There has been rapid development in generative AI tools across the education sector, which in turn is leading to increased adoption by teachers. However, this raises concerns regarding the safety and age-appropriateness of the AI-generated content that is being created for use in classrooms. This paper explores Oak National Academy's approach to addressing these concerns within the development of the UK Government's first publicly available generative AI tool - our AI-powered lesson planning assistant (Aila). Aila is intended to support teachers planning national curriculum-aligned lessons that are appropriate for pupils aged 5-16 years. To mitigate safety risks associated with AI-generated content we have implemented four key safety guardrails: (1) prompt engineering to ensure AI outputs are generated within pedagogically sound and curriculum-aligned parameters; (2) input threat detection to mitigate attacks; (3) an Independent Asynchronous Content Moderation Agent (IACMA) to assess outputs against predefined safety categories; and (4) taking a human-in-the-loop approach, to encourage teachers to review generated content before it is used in the classroom. Through our on-going evaluation of these safety guardrails we have identified several challenges and opportunities to take into account when implementing and testing safety guardrails. This paper highlights ways to build more effective safety guardrails in generative AI education tools including the on-going iteration and refinement of guardrails, as well as enabling cross-sector collaboration through sharing both open-source code/datasets and learnings.

Teaching robots dexterous skills from human videos remains challenging due to the reliance on low-level trajectory imitation, which fails to generalize across object types, spatial layouts, and manipulator configurations. We propose Graph-Fused Vision-Language-Action (GF-VLA), a framework that enables dual-arm robotic systems to perform task-level reasoning and execution directly from RGB and Depth human demonstrations. GF-VLA first extracts Shannon-information-based cues to identify hands and objects with the highest task relevance, then encodes these cues into temporally ordered scene graphs that capture both hand-object and object-object interactions. These graphs are fused with a language-conditioned transformer that generates hierarchical behavior trees and interpretable Cartesian motion commands. To improve execution efficiency in bimanual settings, we further introduce a cross-hand selection policy that infers optimal gripper assignment without explicit geometric reasoning. We evaluate GF-VLA on four structured dual-arm block assembly tasks involving symbolic shape construction and spatial generalization. Experimental results show that the information-theoretic scene representation achieves over 95 percent graph accuracy and 93 percent subtask segmentation, supporting the LLM planner in generating reliable and human-readable task policies. When executed by the dual-arm robot, these policies yield 94 percent grasp success, 89 percent placement accuracy, and 90 percent overall task success across stacking, letter-building, and geometric reconfiguration scenarios, demonstrating strong generalization and robustness across diverse spatial and semantic variations.

We propose a hybrid architecture that integrates decision tree-based symbolic reasoning with the generative capabilities of large language models (LLMs) within a coordinated multi-agent framework. Unlike prior approaches that loosely couple symbolic and neural modules, our design embeds decision trees and random forests as callable oracles within a unified reasoning system. Tree-based modules enable interpretable rule inference and causal logic, while LLM agents handle abductive reasoning, generalization, and interactive planning. A central orchestrator maintains belief state consistency and mediates communication across agents and external tools, enabling reasoning over both structured and unstructured inputs. The system achieves strong performance on reasoning benchmarks. On \textit{ProofWriter}, it improves entailment consistency by +7.2\% through logic-grounded tree validation. On GSM8k, it achieves +5.3\% accuracy gains in multistep mathematical problems via symbolic augmentation. On \textit{ARC}, it boosts abstraction accuracy by +6.0\% through integration of symbolic oracles. Applications in clinical decision support and scientific discovery show how the system encodes domain rules symbolically while leveraging LLMs for contextual inference and hypothesis generation. This architecture offers a robust, interpretable, and extensible solution for general-purpose neuro-symbolic reasoning.

Despite the promising potential of large language model (LLM) based register-transfer-level (RTL) code generation, the overall success rate remains unsatisfactory. Errors arise from various factors, with limited understanding of specific failure causes hindering improvement. To address this, we conduct a comprehensive error analysis and manual categorization. Our findings reveal that most errors stem not from LLM reasoning limitations, but from insufficient RTL programming knowledge, poor understanding of circuit concepts, ambiguous design descriptions, or misinterpretation of complex multimodal inputs. Leveraging in-context learning, we propose targeted error correction techniques. Specifically, we construct a domain-specific knowledge base and employ retrieval-augmented generation (RAG) to supply necessary RTL knowledge. To mitigate ambiguity errors, we introduce design description rules and implement a rule-checking mechanism. For multimodal misinterpretation, we integrate external tools to convert inputs into LLM-compatible meta-formats. For remaining errors, we adopt an iterative debugging loop (simulation-error localization-correction). Integrating these techniques into an LLM-based framework significantly improves performance. We incorporate these error correction techniques into a foundational LLM-based RTL code generation framework, resulting in significantly improved performance. Experimental results show that our enhanced framework achieves 91.0\% accuracy on the VerilogEval benchmark, surpassing the baseline code generation approach by 32.7\%, demonstrating the effectiveness of our methods.

A central challenge in this domain is the inherent trade-off between enhancing adversarial robustness and preserving the model's zero-shot generalization capabilities. We analyze two primary defense paradigms that have emerged from recent research. The first, Adversarial Fine-Tuning (AFT), involves modifying model parameters. We trace its evolution from early methods focused on protecting vision-language alignment (TeCoA) and mitigating overfitting through pre-trained model guidance (PMG-AFT, TGA-ZSR), to more advanced strategies that proactively re-engineer the embedding space's geometry to build intrinsic robustness (LAA T, TIMA). The second paradigm, Training-Free and Test-Time Defenses, avoids parameter modification altogether. We examine its progression from simple, heuristic-based input manipulations (AOM, TTC) to theoretically grounded purification methods in the model's latent space (CLIPure). By analyzing these works, we distill the field's core problems--including the robustness-generalization dilemma, geometric vulnerabilities, and computational costs--and identify key insights. We conclude by outlining promising future directions, such as the development of hybrid defense models and the pursuit of large-scale adversarial pre-training to create natively robust foundation models.

