The extent to which decoder-only language models (LMs) engage in planning, that is, organizing intermediate computations to support coherent long-range generation, remains an open and important question, with implications for interpretability, reliability, and principled model design. Planning involves structuring computations over long horizons, considering multiple possible continuations, and selectively reusing past information, but how effectively transformer-based LMs realize these capabilities is still unclear. We address these questions by analyzing the hidden states at the core of transformer computations, which capture intermediate results and act as carriers of information. Since these hidden representations are often redundant and encumbered with fine-grained details, we develop a pipeline based on vector-quantized variational autoencoders that compresses them into compact summary codes. These codes enable measuring mutual information, allowing systematic analysis of the computational structure underlying model behavior. Using this framework, we study planning in LMs across synthetic grammar, path-finding tasks, and natural language datasets, focusing on three key aspects: (i) the planning horizon of pre-output computations, (ii) the extent to which the model considers alternative valid continuations, and (iii) the reliance of new predictions on earlier computations. By answering these questions, we advance the understanding of how planning is realized in LMs and contribute a general-purpose pipeline for probing the internal dynamics of LMs and deep learning systems. Our results reveal that the effective planning horizon is task-dependent, that models implicitly preserve information about unused correct continuations, and that predictions draw most on recent computations, though earlier blocks remain informative.

Practical lab education in computer science often faces challenges such as plagiarism, lack of proper lab records, unstructured lab conduction, inadequate execution and assessment, limited practical learning, low student engagement, and absence of progress tracking for both students and faculties, resulting in graduates with insufficient hands-on skills. In this paper, we introduce AsseslyAI, which addresses these challenges through online lab allocation, a unique lab problem for each student, AI-proctored viva evaluations, and gamified simulators to enhance engagement and conceptual mastery. While existing platforms generate questions based on topics, our framework fine-tunes on a 10k+ question-answer dataset built from AI/ML lab questions to dynamically generate diverse, code-rich assessments. Validation metrics show high question-answer similarity, ensuring accurate answers and non-repetitive questions. By unifying dataset-driven question generation, adaptive difficulty, plagiarism resistance, and evaluation in a single pipeline, our framework advances beyond traditional automated grading tools and offers a scalable path to produce genuinely skilled graduates.

Abstract--LLMs demonstrate surface-level fluency in code generation but struggle with structured reasoning tasks requiring correctness and semantic alignment. While Chain-of-Thought (CoT) prompting enhances reasoning through intermediate steps, it suffers from verbosity and inefficiency. Chain-of-Draft (CoD) prompting offers more concise reasoning, but the stochastic nature of LLMs produces varying solution quality, making optimal selection challenging. D, a reinforcement learning framework that learns to select the most promising candidate from CoD-generated solutions. Our approach uses strategy-guided prompting to encourage diverse reasoning styles and models solution selection as a contextual bandit problem. D outperforms and in some cases, on par with standard prompting, CoT, and CoD baselines while achieving cost and token efficiency from the user's perspective through a multi-candidate design that charges only for the selected output, reducing user billing by over 50% and improving LLM response quality, making M Large language models (LLMs) have become powerful tools for automating software engineering tasks, including code completion and program repair. Despite their fluency and generalization capabilities, LLMs often produce brittle or incorrect code, especially in tasks that require multi-step reasoning or nuanced understanding of program semantics. This limitation stems from the fact that most LLMs generate code in a single forward pass, without explicitly modeling the reasoning process that underlies correct and efficient solutions. To address this, recent work has explored Chain-of-Thought (CoT) prompting [1], which encourages LLMs to generate intermediate reasoning steps before producing a final answer. Originally developed for arithmetic and symbolic reasoning tasks, CoT has been adapted to code-related domains to improve correctness [2]-[6].

