代码大模型 / AI 编程

Realistic coding-agent benchmarks often replay public GitHub issues and pull requests, making them vulnerable to overlap with model pretraining, fine-tuning, synthetic-data generation, or benchmark-driven model selection. Fully synthetic tasks avoid direct historical replay, but can drift away from real repository needs. We propose SWE-Future, a forecast-conditioned data synthesis method for future-oriented coding tasks. Given a forecast snapshot at time $T_0$, the method uses only pre-$T_0$ repository evidence to forecast future feature implementation/enhancement, bugfix, and refactor task families. We first validate this forecasting step retrospectively: after forecasts are fixed, later pull requests are used only to measure whether the predicted task families match future repository work. In an 80-repository study, the forecaster achieves 58.1\% future-work relevance under the main semantic matching metric. We then use validated forecast families as conditioning signals to synthesize a 200-task coding-agent dataset across 61 repositories from a task-generation snapshot, rather than replaying the later pull requests used for validation. SWE-Future shows that repository-evolution forecasts can guide realistic, future-oriented coding-task synthesis while reducing direct dependence on historical pull-request replay.

Coding agents are increasingly used to automate software engineering tasks. To guide their behavior, these agents commonly rely on configuration files, typically named AGENTS.‌md or CLAUDE.‌md, which provide instructions about architecture, workflows, coding conventions, and testing practices. Despite their growing importance, little is known about common problems affecting the definition and maintenance of these files. In this paper, we present the first catalog of smells for coding-agent configuration files. To identify such smells, we first conducted a grey literature review and a repository mining analysis. As a result, we identified six configuration smells and proposed automated heuristics to detect them. To evaluate the prevalence of the proposed smells, we analyzed 100 popular open-source repositories containing either an AGENTS.‌md or a CLAUDE.‌md file. Our results show that configuration smells are widespread. Lint Leakage was the most common smell, affecting 62% of the files, followed by Context Bloat (42%) and Skill Leakage (35%). We further show that several smells frequently co-occur, particularly Context Bloat, Skill Leakage, and Conflicting Instructions.

Repairing system crashes discovered by kernel fuzzers like Syzkaller is a critical yet underexplored challenge in software engineering. While recent works have introduced Large Language Model (LLM) based agents for Linux kernel crash-resolution, their evaluation benchmarks are usually static and thus, do not capture the evolving nature of the Linux kernel, and suffer from potential data contamination due to LLM knowledge cutoffs. To address the above problem, we present (i) Live-kBench, an evaluation framework for self-evolving benchmarks that continuously scrapes and evaluates agents on freshly discovered kernel bugs, and (ii) kEnv, an agent-agnostic standardized crash-resolution environment for kernel compilation, execution, and feedback. This design decouples agent workflows from heavy-weight execution, enabling fair and scalable comparison across diverse agent frameworks under identical conditions. To this end, we curate an inaugural dataset of 534 Linux kernel bugs and empirically demonstrate a significant performance gap, with agents achieving up to 25% higher equivalent patch rate on bugs fixed before the LLM knowledge cutoff. Using kEnv, we benchmark three state-of-the-art agents, showing that they resolve 74% of crashes on the first attempt (plausible patches); however only ~20% of generated patches closely match developer fixes. Additionally, exposing crash resolution feedback improves crash resolution rate by 29%. Live-kBench provides the community with an evaluation infrastructure for self-evolving benchmarks that is both time and attribute sensitive; complete with a public dashboard to track agent progress on Linux kernel bugs.

Conversational LLM-based ``programming assistants'' provide a range of benefits to developers. However, recent studies demonstrate the variety in individual developers' needs regarding programming assistants, and challenges encountered by only specific groups of developers. In this study, we explore the role of cognitive diversity in shaping interactions with GitHub Copilot chat. Through a mixed-methods think aloud study with 27 professional developers and students, we characterize 5 distinct ``interaction modes'' and 10 underlying needs in developers' interactions, forming a conceptual model. We characterize links between these modes, needs, and developers' problem-solving styles and experience profiles, showing how cognitive diversity may shape developers' interactions. We provide insights and recommendations for researchers and practitioners on how to design, research, and employ programming assistants to better account for diverse developer needs.