The surge in rich multimodal content on social media platforms has greatly advanced Multimodal Sentiment Analysis (MSA), with Large Language Models (LLMs) further accelerating progress in this field. Current approaches primarily leverage the knowledge and reasoning capabilities of parameter-heavy (Multimodal) LLMs for sentiment classification, overlooking autonomous multimodal sentiment reasoning generation in resource-constrained environments. Therefore, we focus on the Resource-Limited Joint Multimodal Sentiment Reasoning and Classification task, JMSRC, which simultaneously performs multimodal sentiment reasoning chain generation and sentiment classification only with a lightweight model. We propose a Multimodal Chain-of-Thought Reasoning Distillation model, MulCoT-RD, designed for JMSRC that employs a "Teacher-Assistant-Student" distillation paradigm to address deployment constraints in resource-limited environments. We first leverage a high-performance Multimodal Large Language Model (MLLM) to generate the initial reasoning dataset and train a medium-sized assistant model with a multi-task learning mechanism. A lightweight student model is jointly trained to perform efficient multimodal sentiment reasoning generation and classification. Extensive experiments on four datasets demonstrate that MulCoT-RD with only 3B parameters achieves strong performance on JMSRC, while exhibiting robust generalization and enhanced interpretability.

Traditional parameter-efficient fine-tuning (PEFT) methods such as LoRA are tightly coupled with the base model architecture, which constrains their applicability across heterogeneous pretrained large language models (LLMs). To address this limitation, we introduce Cross-LoRA, a data-free framework for transferring LoRA modules between diverse base models without requiring additional training data. Cross-LoRA consists of two key components: (a) LoRA-Align, which performs subspace alignment between source and target base models through rank-truncated singular value decomposition (SVD) and Frobenius-optimal linear transformation, ensuring compatibility under dimension mismatch; and (b) LoRA-Shift, which applies the aligned subspaces to project source LoRA weight updates into the target model parameter space. Both components are data-free, training-free, and enable lightweight adaptation on a commodity GPU in 20 minutes. Experiments on ARCs, OBQA and HellaSwag show that Cross-LoRA achieves relative gains of up to 5.26% over base models . Across other commonsense reasoning benchmarks, Cross-LoRA maintains performance comparable to that of directly trained LoRA adapters.

Aligning LLMs with user preferences is crucial for real-world use but often requires costly fine-tuning or expensive inference, forcing trade-offs between alignment quality and computational cost. Existing inference-time methods typically ignore this balance, focusing solely on the optimized policy's performance. We propose HIA (Heuristic-Guided Inference-time Alignment), a tuning-free, black-box-compatible approach that uses a lightweight prompt optimizer, heuristic reward models, and two-stage filtering to reduce inference calls while preserving alignment quality. On real-world prompt datasets, HelpSteer and ComPRed, HIA outperforms best-of-N sampling, beam search, and greedy search baselines in multi-objective, goal-conditioned tasks under the same inference budget. We also find that HIA is effective under low-inference budgets with as little as one or two response queries, offering a practical solution for scalable, personalized LLM deployment.

With the remarkable advancement of AI agents, the number of their equipped tools is increasing rapidly. However, integrating all tool information into the limited model context becomes impractical, highlighting the need for efficient tool retrieval methods. In this regard, dominant methods primarily rely on semantic similarities between tool descriptions and user queries to retrieve relevant tools. However, they often consider each tool independently, overlooking dependencies between tools, which may lead to the omission of prerequisite tools for successful task execution. To deal with this defect, in this paper, we propose Tool Graph Retriever (TGR), which exploits the dependencies among tools to learn better tool representations for retrieval. First, we construct a dataset termed TDI300K to train a discriminator for identifying tool dependencies. Then, we represent all candidate tools as a tool dependency graph and use graph convolution to integrate the dependencies into their representations. Finally, these updated tool representations are employed for online retrieval. Experimental results on several commonly used datasets show that our TGR can bring a performance improvement to existing dominant methods, achieving SOTA performance. Moreover, in-depth analyses also verify the importance of tool dependencies and the effectiveness of our TGR.

The integration of large language models into healthcare necessitates a rigorous evaluation of their ethical reasoning, an area current benchmarks often overlook. We introduce PrinciplismQA, a comprehensive benchmark with 3,648 questions designed to systematically assess LLMs' alignment with core medical ethics. Grounded in Principlism, our benchmark features a high-quality dataset. This includes multiple-choice questions curated from authoritative textbooks and open-ended questions sourced from authoritative medical ethics case study literature, all validated by medical experts. Our experiments reveal a significant gap between models' ethical knowledge and their practical application, especially in dynamically applying ethical principles to real-world scenarios. Most LLMs struggle with dilemmas concerning Beneficence, often over-emphasizing other principles. Frontier closed-source models, driven by strong general capabilities, currently lead the benchmark. Notably, medical domain fine-tuning can enhance models' overall ethical competence, but further progress requires better alignment with medical ethical knowledge. PrinciplismQA offers a scalable framework to diagnose these specific ethical weaknesses, paving the way for more balanced and responsible medical AI.