1 citations · 1 across the 5 of their papers we have counts for
Showing 2026Show all
3 papers · 1 filter
cs.LG2026
Controlling Sharpening in LLM Post-Training
Simon Matrenok, Nicolas Menet, Nicolas Flammarion +1
LLM post-training via reinforcement learning has shown consistent improvements in accuracy at the cost of reducing behavioral coverage - a phenomenon known as sharpening that can s…
cs.LG2026
POETS: Uncertainty-Aware LLM Optimization via Compute-Efficient Policy Ensembles
Nicolas Menet, Andreas Krause, Abbas Rahimi
Balancing exploration with exploitation is a core challenge in black-box optimization and reinforcement learning. We introduce POETS (licy nsembles for $\t…
cs.SE2026
A Theoretical Analysis of Test-Driven Code Generation
Nicolas Menet, Michael Hersche, Andreas Krause +1
Code assistants are increasingly utilized in test-driven software development, yet the theoretical mechanisms behind their environment-interaction strategies remain underexplored.…