Papers

Existing fairness analysis tools predominantly operate as post-training evaluation frameworks, requiring practitioners to complete the full model development lifecycle before assessing bias. We present FairLint-DL, a Visual Studio Code extension that implements a shift-left approach to fairness testing by enabling pre-training, IDE-native bias detection directly on tabular datasets. FairLint-DL trains a configurable deep neural network as a proxy model and applies information-theoretic Quantitative Individual Discrimination (QID) metrics. Grounded in Shannon and min-entropy, QID quantifies the causal influence of protected attributes on predictions. The system implements a two-phase gradient-guided search algorithm for discovering discriminatory instances, a causal debugging pipeline that localizes bias to specific network layers and neurons via sensitivity analysis, and dual explainability engines using SHAP and LIME for feature-level attribution. Evaluation on three tabular benchmarks (Adult Census Income, German Credit, and Bank Marketing) reveals fairness concerns that vary widely across datasets: on Adult, 96.0% of analyzed instances exhibit QID above the 0.1-bit significance threshold, with a mean QID of 0.619 bits and a disparate impact ratio of 0.581, violating the four-fifths legal rule. FairLint-DL produces these results within 12 seconds on cached models, demonstrating the feasibility of integrating fairness analysis into the developer workflow without significant overhead.

In agentic distributed systems, an agent may be authorized to mutate external infrastructure while lacking evidence that the mutation is ready to execute. Cognitive Admission Control (CAC) makes this evidence requirement explicit. A policy maps a typed action and its modeled risk to assurance obligations specifying predicates, evidence classes, scope, freshness, and witness-set constraints. A deterministic evaluator distinguishes satisfied, violated, and unresolved obligations; unresolved conditions produce targeted evidence-acquisition requests. Successful admission produces a certificate binding the action, its witness manifest, and dispatch-time guards. We formalize the admission calculus and the assumptions connecting it to mediated execution. The guarantees are policy-relative: physical safety additionally requires sound evidence, an adequate environment model, and preservation of relevant conditions through the effect. A TypeScript prototype is evaluated in 2,730 controlled local trials with independent effect observation and matched fault schedules. Across 390 CAC trials, 120 effects complete without modeled harm and no harmful effects occur. A live-policy baseline achieves the same completion count but admits the constructed correlated-witness failure. Mechanism ablations isolate guard, evidence-class, structural-cut, and remediation behavior. A further 9,000 measurements exercise the complete local dispatch path with persistent replay protection. These results establish tested implementation behaviors and local costs, not production failure rates or comparisons of language-model capability.

When a coding agent returns to existing software, it inherits evidence from earlier engineering work: tests, type checks, proofs, static analyses, and traces. Reloading all of it is wasteful, but dropping a piece the change depends on can leave a required property unsupported. Given the properties a change must preserve, its obligations, we ask which least-cost subset of the available evidence re-establishes them, and we call such a subset a task-conditioned assurance envelope. Evidence and the rules that combine it form a typed inference graph; an obligation is met when forward chaining from the selected evidence reaches it, and we validate every selection by that closure rather than by trusting the optimizer. The software-derived graphs in our evaluation come from preserved outcomes of prior AI coding-agent runs; we freeze those artifacts and ask which accumulated evidence should be restored for a later task. Small graphs from Rust, IronBlocks, and Pong outcomes show that the minimum envelope depends on the task, that none may exist when current evidence cannot re-establish a required property, that some properties need several pieces of evidence together, and that expanding the requirements adds evidence rather than replacing it. A prespecified synthetic benchmark of 249 instances characterizes computation: a baseline that discards the 'several pieces together' structure necessarily fails to re-derive them; every completed exact cross-check agreed with the CP-SAT optimizer; and median solve time stayed below 20 ms at 500-evidence graphs, except that graphs with many alternative derivations per target timed out at far smaller sizes, so structure, not raw size, drives difficulty. The contribution is a bounded application of established optimization to selecting assurance context for a software change; discovering the obligations and downstream agent benefit remain open.

