Some generative linguists report that in formal settings, learners of English as a foreign language often strive to acquire morphemes such as the third-person singular –s and produce utterances such as *he play. This study reviews generative linguistics, psychology, neuroscience, and biolinguistics, examining how speech and other forms of action involve hierarchically organised groups (chunks) of words or acts that are invariably produced in linear order. Chunks contribute to brain efficiency, facilitating acquisition and enabling brain automaticity. A study was conducted to improve the accuracy rates of sentence segments featuring the third-person singular –s (e.g., “he VERB+s”) by orally rehearsing chunk-based sentences (e.g., [He plays] [a lot]). Sixty-four children from three Spanish schools, learning English as a foreign language and aged 8–11, participated in this study. The participants, divided into a control group and two experimental groups, completed an oral sentence transformation task following a pre-test–post-test design. The Wilcoxon test showed statistically significant results for the experimental groups after the administration of oral chunk-based training. Quartiles and deciles demonstrated improvement in these groups. The findings suggest that oral chunk-based training could foster chunk and morpheme acquisition. This pedagogy might enhance brain efficiency in learning and promote automatic speech.

Large Language Models are increasingly used for high-level robotic reasoning, yet their latency and stochasticity complicate their direct use in low-level control. Moreover, extracting actionable navigation cues from multimodal context incurs inference costs that are challenging for embedded platforms. We present a plug-and-play framework that augments a finite-state machine with asynchronous velocity suggestions generated by a Large Language Model, using an off-the-shelf DistilGPT-2 model running on-device on a Jetson AGX Orin. The system extracts task-relevant cues from the current context and integrates them only if they satisfy deadline, schema, and kinematic validation, thereby preserving a deterministic 50 Hz control loop with a <5 ms fallback path. We compare multiple Large Language Models for embedded robot control and quantify trade-offs among model size, inference time, and output validity. To assess whether the Large Language Models add value beyond signal processing, we include an ablation against a standard smoothing baseline; the results indicate that the Large Language Models contribute anticipatory, context-dependent adjustments that are not captured by filtering alone. Experiments in Gazebo and on a real TurtleBot3 reduce the final position error from 0.246 m to 0.159 m and improve trajectory efficiency from 0.821 to 0.901 without increasing control-loop latency. Approximately 80% of the Large Language Models’ outputs pass validation and are applied. Overall, the framework reduces developer effort by enabling behavioral changes at the prompt level while maintaining interpretable, robust edge-based navigation.

This paper presents a proof-of-concept for a natural-language-based closed-loop controller that regulates the temperature of a simple single-input single-output (SISO) thermal process. The key idea is to express a relay-with-hysteresis policy in plain English and let a local large language model (LLM) interpret sensor readings and output a binary actuation command at each sampling step. Beyond interface convenience, we demonstrate that natural language can serve as a valid medium for modeling physical reality and executing deterministic reasoning in control loops. We implement a compact plant model and compare two controllers: a conventional coded relay and an LLM-driven controller prompted with the same logic and constrained to a single-token output. The workflow integrates schema validation, retries, and a safe fallback, while a stepwise evaluator checks agreement with the baseline. In a long-horizon (1000-step) simulation, the language controller reproduces the hysteresis behavior with matching switching patterns. Furthermore, sensitivity and ablation studies demonstrate the system’s robustness to measurement noise and the LLM’s ability to correctly execute the hysteresis policy, thereby preserving the theoretical robustness inherent to this control law. This work demonstrates that, for slow thermal dynamics, natural-language policies can achieve comparable performance to classical relay systems while providing a transparent, human-readable interface and facilitating rapid iteration.

Humans acquire meaningful language by storing perceptual categories, category-word mappings, and conditional IF–THEN rules in rich, cross-domain, multimodal contexts. Crucially, structured cross-domain input that pairs visual context and language (text) appears to be fundamental to this process, enabling individuals to acquire, for example, the lexicon. The present study investigates whether Large Language Models (LLMs) can learn words when trained on structured cross-domain input rather than text-only exposure. This paper incorporates a controlled Fictitious-Animal Paradigm featuring 32 creatures and 32 pseudowords, divided into two phases: single-animal and dual-animal scenes. Single-animal contexts entailed storing categories and mappings, while dual-animal environments involved storing logical constraints and performing inference. The authors propose a computational model centred on four capacities for context-based word learning: storing perceptual categories, category-word mappings, and the Mutual Exclusivity rule (formalised as a conditional IF-THEN statement), and retrieving stored information to assign novel labels through inference. The evaluation demonstrates that structured cross-domain input enables LLMs to exhibit behaviour consistent with conditional IF–THEN rules, allowing them to infer and acquire novel words based on current visual contexts. These findings suggest that, with this input that integrates context and text, LLMs display adaptive, real-time human-like inferential reasoning in word learning.