Indias e-commerce market is projected to grow rapidly, with last-mile delivery accounting for nearly half of operational expenses. Although vehicle routing problem (VRP) based solvers are widely used for delivery planning, their effectiveness in real-world scenarios is limited due to unstructured addresses, incomplete maps, and computational constraints in distance estimation. This study proposes a framework that employs large language models (LLMs) to critique VRP-generated routes against policy-based criteria, allowing logistics operators to evaluate and prioritise more efficient delivery plans. As a illustration of our approach we generate, annotate and evaluated 400 cases using large language models. Our study found that open-source LLMs identified routing issues with 79% accuracy, while proprietary reasoning models achieved reach upto 86%. The results demonstrate that LLM-based evaluation of VRP-generated routes can be an effective and scalable layer of evaluation which goes beyond beyond conventional distance and time based metrics. This has implications for improving cost efficiency, delivery reliability, and sustainability in last-mile logistics, especially for developing countries like India.

Modern software development teams rely heavily on issue tracking systems such as JIRA and collaborative platforms like GitHub to manage feature requests, bug reports, and code changes. However, as projects scale, the volume of tickets, developer comments, and associated pull requests (PRs) grows exponentially, leading to information overload. Developers often spend significant time searching for past resolutions of similar issues, interpreting scattered conversations, and understanding linked code changes. Prior research has shown that machine learning techniques can aid in bug classification and triage [1], yet such approaches often fall short when handling the semantic variability in real-world bug reports. For instance, a bug describing "UI crash when toggling feature flags in React 19" might not be directly matched with an earlier issue phrased as "application freeze due to concurrent rendering," even though the root cause overlaps, reflecting broader challenges in applying traditional supervised methods to complex, evolving enterprise data [2]. To address this gap, we propose a Retrieval-Augmented Generation (RAG) framework that combines semantic retrieval with context-aware language models for ticket resolution. RAG has been shown to reduce hallucinations and improve factual accuracy by grounding model outputs in retrieved evidence [3], making it well-suited for enterprise contexts where precision and reliability are critical. Our system leverages Sentence-Transformers to create embeddings of JIRA tickets, user comments, and PR descriptions, FAISS (Facebook AI Similarity Search) to perform efficient approximate nearest neighbor (ANN) search across a large corpus of tickets and code metadata, and a Large Language Model (LLM) decoder that synthesizes retrieved evidence into grounded, context-rich resolution suggestions. This approach demonstrates how resolution latency can be reduced, organizational knowledge reuse improved, and duplicate engineering effort minimized, while incorporating linked PR information to provide actionable code-change insights that guided past fixes.

Code generation models based on large language models (LLMs) have gained wide adoption, but challenges remain in ensuring safety, accuracy, and controllability, especially for complex tasks. Existing methods often lack dynamic integration of external tools, transparent reasoning, and user control over safety. To address these issues, we propose a controllable code generation framework utilizing the ReAct paradigm for multi-agent task execution. This framework is a multi-agent system designed to enable efficient, precise, and interpretable code generation through dynamic interactions between LLMs and external resources. The framework adopts a collaborative architecture comprising four specialized agents: a Planner for task decomposition, a Searcher that leverages the ReAct framework for reasoning and tool integration, a CodeGen agent for accurate code generation, and an Extractor for structured data retrieval. The ReAct-based Searcher alternates between generating reasoning traces and executing actions, facilitating seamless integration of internal knowledge with external tools (such as search engines) to enhance accuracy and user control. Experimental results show the framework's effectiveness across multiple languages, achieving a 94.8% security rate on the SVEN dataset with CodeQL, outperforming existing approaches. Its transparent reasoning process fosters user trust and improves controllability.

