2 papers
cs.LG2026
Policy-Invariant Reward Shaping from LLM Feedback: A Framework for Hybrid RL Agents
Christophe D. Hounwanou, John Emeka Eze, Yaé U. Gaba
Combining large language models with reinforcement learning is increasingly explored, yet the theoretical status of LLM-derived reward signals is often left implicit. We formalize…
cs.AI2026
Hybrid LLM-Augmented Reinforcement Learning Agents for Complex Sequential Decision Tasks
Christophe D. Hounwanou, John Emeka Eze, Yaé Ulrich Gaba
Large Language Models (LLMs) have recently shown strong capabilities in reasoning, planning, and tool-use, enabling new forms of autonomous agents. However, LLM-based agents strugg…