4 papers
SAC-GLAM: Improving Online RL for LLM agents with Soft Actor-Critic and Hindsight Relabeling
Loris Gaven, Clement Romac, Thomas Carta +3
The past years have seen Large Language Models (LLMs) strive not only as generative models but also as agents solving textual sequential decision-making tasks. When facing complex…
Optimizing for Persuasion Improves LLM Generalization: Evidence from Quality-Diversity Evolution of Debate Strategies
Aksel Joonas Reedi, Corentin Léger, Julien Pourcel +3
Large Language Models (LLMs) optimized to output truthful answers often overfit, producing brittle reasoning that fails to generalize. While persuasion-based optimization has shown…
HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents
Thomas Carta, Clément Romac, Loris Gaven +3
We study goal-conditioned reinforcement learning in partially observable environments with sparse rewards and large, structured goal spaces. In such settings, complex goals often r…
MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces
Loris Gaven, Thomas Carta, Clément Romac +4
Open-ended learning agents must efficiently prioritize goals in vast possibility spaces, focusing on those that maximize learning progress (LP). When such autotelic exploration is…