Explainability and interpretability are cornerstones of frontier and next-generation artificial intelligence (AI) systems. This is especially true in recent systems, such as large language models (LLMs), and more broadly, generative AI. On the other hand, adaptability to new domains, contexts, or scenarios is also an important aspect for a successful system. As such, we are particularly interested in how we can merge these two efforts, that is, investigating the design of transferable and interpretable neurosymbolic AI systems. Specifically, we focus on a class of systems referred to as ''Agentic Retrieval-Augmented Generation'' systems, which actively select, interpret, and query knowledge sources in response to natural language prompts. In this paper, we systematically evaluate how different conceptualizations and representations of knowledge, particularly the structure and complexity, impact an AI agent (in this case, an LLM) in effectively querying a triplestore. We report our results, which show that there are impacts from both approaches, and we discuss their impact and implications.

Multimodal large language models (MLLMs) still perform poorly on scientific tasks, particularly those requiring multi-step and interpretable reasoning. Their limitations include insufficient scientific reasoning patterns, lack of global coherence in multi-step inference, and the absence of reflective self-correction, making them unreliable in structured scientific contexts. We introduce EduFlow, the first end-to-end framework that covers the full pipeline of educational scientific reasoning, including data selection, MCTS-based trajectory construction, model training, and output optimization. At its core is EduPRM, a process-aware reward model that critiques reasoning steps with tags and justifications. EduPRM is trained via curriculum learning on three complementary supervision sources: MCTS-guided trajectories, error-injected critiques, and teacher-student dialogues, enabling dynamic adaptation to multi-stage problem solving and iterative refinement during inference. We further propose EduMCTS, a domain-adapted search framework that introduces bootstrapping actions specifically designed for educational reasoning, such as a self-reflection mechanism that promotes reflective error correction. It further leverages EduPRM's fine-grained feedback to guide the search toward higher-quality reasoning trajectories. By applying self-consistency and rejection sampling, we constructed EduMCTS-160K, a large-scale dataset of educational reasoning trajectories. Extensive experiments demonstrate that EduFlow enhances reasoning consistency and coherence. Code, data, and models will be released.

Humour translation plays a vital role as a bridge between different cultures, fostering understanding and communication. Although most existing Large Language Models (LLMs) are capable of general translation tasks, these models still struggle with humour translation, which is especially reflected through linguistic interference and lacking humour in translated text. In this paper, we propose a psychology-inspired Humour Decomposition Mechanism (HDM) that utilises Chain-of-Thought (CoT) to imitate the ability of the human thought process, stimulating LLMs to optimise the readability of translated humorous texts. Moreover, we integrate humour theory in HDM to further enhance the humorous elements in the translated text. Our automatic evaluation experiments on open-source humour datasets demonstrate that our method significantly improves the quality of humour translation, yielding average gains of 7.75\% in humour, 2.81\% in fluency, and 6.13\% in coherence of the generated text.

We present StockSim, an open-source simulation platform for systematic evaluation of large language models (LLMs) in realistic financial decision-making scenarios. Unlike previous toolkits that offer limited scope, StockSim delivers a comprehensive system that fully models market dynamics and supports diverse simulation modes of varying granularity. It incorporates critical real-world factors, such as latency, slippage, and order-book microstructure, that were previously neglected, enabling more faithful and insightful assessment of LLM-based trading agents. An extensible, role-based agent framework supports heterogeneous trading strategies and multi-agent coordination, making StockSim a uniquely capable testbed for NLP research on reasoning under uncertainty and sequential decision-making. We open-source all our code at https: //github.com/harrypapa2002/StockSim.

Large language models (LLMs) often develop learned mechanisms specialized to specific datasets, such as reliance on domain-specific correlations, which yield high-confidence predictions without generalizable reasoning. While beneficial in one setting, these dataset-specific mechanisms typically degrade performance when models encounter novel tasks or distributions. In this work, we introduce a fine-tuning approach designed to enhance generalization by identifying and pruning neurons associated with dataset-specific mechanisms in transformer-based LLMs. Our method employs Integrated Gradients to quantify each neuron's influence on high-confidence predictions, pinpointing those that disproportionately contribute to dataset-specific performance without supporting robust, transferable reasoning. Selectively pruning these neurons compels the model to depend on generalizable representations. Evaluated across multiple-choice benchmarks, our pruning-based fine-tuning significantly enhances performance, surpassing prior (non-pruning) adaptation methods.