Accurate project localization (e.g., files and functions) for issue resolution is a critical first step in software maintenance. However, existing benchmarks for issue localization, such as SWE-Bench and LocBench, are limited. They focus predominantly on pull-request issues and code locations, ignoring other evidence and non-code files such as commits, comments, configurations, and documentation. To address this gap, we introduce MULocBench, a comprehensive dataset of 1,100 issues from 46 popular GitHub Python projects. Comparing with existing benchmarks, MULocBench offers greater diversity in issue types, root causes, location scopes, and file types, providing a more realistic testbed for evaluation. Using this benchmark, we assess the performance of state-of-the-art localization methods and five LLM-based prompting strategies. Our results reveal significant limitations in current techniques: even at the file level, performance metrics (Acc@5, F1) remain below 40%. This underscores the challenge of generalizing to realistic, multi-faceted issue resolution. Modern software projects are inherently complex. They often consist of thousands of files spanning code, configurations, tests, and documentation. The complexity making developers routinely encounter a wide spectrum of issues, ranging from runtime failures and unexpected results to enhancement requests and usage questions. A prerequisite for resolving these issues is to accurately identify the locations, such as the relevant files and functions. Existing benchmarks have advanced research on issue localization. SWE-Bench Jimenez et al. collects 2,294 issues with pull requests from 12 Python projects, primarily targeting bug fixing. To encourage adoption, it releases SWE-bench Lite, a subset of 300 instances.

Recent advancements in training paradigms for Large Language Models (LLMs) have unlocked their remarkable capabilities in natural language processing and cross-domain generalization. While LLMs excel in tasks like programming and mathematical problem-solving, their zero-shot performance in specialized domains requiring expert knowledge, such as cybersecurity, is often suboptimal. This limitation arises because foundational LLMs are designed for general-purpose applications, constraining their ability to encapsulate domain-specific expertise within their parameter space. To address this, we explore fine-tuning strategies to embed cybersecurity knowledge into LLMs, enhancing their performance in cybersecurity question-answering (Q\&A) tasks while prioritizing computational efficiency. Specifically, we investigate Supervised Fine-Tuning (SFT), Low-Rank Adaptation (LoRA), and Quantized Low-Rank Adaptation (QLoRA) using a cybersecurity Q\&A dataset. Our results demonstrate that these fine-tuning approaches significantly outperform the foundational model in cybersecurity Q\&A tasks. Moreover, LoRA and QLoRA achieve comparable performance to SFT with substantially lower computational costs, offering an efficient pathway for adapting LLMs to specialized domains. Our work highlights the potential of low-rank fine-tuning strategies to bridge the gap between general-purpose LLMs and domain-specific applications.

Recent curriculum reinforcement learning for large language models (LLMs) typically rely on difficulty-based annotations for data filtering and ordering. However, such methods suffer from local optimization, where continual training on simple samples in the early steps can cause the policy to lose its exploration. We propose a novel schema, namely Hamiltonian curiosity augmented large language model reinforcement (HAMMER), that transfers diversity metrics, commonly used in dataset evaluation, into the dynamic reinforcement learning procedure, where training samples are ordered via a minimum-semantic Hamiltonian path making the initial training retrain more exploration. From a theoretical perspective of generalization bounds, diversity-driven ordering facilitates stable convergence. Empirical evaluations indicate that HAMMER stimulates model "curiosity" and consistently achieves a 3% to 4% average accuracy gain across diverse inference benchmark.

Tool-augmented language agents frequently fail in real-world deployment due to tool malfunctions--timeouts, API exceptions, or inconsistent outputs--triggering cascading reasoning errors and task abandonment. Existing agent training pipelines optimize only for success trajectories, failing to expose models to the tool failures that dominate real-world usage. We propose \textbf{PALADIN}, a generalizable framework for equipping language agents with robust failure recovery capabilities. PALADIN trains on 50,000+ recovery-annotated trajectories constructed via systematic failure injection and expert demonstrations on an enhanced ToolBench dataset. Training uses LoRA-based fine-tuning to retain base capabilities while injecting recovery competence. At inference, PALADIN detects execution-time errors and retrieves the most similar case from a curated bank of 55+ failure exemplars aligned with ToolScan's taxonomy, then executes the corresponding recovery action. This approach generalizes to novel failures beyond the training distribution, retaining 95.2\% recovery performance on unseen tool APIs. Evaluation across PaladinEval and ToolReflectEval demonstrates consistent improvements in Recovery Rate (RR), Task Success Rate (TSR), Catastrophic Success Rate (CSR), and Efficiency Score (ES). PALADIN improves RR from 32.76% to 89.68% (+57% relative) over ToolBench and outperforms the strongest baseline CRITIC (76.34%) by +13.3%. Against vanilla agents, PALADIN achieves 89.86\% RR (+66% relative improvement from 23.75%). These results establish PALADIN as an effective method for building fault-tolerant agents capable of robust recovery in real-world tool environments.

