Nathan Grinsztajn

4

Papers

51

Total Citations

Papers (4)

Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX

Memory-Enhanced Neural Solvers for Routing Problems

ShiQ: Bringing back Bellman to LLMs

NeurIPS 2025arXiv

Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs