While Large Language Models (LLMs) are increasingly applied in student-facing educational tools, their potential to directly support educators through locally deployable and customizable solutions remains underexplored. Many existing approaches rely on proprietary, cloud-based systems that raise significant cost, privacy, and control concerns for educational institutions. To address these barriers, we introduce an end-to-end, open-source framework that empowers educators using small (3B-7B parameter), locally deployable LLMs. Our system is designed for comprehensive teacher support, including customized teaching material generation and AI-assisted assessment. The framework synergistically combines Retrieval-Augmented Generation (RAG) and Context-Augmented Generation (CAG) to produce factually accurate, pedagogically-styled content. A core feature is an interactive refinement loop, a teacher-in-the-loop mechanism that ensures educator agency and precise alignment of the final output. To enhance reliability and safety, an auxiliary verifier LLM inspects all generated content. We validate our framework through a rigorous evaluation of its content generation capabilities and report on a successful technical deployment in a college physics course, which confirms its feasibility on standard institutional hardware. Our findings demonstrate that carefully engineered, self-hosted systems built on small LLMs can provide robust, affordable, and private support for educators, achieving practical utility comparable to much larger models for targeted instructional tasks. This work presents a practical blueprint for the development of sovereign AI tools tailored to the real-world needs of educational institutions.

Table-based question answering requires complex reasoning capabilities that current LLMs struggle to achieve with single-pass inference. Existing approaches, such as Chain-of-Thought reasoning and question decomposition, lack error detection mechanisms and discard problem-solving experiences, contrasting sharply with how humans tackle such problems. In this paper, we propose MAPLE (Multi-agent Adaptive Planning with Long-term mEmory), a novel framework that mimics human problem-solving through specialized cognitive agents working in a feedback-driven loop. MAPLE integrates 4 key components: (1) a Solver using the ReAct paradigm for reasoning, (2) a Checker for answer verification, (3) a Reflector for error diagnosis and strategy correction, and (4) an Archiver managing long-term memory for experience reuse and evolution. Experiments on WiKiTQ and TabFact demonstrate significant improvements over existing methods, achieving state-of-the-art performance across multiple LLM backbones.

Large Reasoning Models (LRMs) extend large language models with explicit, multi-step reasoning traces to enhance transparency and performance on complex tasks. However, these reasoning traces can be redundant or logically inconsistent, becoming a new and hard-to-detect source of hallucination. Existing hallucination detection methods focus primarily on answer-level uncertainty and often fail to detect hallucinations or logical inconsistencies arising from the model's reasoning trace. This oversight is particularly problematic for LRMs, where the explicit thinking trace is not only an important support to the model's decision-making process but also a key source of potential hallucination. To this end, we propose RACE (Reasoning and Answer Consistency Evaluation), a novel framework specifically tailored for hallucination detection in LRMs. RACE operates by extracting essential reasoning steps and computing four diagnostic signals: inter-sample consistency of reasoning traces, entropy-based answer uncertainty, semantic alignment between reasoning and answers, and internal coherence of reasoning. The joint utilization of these signals makes RACE a more robust detector of hallucinations in LRMs. Experiments across datasets and different LLMs demonstrate that RACE outperforms existing hallucination detection baselines, offering a robust and generalizable solution for evaluating LRMs. The source code is available at https://github.com/bebr2/RACE

Language models have demonstrated remarkable capabilities in reasoning tasks through test-time scaling techniques like best-of-N sampling and tree search. However, these approaches often demand substantial computational resources, creating a critical trade-off between performance and efficiency. We introduce STAND (STochastic Adaptive N-gram Drafting), a novel model-free speculative decoding approach that exploits the inherent redundancy in reasoning trajectories to achieve significant acceleration without compromising accuracy. Our analysis shows that reasoning paths frequently reuse similar reasoning patterns, enabling efficient model-free token prediction without requiring separate draft models. By introducing stochastic drafting and preserving probabilistic information through a memory-efficient logit-based N-gram module, combined with optimized Gumbel-Top-K sampling and data-driven tree construction, STAND significantly improves token acceptance rates. Extensive evaluations across multiple models and reasoning tasks (AIME-2024, GPQA-Diamond, and LiveCodeBench) demonstrate that STAND reduces inference latency by 60-65% compared to standard autoregressive decoding while maintaining accuracy. Furthermore, STAND consistently outperforms state-of-the-art speculative decoding methods across diverse inference patterns, including single-trajectory decoding, batch decoding, and test-time tree search. As a model-free approach, STAND can be applied to any existing language model without additional training, making it a powerful plug-and-play solution for accelerating language model reasoning.

In recent years, Multimodal Large Language Models (MLLMs) have been extensively utilized for multimodal reasoning tasks, including Graphical User Interface (GUI) automation. Unlike general offline multimodal tasks, GUI automation is executed in online interactive environments, necessitating step-by-step decision-making based on real-time status of the environment. This task has a lower tolerance for decision-making errors at each step, as any mistakes may cumulatively disrupt the process and potentially lead to irreversible outcomes like deletions or payments. To address these issues, we introduce a pre-operative critic mechanism that provides effective feedback prior to the actual execution, by reasoning about the potential outcome and correctness of actions. Specifically, we propose a Suggestion-aware Gradient Relative Policy Optimization (S-GRPO) strategy to construct our pre-operative critic model GUI-Critic-R1, incorporating a novel suggestion reward to enhance the reliability of the model's feedback. Furthermore, we develop a reasoning-bootstrapping based data collection pipeline to create a GUI-Critic-Train and a GUI-Critic-Test, filling existing gaps in GUI critic data. Static experiments on the GUI-Critic-Test across both mobile and web domains reveal that our GUI-Critic-R1 offers significant advantages in critic accuracy compared to current MLLMs. Dynamic evaluation on GUI automation benchmark further highlights the effectiveness and superiority of our model, as evidenced by improved success rates and operational efficiency.

