4 papers
Conv-to-Bench: Evaluating Language Models Via User-Assistant Dialogues In Code Tasks
Victor M. dos Santos, Andre C. Castro, Samuel L. de S. Toledo +5
The rapid advancement of Large Language Models (LLMs) has outpaced the scalability of traditional evaluation benchmarks, which remain heavily dependent on labor-intensive expert cu…
Do Reasoning Models Ask Better Questions? A Formal Information-Theoretic Analysis on Multi-Turn LLM Games
Daniel M. Pedrozo, Telma W. de L. Soares, Bryan L. M. de Oliveira
Large Language Models (LLMs) excel at many tasks but still struggle with a critical ability for LLM-based agents: asking good questions for resolving ambiguity in user requests. Wh…
Learning Without Critics? Revisiting GRPO in Classical Reinforcement Learning Environments
Bryan L. M. de Oliveira, Felipe V. Frujeri, Marcos P. C. M. Queiroz +3
Group Relative Policy Optimization (GRPO) has emerged as a scalable alternative to Proximal Policy Optimization (PPO) by eliminating the learned critic and instead estimating advan…
Sliding Puzzles Gym: A Scalable Benchmark for State Representation in Visual Reinforcement Learning
Bryan L. M. de Oliveira, Luana G. B. Martins, Bruno Brandão +3
Effective visual representation learning is crucial for reinforcement learning (RL) agents to extract task-relevant information from raw sensory inputs and generalize across divers…