Poster · Sydney
MURPHY: Feedback-Aware GRPO with Retrospective Credit Assignment for Multi-Turn Code Generation
- When
- Wed 9 Dec 2026, 10:00–13:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 3
- Authors
- Chanakya Ekbote, Vijay Lingam, Sujay Sanghavi, Luke Huan, Behrooz O Tehrani, Anoop Deoras, Stefano Soatto
- Organisations
- Massachusetts Institute of Technology, Amazon, University of Texas at Austin, University of California, Los Angeles
- QRS classification
- Reinforcement learning