This work presents OPENXRD, an open-book pipeline designed for crystallography question answering, which integrates textual prompts with concise supporting content generated by GPT-4.5. Instead of using scanned textbooks, which may lead to copyright issues, OPENXRD generates compact, domain-specific references that help smaller models understand key concepts in X-ray diffraction (XRD). We evaluate OPENXRD on a well-defined set of 217 expert-level XRD questions by comparing different vision-language models, including GPT-4 and LLaVA-based frameworks such as Mistral, LLaMA, and QWEN, under both closed-book (without supporting material) and open-book (with supporting material) conditions. Our experimental results show significant accuracy improvements in models that use the GPT-4.5-generated summaries, particularly those with limited prior training in crystallography. OPENXRD uses knowledge from larger models to fill knowledge gaps in crystallography and shows that AI-generated texts can help smaller models reason more effectively in scientific tasks. While the current version of OPENXRD focuses on text-based inputs, we also explore future extensions such as adding real crystal diagrams or diffraction patterns to improve interpretation in specialized materials science contexts. Overall, OPENXRD shows that specialized open-book systems can be useful in materials science and provides a foundation for broader natural language processing (NLP) tools in critical scientific fields.

This paper addresses emerging system-level challenges in heterogeneous retrieval-augmented generation (RAG) serving, where complex multi-stage workflows and diverse request patterns complicate efficient execution. We present HedraRAG, a runtime system built on a graph-based abstraction that exposes optimization opportunities across stage-level parallelism, intra-request similarity, and inter-request skewness. These opportunities are realized through dynamic graph transformations, such as node splitting, reordering, edge addition, and dependency rewiring, applied to wavefronts of subgraphs spanning concurrent requests. The resulting execution plans are mapped onto hybrid CPU-GPU pipelines to improve resource utilization and reduce latency. Evaluations across a wide range of RAG workflows demonstrate speedups exceeding 1.5x and reaching up to 5x over existing frameworks, showcasing the effectiveness of coordinated generation and retrieval in serving environments.

Recently, the role of LLM-as-judge in evaluating large language models has gained prominence. However, current judge models suffer from narrow specialization and limited robustness, undermining their capacity for comprehensive evaluations. In this work, we present CompassJudger-2, a novel generalist judge model that overcomes these limitations via a task-driven, multi-domain data curation strategy. Central to our approach is supervising judgment tasks with verifiable rewards, guiding intrinsic critical reasoning through rejection sampling to foster robust, generalizable judgment capabilities. We introduce a refined learning objective with margin policy gradient loss to enhance performance. Empirically, CompassJudger-2 achieves superior results across multiple judge and reward benchmarks, and our 7B model demonstrates competitive judgment accuracy with significantly larger models like DeepSeek-V3 and Qwen3-235B-A22B. Additionally, we propose JudgerBenchV2, a comprehensive benchmark evaluating cross-domain judgment accuracy and rank consistency to standardize judge model evaluation. These contributions advance robust, scalable LLM judgment and establish new performance and evaluation standards.

In decision-making conversations, experts must navigate complex choices and make on-the-spot decisions while engaged in conversation. Although extensive historical data often exists, the real-time nature of these scenarios makes it infeasible for decision-makers to review and leverage relevant information. This raises an interesting question: What if experts could utilize relevant past data in real-time decision-making through insights derived from past data? To explore this, we implemented a conversational user interface, taking doctor-patient interactions as an example use case. Our system continuously listens to the conversation, identifies patient problems and doctor-suggested solutions, and retrieves related data from an embedded dataset, generating concise insights using a pipeline built around a retrieval-based Large Language Model (LLM) agent. We evaluated the prototype by embedding Health Canada datasets into a vector database and conducting simulated studies using sample doctor-patient dialogues, showing effectiveness but also challenges, setting directions for the next steps of our work.

Recent advancements in reasoning-based Large Language Models (LLMs), particularly their potential through test-time scaling, have created significant opportunities for distillation in code generation and critique. However, progress in both areas fundamentally depends on large-scale, high-quality datasets. In this work, we introduce OpenCodeReasoning-II, a dataset consists of 2.5M question-solution-critique triples (approx. 35K unique programming questions), making it nearly twice the size of the previous largest publicly available code reasoning dataset. In this work, we employ a two-stage supervised fine-tuning strategy. The first stage focuses on fine-tuning for code generation, while the second stage involves the joint training of models for both code generation and critique. Our resulting finetuned Qwen2.5-Instruct models achieve performance in code generation that either exceeds or equals the best prior open-weight distilled models. Notably, the integration of our code generation and critique models leads to significant improvements in competitive coding performance. Furthermore, we present an extension of the LiveCodeBench benchmark to specifically support the C++ programming language, thereby facilitating more comprehensive LLM evaluation using this benchmark.