The rapid integration of Large Language Models (LLMs) and the Model Context Protocol (MCP) into industrial software engineering has created a pressing need to update software engineering education to align with emerging technologies and evolving industry demands. This study investigates an innovative approach that integrates LLMs and MCP into a collaborative teaching model for software engineering education, aiming to build a practical learning framework closely connected to real-world engineering practices. By embedding LLM and MCP driven tools into daily teaching, code assistance, and engineering simulations, the model effectively bridges the gap between traditional instruction and industrial workflows. This integration enhances students' programming competence, practical problem-solving abilities, and proficiency in using intelligent engineering tools. Furthermore, through partnerships with industry internships, students can apply these technologies in real-world settings, further strengthening the connection between academic preparation and professional practice. Overall, this research offers a practical pathway for reforming and innovating software engineering education in the era of artificial intelligence.

With the increasing complexity of large-scale software systems, identifying all necessary modifications for a specific change is challenging. Co-changed methods, which are methods frequently modified together, are crucial for understanding software dependencies. However, existing methods often produce large results with high false positives. Focusing on pull requests instead of individual commits provides a more comprehensive view of related changes, capturing essential co-change relationships. To address these challenges, we propose a learning-to-rank approach that combines source code features and change history to predict and rank co-changed methods at the pull-request level. Experiments on 150 open-source Java projects, totaling 41.5 million lines of code and 634,216 pull requests, show that the Random Forest model outperforms other models by 2.5 to 12.8 percent in NDCG@5. It also surpasses baselines such as file proximity, code clones, FCP2Vec, and StarCoder 2 by 4.7 to 537.5 percent. Models trained on longer historical data (90 to 180 days) perform consistently, while accuracy declines after 60 days, highlighting the need for bi-monthly retraining. This approach provides an effective tool for managing co-changed methods, enabling development teams to handle dependencies and maintain software quality.

Agent skills allow LLM-based coding agents to acquire domain-specific capabilities from third-party packages, but they also introduce a new supply-chain attack surface. We present PhantomSkill, an attack framework that hides malicious behavior in a skill's auxiliary resources rather than in its textual description. Its core technique, VulMask, rewrites overt malicious scripts into vulnerability-shaped implementations whose malicious behavior is activated only under attacker-controlled trigger conditions. This design shifts the visible signal from explicit malicious intent to ordinary-looking insecure code. Across representative host skills, attack goals, coding agents, generation models, and automated reviewers, VulMask preserves benign utility while reducing warning and malware-level detection compared with overt malicious scripts. Our results show that skill ecosystems require resource-level vetting, execution-time containment, and security policies that treat exploitable vulnerabilities in agent skills as potential malicious payloads.

This experience report presents a model-driven approach to legacy system modernization that inserts an enriched, technology-agnostic intermediate model between the legacy codebase and the modern target platform, and reports on its application and evaluation. The four-stage process of analysis, enrichment, synthesis, and transition systematically extracts, abstracts, and transforms system artifacts. We apply our approach to a large industrial application built on legacy versions of the .NET Framework and ASP.NET MVC and show that core user interface components and page structures can be migrated semi-automatically to a modern web stack while preserving functional behavior and essential non-functional qualities. By consolidating architectural knowledge into explicit model representations, the resulting codebase exhibits higher maintainability and extensibility, thereby improving developer experience. Although automation is effective for standard patterns, migration of bespoke layout composites remains challenging and requires targeted manual adaptation. Our contributions are: (i) an end-to-end model-driven process, (ii) an enriched intermediate model that captures structure, dependencies, and semantic metadata, (iii) transformation rules that preserve functional behavior and essential non-functional qualities, and (iv) application and evaluation of the approach in an industrial setting. Overall, model-based abstractions reduce risk and effort while supporting scalable, traceable modernization of legacy applications. Our approach generalizes to comparable modernization contexts and promotes reuse of migration patterns.

The prevailing engineering intuition for addressing conceptual drift in long-horizon LLM collaboration is to trade more formal constraints for more reliable outputs -- designing symbolic identifier systems, accumulating defensive rules in System Prompts, expanding context windows. Our engineering record shows that in long-horizon settings, this direction may produce effects contrary to design intent. Using action research methods in a real software project (Bang-v3) spanning approximately one month and 391 collaborative sessions, we document and analyze the failure process of these strategies. When the symbolic system exceeds a complexity threshold, LLMs do not become more accurate -- instead, they abandon genuine understanding of business semantics, retreat to self-referential reasoning within the symbolic layer, and generate outputs that appear internally consistent but are physically disconnected from reality. We name this failure pattern "Index Sickness," and its canonical manifestation "Phantom Legislation." We name the underlying principle the "Pang Principle (Semantic Vitality Law)": natural language carrying explicit purpose conveys far greater information quality than symbolic expression. From this, we design and validate its physical engineering mechanism: "Baseline-Log Physical Separation." In the same project, this mechanism reduced AI Instructions volume by ~75%, and across the subsequent ~150 sessions, no recurrence of Index Sickness was observed. A bilingual companion version (Chinese) is included as supplementary material.

