Yoann Poupart
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
ML×1Multiagent×1
Frequent co-authors
Research Timeline
2026
Policy Gradient Steering: Interventions from Behavioral Objectives
This paper proposes Policy Gradient Steering (PGS), a new method for dynamically changing a large language model's behavior at inference time using reinforcement learning.
Highlighted terms show continued research focus across papers