Poster · Atlanta
Multi-Turn RL Makes Small Language Model Competitive for Optimization Modeling
- When
- Wed 9 Dec 2026, 16:30–19:30 EST
- Where
- Hall C1, Georgia World Congress Center
- Session
- Atlanta Poster Session 2
- Authors
- Xinzhi Zhang, Zeyi Chen, Humishka Zope, Hugo Barbalho, Konstantina Mellou, Marco Molinaro, Janardhan Kulkarni, Ishai Menache, Sirui Li
- Organisations
- Microsoft, University of Washington, Stanford University, Puc-Rio
- QRS classification
- Reinforcement learning, Language models