When a single software artifact changes - a requirement, a configuration value, or a function - engineers must determine what else is impacted. Existing change-impact-analysis (CIA) tooling tends to rely on one of two signals in isolation: semantic similarity recovered from text (information-retrieval traceability, code search, embeddings), or structural dependency following (call graphs, IDE "find usages", test-impact selection). Each has a characteristic blind spot. A semantically driven tool misses an impacted artifact whose text shares no vocabulary with the change; a structurally driven tool misses artifacts related in meaning but not joined by an edge, and most operate only over code rather than the Requirement-Config-Service-Test chain. We argue for a training-free and interpretable analyzer that fuses both signals over the same embeddings. We model the system as a heterogeneous artifact graph with typed edges recovered by static analysis, compute a semantic prior by cosine similarity to the changed artifact, propagate impact multi-hop with decay over a row-normalized propagation matrix, and blend the two with a single tunable weight lambda. A small but complete proof-of-concept on a payment subsystem (5 labelled change scenarios) shows the mechanism we care about: artifacts with zero textual overlap with the change are still recovered through propagation, and helper functions that propagation alone cannot reach are recovered through the semantic layer. The fusion is the only configuration that covers both blind spots, and lambda acts as an explicit precision/recall control. Drawing on four publicly documented production failures, we argue that the same formulation extends to operational artifacts (images, metrics, dashboards, data schemas) that code-only analysis cannot reach.

Despite rapid advances in UAV technologies, current deployments remain limited due to several gaps in UAV systems research. To address these challenges, we propose OmniDroneX, a unified Drone-as-a-Service ecosystem, in which drones are transitioned from fixed function platforms into dynamically composable entities that can be integrated with external infrastructures to offer omni-capabilities. OmniDroneX bridges low-level physical primitives with high-level mission intent through a unified vendor-agnostic interface (libUAV) and a formal physical-service abstraction model (PT-SOA). A core innovation is the diverse application of large language models (LLMs) across multiple layers of the OmniDroneX architecture. LLMs are used to assist in identifying and formalizing primitive device functions and abstract service definitions, supporting automated service composition and workflow generation, and enabling interactive, natural-language mission specification and refinement. OmniDroneX also incorporates important categories of composition techniques that are essential in dynamic UAV systems, including physical layer composition for drone capability augmentation, as well as spatiotemporal, functional, collaborative, exception-aware, and QoS-based service compositions. Collectively, these features allow OmniDroneX to serve as a foundation for scalable, resilient, and self-evolving UAV ecosystems operating in complex and dynamic environments.

TLA+ is a formal specification language for verifying distributed systems and safety-critical protocols. Large language models (LLMs) frequently produce TLA+ specifications that fail the TLC model checker for semantic reasons. Across 25 LLMs, the best public baseline is 26.6% syntactic parse and 8.6% semantic model-check. We present TLA-Prover, a 20-billion-parameter model for TLA+ specification synthesis. Training combines supervised fine-tuning (SFT) on verified examples with repair-based group-relative policy optimization (GRPO). In the GRPO stage, the model learns to fix its own rejected specifications. We also train a direct preference optimization (DPO) variant from the same SFT checkpoint as an ablation. TLC provides the reward signal directly, with no learned reward model. Four tiers grade each output: Bronze (parses), Silver (no warnings), Gold (passes TLC), and Diamond. To reach Diamond, the model's correctness property is automatically altered in a small way; TLC must then detect a violation. If TLC still passes, the property was always-true and contributes nothing; the output fails Diamond. TLA-Prover reaches 9/30 (i.e. pass@1 = 30%) at both Gold and Diamond on a held-out 30-problem benchmark. This is roughly 3.5x the 8.6% untuned baseline. The DPO variant reaches 20% at Diamond. Gold and Diamond coincide at every checkpoint; this prevents the trivial-property failure mode.