Time series forecasting has various applications, such as meteorological rainfall prediction, traffic flow analysis, financial forecasting, and operational load monitoring for various systems. Due to the sparsity of time series data, relying solely on time-domain or frequency-domain modeling limits the model's ability to fully leverage multi-domain information. Moreover, when applied to time series forecasting tasks, traditional attention mechanisms tend to over-focus on irrelevant historical information, which may introduce noise into the prediction process, leading to biased results. We proposed WDformer, a wavelet-based differential Transformer model. This study employs the wavelet transform to conduct a multi-resolution analysis of time series data. By leveraging the advantages of joint representation in the time-frequency domain, it accurately extracts the key information components that reflect the essential characteristics of the data. Furthermore, we apply attention mechanisms on inverted dimensions, allowing the attention mechanism to capture relationships between multiple variables. When performing attention calculations, we introduced the differential attention mechanism, which computes the attention score by taking the difference between two separate softmax attention matrices. This approach enables the model to focus more on important information and reduce noise. WDformer has achieved state-of-the-art (SOTA) results on multiple challenging real-world datasets, demonstrating its accuracy and effectiveness. Code is available at https://github.com/xiaowangbc/WDformer.

We introduce Blueprint-Bench, a benchmark designed to evaluate spatial reasoning capabilities in AI models through the task of converting apartment photographs into accurate 2D floor plans. While the input modality (photographs) is well within the training distribution of modern multimodal models, the task of spatial reconstruction requires genuine spatial intelligence: inferring room layouts, understanding connectivity, and maintaining consistent scale. We evaluate leading language models (GPT-5, Claude 4 Opus, Gemini 2.5 Pro, Grok-4), image generation models (GPT-Image, NanoBanana), and agent systems (Codex CLI, Claude Code) on a dataset of 50 apartments with approximately 20 interior images each. Our scoring algorithm measures similarity between generated and ground-truth floor plans based on room connectivity graphs and size rankings. Results reveal a significant blind spot in current AI capabilities: most models perform at or below a random baseline, while human performance remains substantially superior. Image generation models particularly struggle with instruction following, while agent-based approaches with iterative refinement capabilities show no meaningful improvement over single-pass generation. Blueprint-Bench provides the first numerical framework for comparing spatial intelligence across different model architectures. We will continue evaluating new models as they are released and welcome community submissions, monitoring for the emergence of spatial intelligence in generalist AI systems.

Integrated wind-solar-wave marine energy systems hold broad promise for supplying clean electricity in offshore and coastal regions. By leveraging the spatiotemporal complementarity of multiple resources, such systems can effectively mitigate the intermittency and volatility of single-source outputs, thereby substantially improving overall power-generation efficiency and resource utilization. Accurate ultra-short-term forecasting is crucial for ensuring secure operation and optimizing proactive dispatch. However, most existing forecasting methods construct separate models for each energy source, insufficiently account for the complex couplings among multiple energies, struggle to capture the system's nonlinear and nonstationary dynamics, and typically depend on extensive manual parameter tuning-limitations that constrain both predictive performance and practicality. We address this issue using a Bayesian-optimized Multivariate Variational Mode Decomposition-Long Short-Term Memory (MVMD-LSTM) framework. The framework first applies MVMD to jointly decompose wind, solar and wave power series so as to preserve cross-source couplings; it uses Bayesian optimization to automatically search the number of modes and the penalty parameter in the MVMD process to obtain intrinsic mode functions (IMFs); finally, an LSTM models the resulting IMFs to achieve ultra-short-term power forecasting for the integrated system. Experiments based on field measurements from an offshore integrated energy platform in China show that the proposed framework significantly outperforms benchmark models in terms of MAPE, RMSE and MAE. The results demonstrate superior predictive accuracy, robustness, and degree of automation.