Temperature as a Meta-Policy: Adaptive Temperature in LLM Reinforcement Learning
This work addresses the challenge of adaptive exploration in LLM reinforcement learning for researchers and practitioners, offering a novel but incremental improvement over existing temperature control methods.
The paper tackles the problem of static temperature hyperparameters limiting exploration-exploitation trade-offs in LLM reinforcement learning by proposing TAMPO, a framework that learns temperature as a meta-policy, resulting in improved performance on five mathematical reasoning benchmarks.
Temperature is a crucial hyperparameter in large language models (LLMs), controlling the trade-off between exploration and exploitation during text generation. High temperatures encourage diverse but noisy outputs, while low temperatures produce focused outputs but may cause premature convergence. Yet static or heuristic temperature schedules fail to adapt to the dynamic demands of reinforcement learning (RL) throughout training, often limiting policy improvement. We propose Temperature Adaptive Meta Policy Optimization (TAMPO), a new framework that recasts temperature control as a learnable meta-policy. TAMPO operates through a hierarchical two-loop process. In the inner loop, the LLM policy is updated (e.g., using GRPO) with trajectories sampled at the temperature selected by the meta-policy. In the outer loop, meta-policy updates the distribution over candidate temperatures by rewarding those that maximize the likelihood of high-advantage trajectories. This trajectory-guided, reward-driven mechanism enables online adaptation without additional rollouts, directly aligning exploration with policy improvement. On five mathematical reasoning benchmarks, TAMPO outperforms baselines using fixed or heuristic temperatures, establishing temperature as an effective learnable meta-policy for adaptive exploration in LLM reinforcement learning. Accepted at ICLR 2026.