Reasoning LLMs under fixed token budgets often commit before verification finishes, or spend the budget on deliberation that never reaches a final answer. Existing inference-time controllers regulate reasoning length, which does not indicate whether the current prefix is ready to be finalized. We introduce ParentingLLM, an inference-time controller that paces reasoning maturity, defined as the prefix’s readiness to commit given the remaining budget, against a user-specified target schedule, without fine-tuning the underlying LLM. The maturity estimate combines consumed budget with a forked forced-commit probe; the controller injects Wait when the estimate runs ahead of the schedule and Hurry when it lags. On MATH-500, GPQA-Diamond, AIME 24+25, and GSM-Hard with three Gemma-4 models and Qwen3.5-9B, ParentingLLM improves over prior inference-time baselines, with the largest gains on AIME 24+25 under a tight budget (-22.6 burst rate, +4.0 to +7.3 accuracy at B=1024).

Employing large language models (LLMs) to enable embodied agents has become popular, yet it presents several limitations in practice. In this work, rather than using LLMs directly as agents, we explore their use as tools for embodied agent learning. Specifically, to train separate agents via offline reinforcement learning (RL), an LLM is used to provide dense reward feedback on individual actions in training datasets. In doing so, we present a consistency-guided reward ensemble framework (CoREN), designed for tackling difficulties in grounding LLM-generated estimates to the target environment domain. The framework employs an adaptive ensemble of spatio-temporally consistent rewards to derive domain-grounded rewards in the training datasets, thus enabling effective offline learning of embodied agents in different environment domains. Experiments with the VirtualHome benchmark demonstrate that CoREN significantly outperforms other offline RL agents, and it also achieves comparable performance to state-of-the-art LLM-based agents with 8B parameters, despite CoREN having only 117M parameters for the agent policy network and using LLMs only for training.