Supervised fine-tuning of code LLMs typically applies uniform cross-entropy loss to all response tokens, implicitly assuming that every token provides equally useful learning signal. Recent token-level selection methods challenge this assumption in natural-language SFT by supervising only high-value tokens. However, directly transferring token-level masking to code can break syntactically and semantically coherent program units, because code depends on structural completeness and definition-use relations. We therefore propose CodeBlock, a structure-aware sparse supervision framework that selects structure-complete code evidence rather than isolated tokens. CodeBlock first selects high-quality instruction-response pairs, then partitions code responses into syntactically coherent coding items, estimates their utility by aggregating generalized cross-entropy over core logic tokens, and reranks them with data-flow reach and bridge signals to prioritize blocks that propagate or connect important program dependencies. During training, the full response remains available as context, while loss is applied only to selected code items and informative natural-language tokens. Experiments on six code-generation benchmarks show that CodeBlock achieves stronger average pass@1 than full-token SFT and competitive selection baselines, while using only 1.9% of supervised response tokens.

With data-driven development now widely adopted, online A/B testing is an established method for measuring the effects of new technologies. However, deploying online experiments demands resources for design, implementation, and deployment, and may negatively impact users (e.g., unsafe or unethical outcomes) while requiring weeks of data collection. To address this, the growing research area of off-policy evaluation (OPE), or offline A/B testing, assesses new technologies offline using previously collected logged data. OPE is also a fundamental problem in reinforcement learning and is important where online testing is expensive or risky, such as healthcare, recommender systems, education, and robotics. Despite advances in code-generation large language models (LLMs) and agentic workflows, little is known about whether and how LLMs and LLM-based agents can automatically optimize OPE implementations. We propose GrowthHacker, a benchmark that evaluates baseline LLMs and LLM-based agents on large-scale public datasets. GrowthHacker autonomously and iteratively modifies code, runs OPE, and uses the metrics to guide subsequent optimization. We evaluate methods on Open Bandit Pipeline (OBP) and Scope-RL, and develop a two_agent framework that addresses limitations of existing frameworks while reducing complexity. Across both libraries, two_agent shows the highest reliability (98.1%-100% success rate) and positive-outcome rate (78%), with a median improvement of 4.4% among positive outcomes; CrewAI achieves the highest average improvement (37.9%) and is the only framework with zero extreme-value failures. AutoGen and Default each reach 65% positive-outcome rates. These results establish the feasibility of using LLM-based agents as automated "growth hackers" to continuously improve OPE systems, with implications for scaling data-driven decision-making where manual optimization is expensive.

Enhancing the formal math reasoning capabilities of Large Language Models (LLMs) has become a key focus in both mathematical and computer science communities in recent years. While significant progress has been made in using state-of-the-art Auto-Regressive (AR) LLMs for formal theorem proving, these models suffer from inherent limitations. Their next-token prediction generation methods may yield suboptimal performance due to the challenges of long-range coherence and the compounding of errors over long sequences. Recent advancements in diffusion LLMs (dLLMs), which generate text through iterative denoising of a multi-token block, offer a promising alternative. However, the application of dLLMs to formal mathematics, where maintaining long-range coherence is critical, remains largely understudied. To address the challenges above, we propose **Diffusion-Proof**, to the best of our knowledge, the first framework to train and apply dLLMs for formal theorem proving. Our frameworks contain training and inference methods for two models. The first one is *dLLM-Prover-7B*, which performs whole-proof writing with long-range coherent tactic usage. The second one is *dLLM-Corrector-7B*, which is a novel large block diffusion-based correction model. It leverages the in-filling capabilities of dLLMs to perform local proof correction using bi-directional information. Extensive experiments demonstrate that **Diffusion-Proof** relatively significantly outperforms the AR LLM baseline trained under the same dataset. **Diffusion-Proof** achieves an absolute improvement of **1.61%** on ProofNet-Test and **6.14%** on MiniF2F-Test benchmarks compare to the baseline. Notably, **Diffusion-Proof** successfully resolves one IMO problem that more advanced thinking model DeepSeek-Prover-V2-7B could not solve, showcasing the unique advantage of dLLMs in formal theorem proving.

