8 papers
Learning to Learn from Language Feedback with Social Meta-Learning
Jonathan Cook, Diego Antognini, Martin Klissarov +2
Large language models (LLMs) often struggle to learn from corrective feedback within a conversational context. They are rarely proactive in soliciting this feedback, even when face…
Improving Interactive In-Context Learning from Natural Language Feedback
Martin Klissarov, Jonathan Cook, Diego Antognini +5
Adapting one's thought process based on corrective feedback is an essential ability in human learning, particularly in collaborative settings. In contrast, the current large langua…
Learning When to Plan: Efficiently Allocating Test-Time Compute for LLM Agents
Davide Paglieri, BartÅomiej CupiaÅ, Jonathan Cook +6
Training large language models (LLMs) to reason via reinforcement learning (RL) significantly improves their problem-solving capabilities. In agentic settings, existing methods lik…
Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models
Laura Ruis, Maximilian Mozes, Juhan Bae +7
The capabilities and limitations of Large Language Models have been sketched out in great detail in recent years, providing an intriguing yet conflicting picture. On the one hand,…
Assessing the Zero-Shot Capabilities of LLMs for Action Evaluation in RL
Eduardo Pignatelli, Johan Ferret, Tim Rockäschel +4
The temporal credit assignment problem is a central challenge in Reinforcement Learning (RL), concerned with attributing the appropriate influence to each actions in a trajectory f…
minimax: Efficient Baselines for Autocurricula in JAX
Minqi Jiang, Michael Dennis, Edward Grefenstette +1
Unsupervised environment design (UED) is a form of automatic curriculum learning for training robust decision-making agents to zero-shot transfer into unseen environments. Such aut…