As large language models increasingly gain popularity in real-world applications, processing extremely long contexts, often exceeding the model's pre-trained context limits, has emerged as a critical challenge. While existing approaches to efficient long-context processing show promise, recurrent compression-based methods struggle with information preservation, whereas random access approaches require substantial memory resources. We introduce REFORM, a novel inference framework that efficiently handles long contexts through a two-phase approach. First, it incrementally processes input chunks while maintaining a compressed KV cache, constructs cross-layer context embeddings, and utilizes early exit strategy for improved efficiency. Second, it identifies and gathers essential tokens via similarity matching and selectively recomputes the KV cache. Compared to baselines, REFORM achieves over 52% and 34% performance gains on RULER and BABILong respectively at 1M context length. It also outperforms baselines on Infinite-Bench, RepoEval, and MM-NIAH, demonstrating flexibility across diverse tasks and domains. Additionally, REFORM reduces inference time by 30% and peak memory usage by 5%, achieving both efficiency and superior performance.

Recent advances in Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in solving complex tasks such as mathematics and coding. However, these models frequently exhibit a phenomenon known as overthinking during inference, characterized by excessive validation loops and redundant deliberation, leading to substantial computational overheads. In this paper, we aim to mitigate overthinking by investigating the underlying mechanisms from the perspective of mechanistic interpretability. We first showcase that the tendency of overthinking can be effectively captured by a single direction in the model's activation space and the issue can be eased by intervening the activations along this direction. However, this efficacy soon reaches a plateau and even deteriorates as the intervention strength increases. We therefore systematically explore the activation space and find that the overthinking phenomenon is actually tied to a low-dimensional manifold, which indicates that the limited effect stems from the noises introduced by the high-dimensional steering direction. Based on this insight, we propose Manifold Steering, a novel approach that elegantly projects the steering direction onto the low-dimensional activation manifold given the theoretical approximation of the interference noise. Extensive experiments on DeepSeek-R1 distilled models validate that our method reduces output tokens by up to 71% while maintaining and even improving the accuracy on several mathematical benchmarks. Our method also exhibits robust cross-domain transferability, delivering consistent token reduction performance in code generation and knowledge-based QA tasks. Code is available at: https://github.com/Aries-iai/Manifold_Steering.

Large language models (LLMs) rely on key-value cache (KV cache) to accelerate decoding by reducing redundant computations. However, the KV cache memory usage grows substantially with longer text sequences, posing challenges for efficient deployment. Existing KV cache eviction methods prune tokens using prefilling-stage attention scores, causing inconsistency with actual inference queries, especially under tight memory budgets. In this paper, we propose Lookahead Q-Cache (LAQ), a novel eviction framework that generates low-cost pseudo lookahead queries to better approximate the true decoding-stage queries. By using these lookahead queries as the observation window for importance estimation, LAQ achieves more consistent and accurate KV cache eviction aligned with real inference scenarios. Experimental results on LongBench and Needle-in-a-Haystack benchmarks show that LAQ outperforms existing methods across various budget levels, achieving a 1 $\sim$ 4 point improvement on LongBench under limited cache budget. Moreover, LAQ is complementary to existing approaches and can be flexibly combined to yield further improvements.

We introduce SCRum-9, the largest multilingual Stance Classification dataset for Rumour analysis in 9 languages, containing 7,516 tweets from X. SCRum-9 goes beyond existing stance classification datasets by covering more languages, linking examples to more fact-checked claims (2.1k), and including confidence-related annotations from multiple annotators to account for intra- and inter-annotator variability. Annotations were made by at least two native speakers per language, totalling more than 405 hours of annotation and 8,150 dollars in compensation. Further, SCRum-9 is used to benchmark five large language models (LLMs) and two multilingual masked language models (MLMs) in In-Context Learning (ICL) and fine-tuning setups. This paper also innovates by exploring the use of multilingual synthetic data for rumour stance classification, showing that even LLMs with weak ICL performance can produce valuable synthetic data for fine-tuning small MLMs, enabling them to achieve higher performance than zero-shot ICL in LLMs. Finally, we examine the relationship between model predictions and human uncertainty on ambiguous cases finding that model predictions often match the second-choice labels assigned by annotators, rather than diverging entirely from human judgments. SCRum-9 is publicly released to the research community with potential to foster further research on multilingual analysis of misleading narratives on social media.

Optics is foundational to research in many areas of science and engineering, including nanophotonics, quantum information, materials science, biomedical imaging, and metrology. However, the design, assembly, and alignment of optical experiments remain predominantly manual, limiting throughput and reproducibility. Automating such experiments is challenging due to the strict, non-negotiable precision requirements and the diversity of optical configurations found in typical laboratories. Here, we introduce a platform that integrates generative artificial intelligence, computer vision, and robotics to automate free-space optical experiments. The platform translates user-defined goals into valid optical configurations, assembles them using a robotic arm, and performs micrometer-scale fine alignment using a robot-deployable tool. It then executes a range of automated measurements, including beam characterization, polarization mapping, and spectroscopy, with consistency surpassing that of human operators. This work demonstrates the first flexible, AI-driven automation platform for optics, offering a path towards remote operation, cloud labs, and high-throughput discovery in the optical sciences.