Announcement_8
Two papers got accepted to ICML 2026: CORRECT: COndensed eRror RECognition via knowledge Transfer in multi-agent systems and XRPO: Pushing the limits of GRPO with Targeted Exploration and Exploitation
Two papers got accepted to ICML 2026: CORRECT: COndensed eRror RECognition via knowledge Transfer in multi-agent systems and XRPO: Pushing the limits of GRPO with Targeted Exploration and Exploitation