Baroian, A., & Berger, R. (2026). Prompt replay: Speeding up grpo with on-policy reuse of high-signal prompts.
Chicago Style (17th ed.) CitationBaroian, Andrei, and Rutger Berger. Prompt Replay: Speeding Up Grpo with On-policy Reuse of High-signal Prompts. 2026.
MLA (9th ed.) CitationBaroian, Andrei, and Rutger Berger. Prompt Replay: Speeding Up Grpo with On-policy Reuse of High-signal Prompts. 2026.
Warning: These citations may not always be 100% accurate.