arXiv2
Search
Dark
/ Date
/ Name
Aa
W
/ Date
/ Name
"au:"Telma W. de L. Soares"" — arXiv2 Search
Showing 1–3 of 3 results
/ Date
/ Name
Jan 25, 2026
Do Reasoning Models Ask Better Questions? A Formal Information-Theoretic Analysis on Multi-Turn LLM Games
Nov 5, 2025
Learning Without Critics? Revisiting GRPO in Classical Reinforcement Learning Environments
Oct 17, 2024
Sliding Puzzles Gym: A Scalable Benchmark for State Representation in Visual Reinforcement Learning