Recent research demonstrates that linear models achieve forecasting performance competitive with complex architectures, yet methodologies for enhancing linear models remain underexplored. Motivated by the hypothesis that distinct time series instances may follow heterogeneous linear mappings, we propose the Classification Auxiliary Trend-Seasonal Decoupling Linear Model CATS-Linear, employing Classification Auxiliary Channel-Independence (CACI). CACI dynamically routes instances to dedicated predictors via classification, enabling supervised channel design. We further analyze the theoretical expected risks of different channel settings. Additionally, we redesign the trend-seasonal decomposition architecture by adding a decoupling -- linear mapping -- recoupling framework for trend components and complex-domain linear projections for seasonal components. Extensive experiments validate that CATS-Linear with fixed hyperparameters achieves state-of-the-art accuracy comparable to hyperparameter-tuned baselines while delivering SOTA accuracy against fixed-hyperparameter counterparts.

Real-world time series are influenced by numerous factors and exhibit complex non-stationary characteristics. Non-stationarity can lead to distribution shifts, where the statistical properties of time series change over time, negatively impacting model performance. Several instance normalization techniques have been proposed to address distribution shifts in time series forecasting. However, existing methods fail to account for shifts within individual instances, leading to suboptimal performance. To tackle inner-instance distribution shifts, we propose two novel point-level methods: Learning Distribution (LD) and Learning Conditional Distribution (LCD). LD eliminates internal discrepancies by fitting the internal distribution of input and output with different parameters at different time steps, while LCD utilizes neural networks to predict scaling coefficients of the output. We evaluate the performance of the two methods with various backbone models across public benchmarks and demonstrate the effectiveness of the point-level paradigm through comparative experiments.

Large language models can change answers under harmless edits that matter in practice: RAG outputs flip when passages are reordered, fine-tuning erodes invariances learned at pretraining, debate or chain-of-thought prompts take path-dependent routes, and compiler fusion or reordering perturbs logits near decision boundaries. These failures violate intended invariances, break continuous integration, and force teams to trade safety for speed. The effects are small yet distributed across layers and positions, sensitive to context length and evaluation order, and costly to repair with retraining or formal verification. We present WILSON, a minimal post-hoc diagnostic suite that converts simple loop and reordering checks on internal representations into system signals. WILSON combines an inverse-free curvature map over positions and layers, computed with JVPs and Hutchinson probes, with activation-level commutators that flag reorder risk. Signals are cheap to compute, model-agnostic for standard Transformers, and exported as thresholds and CSV artifacts for orchestrators. This enables concrete actions: guard RAG against order effects, catch fine-tuning regressions, stabilize debate pathways and long multi-turn contexts, and gate fusions or reorders in deployment. In short, WILSON helps anticipate failures and approve safe optimizations so reliability and throughput can improve together without changing model architecture or training.

Recent developments have enabled advanced reasoning in Large Language Models (LLMs) via long Chain-of-Thought (CoT), while long CoT suffers from high computational costs and significant latency losses owing to the autoregressive nature of generative LLMs. CoT compression aims to improve efficiency in the reasoning process by reducing output length. Previous works trade reasoning efficiency by either laborious discrete prompt designing or the construction of external compressed CoT datasets that sacrifice key reasoning details. In this work, we propose Upfront CoT (UCoT): an efficient reasoning framework with upfront thought embedding to automate CoT compression. UCoT is a cooperative workflow involving a small model (compressor) and a large model (executor). The first stage of UCoT trains compressor to generate upfront thought embeddings rich in reasoning information for the executor, avoiding the drawbacks of manually designed prompts. The second stage optimizes executor to utilize upfront thought embeddings to derive the correct answer with short reasoning, using a reward mechanism. Extensive experiments show that UCoT maintains the powerful reasoning ability of executor while significantly reducing the length of CoT. It is worth mentioning that when applying UCoT to the Qwen2.5-7B-Instruct model, the usage of tokens on GSM8K dataset is reduced by 50\%, while the performance is 3.08\% higher than that of the state-of-the-art (SOTA) method. The code and dataset are in supplementary material.