In vibe coding, an emerging AI-driven paradigm, an LLM generates an entire program from a natural language prompt, but what happens to the variability that traditional software engineering carefully builds into code? To answer this question, we conducted an exploratory analysis on 10 vibe coded C/C++ projects, which suggests that there is near-zero in-artifact variability, i.e., at compile and runtime. All variability decisions are resolved at a single new binding time, generation time, the moment the LLM produces the source code. Rather than treating this as a defect to fix, we propose Variability by Regeneration (VbR), to our knowledge the first product-line approach in which the LLM acts as the derivation engine, generating a purpose-built, free of dead code binary for each variant from a declarative specification, while a variant dispatcher transparently routes user requests to the matching binary. We formalise VbR, contrast it with classical SPL derivation, and demonstrate its full pipeline on a wc product family. For SPL engineering, variability in AI-generated software belongs in the specification, not in the code.

Thanks to rapid developments in generative AI, we are in the midst of a paradigm shift that may change how we interact with computers forever. We have observed a growth in the use of natural language prompts to build applications and coding infrastructures without underlying knowledge of the field, and this practice has been dubbed `vibe coding.' It arguably represents what the field of programming has been building towards since the beginning, with every higher level of abstraction that is conceived. Vibe coding promises to be the endpoint for the meta of high-level programming as far as method of input is concerned: eliminating a human's use of code syntax entirely in favour of programming in their mother tongue. This paper aims to evaluate the viability of vibe coding for greenfield software engineering tasks, as well as analyse the benchmarks that have been used to measure its software engineering prowess. To this end, we have developed an evaluation suite for analysing an LLM's proficiency in carrying out simple, isolated greenfield programming tasks in Python to provide scoped insight on the matter.

Block diffusion language models accelerate decoding through parallel block-wise denoising, yet whether they can be reliably scaled for long chain-of-thought (CoT) reasoning remains unresolved. To this end, we develop DreamReasoner-8B, an open-source block diffusion reasoning model, and conduct a systematic study of how training and inference block sizes affect long-CoT reasoning. Our analysis reveals a stark performance disparity: training with large block sizes yields remarkably poor reasoning, whereas small block sizes preserve effective reasoning. To bridge this granularity gap, we propose block-size curriculum learning, which gradually transitions training from fine-grained to coarse-grained block sizes, thereby overcoming this limitation and enabling strong reasoning performance that generalizes across diverse inference block sizes. On mathematical and code reasoning benchmarks, DreamReasoner-8B achieves results competitive with leading open autoregressive models such as Qwen3-8B. This work establishes a practical foundation for efficient, reasoning-capable diffusion language models. We release our model at https://github.com/DreamLM/DreamReasoner.

Scientific workflow management systems (WMS) support scalable and reproducible execution of complex pipelines, but workflow design, implementation, and debugging remain largely manual and require significant expertise. Recent approaches using large language models (LLMs) show promise for workflow generation from natural language, but often rely on direct code synthesis, which limits transparency, reproducibility, and integration with workflow systems. We present an AI-assisted approach to scientific workflow management that combines specification-driven workflow generation, automated debugging, and distributed execution. The method introduces a structured specification phase that separates workflow intent, design, and implementation, allowing validation prior to code generation. We also develop an LLM-based debugging agent that diagnoses and resolves failures across multiple system layers. To support distributed execution and user interaction, we integrate Pegasus, a widely used WMS, with a Model Context Protocol (MCP) layer, providing a unified interface for workflow submission, monitoring, and control. We evaluate the approach using a federated learning workflow for medical imaging, chosen for its parallel, iterative, and dependency-intensive structure. The system generated and executed large-scale workflows with thousands of jobs, reduced debugging effort, and allowed non-expert users to construct workflows with expert-level design patterns. These results indicate that end-to-end AI-assisted workflow generation and execution is feasible, and point toward AI-driven platforms for managing the scientific workflow lifecycle.

