Alexander Schaefer +1
Generating high-quality code remains a challenge for Large Language Models (LLMs). For the evolution of reasoning models on this task, reward models are a necessary intermediate st…