4 papers
Learning When to Plan: Efficiently Allocating Test-Time Compute for LLM Agents
Davide Paglieri, Bartłomiej Cupiał, 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…
Preference-Based Alignment of Discrete Diffusion Models
Umberto Borso, Davide Paglieri, Jude Wells +1
Diffusion models have achieved state-of-the-art performance across multiple domains, with recent advancements extending their applicability to discrete data. However, aligning disc…
BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games
Davide Paglieri, Bartłomiej Cupiał, Samuel Coward +10
Large Language Models (LLMs) and Vision Language Models (VLMs) possess extensive knowledge and exhibit promising reasoning abilities, however, they still struggle to perform well i…
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…