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).

Effective collaboration in multi-agent systems requires mechanisms for coordination and adaptability in dynamic and uncertain environments. However, existing multi-agent systems rarely model resilience explicitly, instead relying on ad-hoc output correction that limits systematic, runtime management of robustness. In this work, we propose Multi-Agent Mesh (MA-Mesh), a framework that constructs a role-based self-healing layer on top of a collaboration pattern. Specifically, MA-Mesh generates resilience-aware system specifications and synthesizes them into executable multi-agent policy code. To enhance resilience, we introduce two self-healing mechanisms: Cross-agent reflection, a mechanism that allows agents to evaluate not only their own outcomes but also the performance of their peers, enabling informed behavioral adjustments and collective policy refinement; Role-based failover, a strategy which dynamically reassigns roles and enables agents to substitute for one another when sub-tasks fail or agents underperform, ensuring continuity of task execution. Experimental results across diverse tasks (e.g., software development, tool use, scientific reasoning) demonstrate that MA-Mesh significantly outperforms existing multi-agent systems in both task performance and robustness under system uncertainty.

Recent advances in LLMs and VLMs have enabled safety systems to reason beyond simple risk patterns toward more contextual and semantic safety concerns. However, as risk patterns continue to evolve and safety rules become more complex, existing training-based end-to-end safeguards face persistent challenges in adaptability and explainable reasoning over complex safety rules. To address these challenges, we propose GuardEn (Guarding by Safety Rule Entailment), an executable safeguard framework that decomposes safety policies into atomic propositions through Safety-Rule Compilation, modeling their composition as executable code. At test time, Scene-Grounded Execution instantiates these atomic propositions with contextual visual information derived from scene graphs, enabling rule-grounded and interpretable safety reasoning. Experiments on SafetyVisionBench demonstrate the effectiveness of programmable safeguard for complex visual safety assessment, achieving an average improvement of 9.8 F1 points over the strongest baseline across four domains.

Language model (LM)-powered agents have shown promise in addressing complex embodied tasks by leveraging the commonsense world knowledge of pre-trained models in interactive physical environments. Yet, real-world deployment requires agents to continually adapt to a stream of tasks, where neither large-scale expert supervision nor reliable external feedback is consistently available. In this paper, we present ASC, a framework for efficient continual embodied task adaptation through amortizing self-correction. Specifically, ASC trains the policy under two objectives: a standard CoT reasoning objective distilled from stronger experts, and a reflexive reasoning objective that internalizes self-correction by correcting initial rationales generated by a previously learned policy. This dual optimization allows the agent to adapt more efficiently through forward knowledge transfer over time, ultimately fostering robust CoT reasoning at inference without requiring explicit reflection. Furthermore, we introduce rationale-wise test-time scaling that dynamically adjusts the depth of CoT reasoning based on the model’s confidence in actions inferred from its own rationales. Through experiments on VirtualHome and ALFWorld, we demonstrate performance superiority over other LM-based planning and continual task adaptation approaches, while achieving strong efficiency in computation, data usage.

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.

In embodied instruction-following (EIF), the integration of pretrained language models (LMs) as task planners emerges as a significant branch, where tasks are planned at the skill level by prompting LMs with pretrained skills and user instructions. However, grounding these pretrained skills in different domains remains challenging due to their intricate entanglement with the domain-specific knowledge. To address this challenge, we present a semantic skill grounding (SemGro) framework that leverages the hierarchical nature of semantic skills. SemGro recognizes the broad spectrum of these skills, ranging from short-horizon low-semantic skills that are universally applicable across domains to long-horizon rich-semantic skills that are highly specialized and tailored for particular domains. The framework employs an iterative skill decomposition approach, starting from the higher levels of semantic skill hierarchy and then moving downwards, so as to ground each planned skill to an executable level within the target domain. To do so, we use the reasoning capabilities of LMs for composing and decomposing semantic skills, as well as their multi-modal extension for assessing the skill feasibility in the target domain. Our experiments in the VirtualHome benchmark show the efficacy of SemGro in 300 cross-domain EIF scenarios.