The advent of agentic vulnerability detection is already becoming a watershed moment for software security. Audits conducted entirely by autonomous LLM agents are uncovering critical vulnerabilities in fundamental software underpinning digital society. Many of these vulnerabilities remained masked for years, surfacing only now with AI agents. Yet the reasoning behind these discoveries remains alarmingly opaque and unvalidated. What assumptions did the agent make about a function's inputs when it deemed that function to be secure? Failures in reasoning and incorrect assumptions can lead to missed vulnerabilities and reduce trust in agentic analysis. We propose a security-specification-first paradigm that (1) exposes the agent's tacit assumptions explicitly as security specifications and (2) continuously refines those specifications via runtime falsification. We realize our approach in Code-Augur, a novel harness for agentic vulnerability detection. Given a codebase, Code-Augur analyzes each component of the system for vulnerable code. When it deems a component to be secure, it commits the local invariants behind that judgment as in-source assertions. In parallel, Code-Augur leverages a guided fuzzer to attempt to falsify those assumptions. When the fuzzer triggers an assertion, this either reveals a genuine vulnerability or a flawed specification to refine. In both cases, this process grounds the agent's understanding, aligning its view of code intent with how the code actually behaves. On real-world subjects, Code-Augur effectively leverages security specifications to detect more vulnerabilities than other state-of-the-art agents. Additionally, Code-Augur found 22 new vulnerabilities in key open-source projects. Compared to curated specialized models like Claude Mythos, Code-Augur offers effective agentic vulnerability detection built on widely available LLMs like Sonnet and DeepSeek.

State Space Models (SSMs) have emerged as an efficient alternative to the Transformer architecture. Prior work shows that, when trained under comparable conditions, SSMs can match or surpass Transformers on code understanding tasks. However, their internal mechanisms remain a black box. We present the first systematic analysis of what SSM-based code models learn along with the direct comparison between SSM and Transformer models in this domain. Our analysis shows that SSMs capture syntactic and semantic structure more effectively than Transformers during pretraining but forgets certain relations during fine-tuning on some tasks. To investigate this behavior, we introduce SSM-Interpret, a frequency-domain framework that exposes a spectral shift toward short-range dependencies during fine-tuning. Guided by these findings, we propose architectural modifications that significantly improve the performance of SSM-based code model by upto +6 MRR on NLCodeSearch. This demonstrates that our analysis not only explains model behavior but also leads directly to better designs.

The limiting resource for training agents via reinforcement learning (RL) is increasingly frontier task supply: valid, solvable tasks just difficult enough to train the current model. As reasoning and agentic models improve, fixed task distributions saturate, while naive synthetic generation yields tasks that are trivial, impossible, or ill-posed. Training a task generator with RL to optimize validity and learnability can address this bottleneck, but direct optimization requires repeated solver rollouts per candidate. For software-engineering (SWE) tasks, a single rollout can take tens of minutes; solver-in-the-loop generator training is intractable. We introduce PROPEL, a solver-amortized framework for training task generators at the targeted solve rate. PROPEL trains a lightweight activation probe on a one-time labeled corpus of generated tasks and solver outcomes. The probe predicts target-solver pass rate from a frozen generator reference model and serves as a proxy for solve rate during generator optimization, reducing generator evaluation to a single forward pass. Across math, code, and software-engineering at multiple model scales, PROPEL shifts generation toward the targeted solve rate: for coding, tasks generated at the learnable frontier increase from $10.1\% \rightarrow 20.0\%$ for a Qwen2.5-3B-Instruct solver and from $5.3\% \rightarrow 12.6\%$ for a Qwen2.5-7B-Instruct solver. For SWE, PROPEL increases the share of generations at the targeted solve rate from $9.8\% \rightarrow 19.6\%$ for Qwen3.5-27B on repositories not seen during training of probe and generator.

Context: Schools, training platforms, and technology firms increasingly need to assess programming proficiency at scale with transparent, reproducible methods that support personalized learning pathways. Objective: This study introduces a pedagogical framework for Scratch project assessment, aligned with the Common European Framework of Reference (CEFR), providing universal competency levels for students and teachers alongside actionable insights for curriculum design. Method: We apply Fuzzy C-Means clustering to 2008246 Scratch projects evaluated via Dr.Scratch, implementing an ordinal criterion to map clusters to CEFR levels (A1-C2), and introducing enhanced classification metrics that identify transitional learners, enable continuous progress tracking, and quantify classification certainty to balance automated feedback with instructor review. Impact: The framework enables diagnosis of systemic curriculum gaps-notably a "B2 bottleneck" where only 13.3% of learners reside due to the cognitive load of integrating Logic Synchronization, and Data Representation--while providing certainty--based triggers for human intervention.

