Current language models have achieved remarkable success in NLP tasks. Nonetheless, individual decoding methods face difficulties in realizing the immense potential of these models. The challenge is primarily due to the lack of a decoding framework that can integrate language models and decoding methods. We introduce DecoStrat, which bridges the gap between language modeling and the decoding process in D2T generation. By leveraging language models, DecoStrat facilitates the exploration of alternative decoding methods tailored to specific tasks. We fine-tuned the model on the MultiWOZ dataset to meet task-specific requirements and employed it to generate output(s) through multiple interactive modules of the framework. The Director module orchestrates the decoding processes, engaging the Generator to produce output(s) text based on the selected decoding method and input data. The Manager module enforces a selection strategy, integrating Ranker and Selector to identify the optimal result. Evaluations on the stated dataset show that DecoStrat effectively produces a diverse and accurate output, with MBR variants consistently outperforming other methods. DecoStrat with the T5-small model surpasses some baseline frameworks. Generally, the findings highlight DecoStrat’s potential for optimizing decoding methods in diverse real-world applications.

Graph-to-text generation (G2T) involves converting structured graph data into natural language text, a task made challenging by the need for encoders to capture the entities and their relationships within the graph effectively. While transformer-based encoders have advanced natural language processing, their reliance on linearized data often obscures the complex interrelationships in graph structures, leading to structural loss. Conversely, graph attention networks excel at capturing graph structures but lack the pre-training advantages of transformers. To leverage the strengths of both modalities and bridge this gap, we propose a novel bidirectional dual cross-attention and concatenation (BDCC) mechanism that integrates outputs from a transformer-based encoder and a graph attention encoder. The bidirectional dual cross-attention computes attention scores bidirectionally, allowing graph features to attend to transformer features and vice versa, effectively capturing inter-modal relationships. The concatenation is applied to fuse the attended outputs, enabling robust feature fusion across modalities. We empirically validate BDCC on PathQuestions and WebNLG benchmark datasets, achieving BLEU scores of 67.41% and 66.58% and METEOR scores of 49.63% and 47.44%, respectively. The results outperform the baseline models and demonstrate that BDCC significantly improves G2T tasks by leveraging the synergistic benefits of graph attention and transformer encoders, addressing the limitations of existing approaches and showcasing the potential for future research in this area.

Current language models have achieved remarkable success in NLP tasks. Nonetheless, individual decoding methods face difficulties in realizing the immense potential of these models. The challenge is primarily due to the lack of a decoding framework that can integrate language models and decoding methods. We introduce the DecoStrat which bridges the gap between language modeling and the decoding process in D2T generation. By leveraging language models, DecoStrat facilitates the exploration of alternative decoding methods tailored to specific tasks. We fine-tune the model on the MultiWOZ dataset to meet task-specific requirements and employ it to generate output(s) through multiple interactive modules of the framework. The Director module orchestrates the decoding processes, engaging the Generator to produce output(s) text based on the selected decoding method and input data. The Manager module enforces a selection strategy, integrating Ranker and Selector to identify the optimal result. Evaluations on the stated dataset show that DecoStrat effectively produces diverse and accurate output, with MBR variants consistently outperforming other methods. DecoStrat with the T5-small model surpasses some baseline. Generally, the findings highlight DecoStrat's potential for optimizing decoding methods in diverse real-world applications.

Reinforcement learning (RL) has emerged as a promising approach for autonomous surgical robotic subtasks. Recent advances include deep reinforcement learning (DRL), imitation learning (IL), and vision–language–action (VLA) models. However, current evidence remains fragmented across simulation benchmarks, task-specific demonstrations, and limited clinical studies. Existing reviews primarily focus on RL algorithms, while the broader pathway from algorithm development to clinically deployable surgical autonomy has not been comprehensively synthesised. This PRISMA 2020-guided systematic review examines RL, IL, safe RL, simulation-to-real (sim-to-real) transfer, foundation models, VLA systems, and regulatory readiness in surgical robotics. We searched IEEE Xplore, PubMed/MEDLINE, Embase, Scopus, Web of Science, the Cochrane Library, ACM Digital Library, arXiv, and medRxiv for studies published between January 2015 and March 2026, with additional studies identified through backward citation tracing. Eligible studies proposed novel RL, imitation learning, or foundation-model approaches for surgical robotics with empirical validation in simulation or on physical robotic platforms. Two reviewers independently extracted data using a predefined coding scheme, and a third reviewer resolved disagreements. Owing to substantial heterogeneity in platforms, tasks, and outcome measures, a quantitative meta-analysis was not feasible; therefore, the evidence was synthesised narratively using a comparative framework. A total of 220 studies met the inclusion criteria, covering eleven active surgical RL platforms, seven paired sim-to-real studies, emerging foundation-model architectures, and three FDA-cleared robotic systems exhibiting Level 3 autonomy. Available comparative studies suggest that hierarchical approaches can outperform flat policies in long-horizon tasks, while language-conditioned models demonstrated promising multi-step surgical capabilities. Seven paired simulation-to-real studies were identified, encompassing tissue retraction, guidewire navigation, and surgical cutting tasks. Sim-to-real performance gaps varied substantially by task and metric, with success-rate gaps ranging from −10 to 50 percentage points (negative values indicating better real-world than simulated performance), while paired mean spatial errors differed by at most 0.61 mm. Most studies employed domain randomization or visual domain adaptation; hierarchical reinforcement learning demonstrated advantages over flat policies in multi-step surgical tasks. Explicit safety-constrained methods (CPO, CBF, and SER), formal verification, and regulatory-aligned evaluation were reported in fewer than 3% of applied studies. Most evidence remained simulation-based, with no reported autonomous RL execution in vivo in humans. Overall, RL-based surgical robotics appears mature at the simulation stage but remains preclinical for autonomous clinical deployment. Future progress requires stronger sim-to-real validation, multimodal safety-aware architectures, alignment with IEC 62304, ISO 14971, FDA guidance, and the EU AI Act, and open benchmarks that jointly evaluate performance, safety, and surgeon trust.