DINOv2 is routinely deployed to recognize objects, scenes, and actions; yet the nature of what it perceives remains unknown. As a working baseline, we adopt the Linear Representation Hypothesis (LRH) and operationalize it using SAEs, producing a 32,000-unit dictionary that serves as the interpretability backbone of our study, which unfolds in three parts. In the first part, we analyze how different downstream tasks recruit concepts from our learned dictionary, revealing functional specialization: classification exploits "Elsewhere" concepts that fire everywhere except on target objects, implementing learned negations; segmentation relies on boundary detectors forming coherent subspaces; depth estimation draws on three distinct monocular depth cues matching visual neuroscience principles. Following these functional results, we analyze the geometry and statistics of the concepts learned by the SAE. We found that representations are partly dense rather than strictly sparse. The dictionary evolves toward greater coherence and departs from maximally orthogonal ideals (Grassmannian frames). Within an image, tokens occupy a low dimensional, locally connected set persisting after removing position. These signs suggest representations are organized beyond linear sparsity alone. Synthesizing these observations, we propose a refined view: tokens are formed by combining convex mixtures of archetypes (e.g., a rabbit among animals, brown among colors, fluffy among textures). This structure is grounded in Gardenfors' conceptual spaces and in the model's mechanism as multi-head attention produces sums of convex mixtures, defining regions bounded by archetypes. We introduce the Minkowski Representation Hypothesis (MRH) and examine its empirical signatures and implications for interpreting vision-transformer representations.

In addition to accurate scene understanding through precise semantic segmentation of LiDAR point clouds, detecting out-of-distribution (OOD) objects, instances not encountered during training, is essential to prevent the incorrect assignment of unknown objects to known classes. While supervised OOD detection methods depend on auxiliary OOD datasets, unsupervised methods avoid this requirement but typically rely on predictive entropy, the entropy of the predictive distribution obtained by averaging over an ensemble or multiple posterior weight samples. However, these methods often conflate epistemic (model) and aleatoric (data) uncertainties, misclassifying ambiguous in distribution regions as OOD. To address this issue, we present an unsupervised OOD detection approach that employs epistemic uncertainty derived from hierarchical Bayesian modeling of Gaussian Mixture Model (GMM) parameters in the feature space of a deep neural network. Without requiring auxiliary data or additional training stages, our approach outperforms existing uncertainty-based methods on the SemanticKITTI dataset, achieving an 18\% improvement in AUROC, 22\% increase in AUPRC, and 36\% reduction in FPR95 (from 76\% to 40\%), compared to the predictive entropy approach used in prior works.

Benchmarks for large language models (LLMs) often rely on rubric-scented prompts that request visible reasoning and strict formatting, whereas real deployments demand terse, contract-bound answers. We investigate whether such "evaluation scent" inflates measured performance without commensurate capability gains. Using a single open-weights model (GPT-OSS-20B), we run six paired A/B scenarios that hold task content and decoding fixed while varying framing (evaluation-oriented vs. real-world) and reasoning depth (Medium/High): deterministic math, strict code-fix, citation generation, incentive flips (caution vs. competence), CoT visibility, and multilingual (Urdu) headers. Deterministic validators compute accuracy, answer-only compliance, hedging/refusals, chain-of-thought (CoT) length, and schema compliance, with pre-registered deltas and composite indices. Across scenarios, evaluation framing reliably inflates CoT (hundreds to >1000 characters) and reduces answer-only compliance, with limited or inconsistent accuracy gains. In structured outputs, it improves wrappers (e.g., fenced blocks, enumerated lists) but not regex-validated substance. Incentive wording reweights error composition: praising caution modestly improves accuracy at high reasoning and reduces wrong-but-confident errors, whereas praising competence yields terser but riskier outputs. Urdu rubric headers reproduce these signatures and can decrease accuracy at higher reasoning depth, indicating multilingual parity risks. We provide a reproducible A/B framework (prompt banks, validators, per-run scores, scripts; versioned DOI) and practical guidance: neutral phrasing or dual-framing checks, contract-aware grading, style-delta reporting, confidence governance, and multilingual dashboards to ensure that benchmark gains reflect deployable capability.