We introduce GRACE-DS, a Guarded Reward-guided Agent Correction Environment in Data Science for pre-deployment evaluation of LLM-powered AutoML agents. GRACE-DS is a set of evaluation metrics in an isolated environment that can be applied to tabular ML tasks specific to a particular organization. It exposes agents to realistic workflow stages, from planning and data inspection through feature engineering, model development, validation, and code repair to final submission, while hidden executable validators measure not only final predictive performance but also leakage avoidance, reproducibility, protocol validity, correction behavior, and reward alignment. The strongest structured regime, flexible iterative interaction (our approach), achieves higher end-to-end normalized hidden-test quality than single-shot generation, unstructured interaction, and restart-based baselines, while also improving protocol-valid completion. Validated across more than 7,000 episodes, these results establish GRACE-DS as a robust platform for assessing the capacity of LLM-based AutoML agents to execute machine learning workflows under production-like conditions and in accordance with organization-specific requirements.

The large-scale digitization of educational assessment has made the continuous oversight of item banks both essential and complex. This paper presents Analytics for Quality Assurance for Item Pools (AQuAP), a dashboard environment for monitoring item quality and item bank health. AQuAP supports the operational implementation of the large scale item generation procedures for high-stakes tests as included in the Item Factory, a framework for automated and human-supported test development. The paper describes AQuAP in relationship with the process of item development, outlines the broader metric framework for item-pool quality assurance, and highlights the Effective Bank Size (EBS) as one central indicator of pool vitality. EBS quantifies how many independent test sessions can be constructed before content repetition occurs and, when coupled with exposure and usage metrics, provides insight into item bank security, diversity, and efficiency. We further introduce bank-health metrics, such as maximum exposure, maximum conditional exposure, adjusted effective bank size, and the rarely-administered fraction, all of which extend this picture of item utilization. AQuAP illustrates how operational analytics can translate psychometric concepts into quality assurance tools for high-volume, AI-enabled testing programs. This work is illustrated with the Duolingo English Test (DET) processes.

The growing deployment of artificial intelligence (AI) necessitates robust deep learning (DL) compilers, such as TVM and ONNX-MLIR. These compilers take as input high-level AI models, lower them through multi-layer transformations, and specialize them to diverse hardware. Testing such compilers is uniquely challenging as correctness depends on implicit constraints embedded throughout the compilation stack. Existing testing approaches largely take type constraints to restrict input model generation and therefore emphasize type validation and monitor compilation crashes or coverage gains. This focus overlooks compiler-platform interaction bugs that arise from interleaved effects across compilation and execution environments. In this work, we propose a scalable, automated DL compiler testing framework for, in tandem, (1) finding compiler-platform interaction bugs and (2) enabling behavior equivalence partitioning. Our key insight is that these bugs are caused by violated assumptions arising from interactions across compilation passes and hardware platforms. Therefore, we move beyond constraining input generation and derive full-stack constraints. Our approach is three-fold. First, we design an automated approach to extract full-stack constraints that jointly guide model generation and characterize compilation behaviors. Second, we prioritize constraints that expose interaction-sensitive behaviors, so our generated models are capable of exercising deep compilation logic. Third, we enable behavior equivalence partitioning by automatically inserting assertions to monitor distinct compilation symptoms that coverage or pass/fail signals miss. We evaluated our tool, XCheck, on three widely-used DL compilers and found 2,034 bug-revealing cases, including memory overflows, integer overflows, and silent unexpected compilations that were rooted in compiler-platform interactions.

We introduce SoliDualSPHysics, a novel open-source and GPU-accelerated software that extends DualSPHysics to enable the numerical simulation of hyperelastic, finite-strain plastic, and brittle fracture behavior in deformable solids within a unified smoothed particle hydrodynamics (SPH) software framework. The software implements a total Lagrangian formulation for solid mechanics that allows direct application of external loads and boundary conditions, enabling independent solid mechanics simulations. Brittle fracture is modeled through a phase-field approach coupled with SPH, allowing crack initiation, propagation, and branching under dynamic loading without explicit crack tracking, ad hoc crack-path criteria, or local refinement. The framework also supports user-defined mathematical expressions to prescribe time- and space-dependent quantities, complementing the solid and fracture extensions and enhancing flexibility across existing and future DualSPHysics applications. Leveraging DualSPHysics' native CPU/GPU parallel architecture, the software achieves substantial computational acceleration for large-scale simulations, and the implementation is verified and validated against benchmark numerical problems and experimental data, demonstrating accuracy, robustness, and favorable scaling performance. Comprehensive implementation details and user documentation are provided to ensure reproducibility and to support further development by the community. The framework and source code are freely available through a public GitHub repository.