Exploration v.s. Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward Paper • 2512.16912 • Published Dec 18, 2025 • 12
GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators Paper • 2512.19682 • Published Dec 22, 2025 • 17
Exploration v.s. Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward Paper • 2512.16912 • Published Dec 18, 2025 • 12