AI coding agents increasingly rely on execution harnesses to interact with repositories and external tools. However, task success does not guarantee reliable execution. Agents may still modify unrelated files, rewrite tests, issue unsafe commands, or ignore failed validations, motivating behavioral guardrails for reliable execution. We present AgentGuard, an instruction-level guardrail framework that learns conditional execution constraints from anomalous trajectories of coding agents. Rather than relying on manually specified safety rules, AgentGuard automatically extracts recurring execution failure patterns, generalizes them into instruction-level behavioral constraints, and organizes them as a lightweight guardrail skill that dynamically activates only the rules relevant to the current instruction. This design enables behavioral guidance while minimizing unnecessary restrictions on normal execution. We evaluate AgentGuard using 642 documented failure traces collected from real coding-agent executions across 382 repository tasks. Guardrails are learned from 461 traces covering 282 tasks and evaluated on a disjoint set of 100 tasks. Using Claude Code with Claude Haiku 4.5 as the underlying coding agent, we compare the baseline agent with the same agent augmented by AgentGuard. Experimental results show that AgentGuard reduces the Abnormal Execution Rate from 69.0% to 26.7% and increases the Successful Task Completion Rate from 21.7% to 35.0%. These results demonstrate that execution guardrails learned from historical failures can substantially improve the reliability of AI coding agents while highlighting the remaining challenge of balancing safety and task completion.

Modern application platforms must isolate workloads while preserving deployment speed, portability, resource efficiency, and security. Virtual machines (VMs) and Docker containers address this requirement at different abstraction layers: VMs virtualize hardware and run independent guest operating systems, whereas containers isolate processes while sharing the host kernel. This paper presents a comparative, literature-based analysis of the two approaches across architecture, configuration and lifecycle management, performance, scalability, and security. Published studies generally associate containers with shorter startup times, smaller images, higher workload density, and near-native execution for many workloads. These benefits depend on workload characteristics, storage and network drivers, resource controls, and experimental design. VMs introduce greater overhead but offer independent kernels, heterogeneous guest operating systems, and a stronger isolation boundary. The comparison therefore treats efficiency and isolation as a design trade-off rather than declaring one technology universally superior. A hybrid architecture, in which containers run inside hardened VMs, often provides a practical balance for cloud and multi-tenant systems.

Large language model coding agents have recently become useful for software tasks, but weaker or open-weight agents still struggle to reliably interpret user intent and execute complex multi-step workflows. This gap is especially visible in long-horizon settings, where an agent must repeatedly inspect prior outcomes, diagnose failure, and choose the next code edit under interaction constraints. It motivates a natural question: what can we do to improve the thinking process of a weak code agent? We study this question in CodeClash, a code-arena benchmark where the original work evaluates 8 commercial coding agents across 6 arenas through multi-round tournaments. Since Qwen3 Coder Plus ranks last among them, we take the open-weight Qwen3-Coder-30B as a case study and investigate how to improve it with distilled knowledge from stronger agents. Our analysis shows that Qwen3-Coder-30B is not well optimized for arena-style interaction: it frequently produces syntax and protocol-breaking errors and exhibits weak strategic adaptation across rounds. These failures are difficult to correct with vanilla instruction tuning alone, since offline SFT cannot directly verify whether a generated action is valid or beneficial. To address this, we propose ReAct SFT, which rewrites teacher trajectories into explicit [obs][thought][act] chains, and trajectoryquality weighted SFT, which reweights samples to encourage post-edit checking. ReAct SFT substantially improves strategic behavior, and our fine-tuned model outperforms the original Qwen3 Coder Plus in tournament evaluation.

Software agents with Large Language Models (LLMs) are designed for Automated Program Repair (APR) tasks, raising the possibility that, in the near future, APR agents will fix bugs automatically without much human intervention. Can we trust an APR agent to produce both functionally correct and secure code in such situations? What if attackers target production APR agents with adversarial issues that seem benign but may influence the agents to produce correct but insecure code? In this paper, we took a first step towards answering these questions by conducting an empirical study. First, we created SWEADV, a benchmark of 750 adversarial issue descriptions constructed from 150 repair tasks in SWE-bench Verified. For each repair task, we created five adversarial issue descriptions, one for each attack type: command execution, deserialization, path traversal, denial of service, and weak hashing. Second, we evaluated mini_swe APR agents from three LLM backends on SWEADV: GPT-5-Mini, MiniMax-M2.5, and DeepSeek-R. We found that on average, adversarial issue descriptions can induce malicious behaviors with successful repair in 51.7% of cases. Third, we investigated whether typical detection mechanisms are sufficient to prevent such malicious patches from being accepted. Pre-repair detection with LLM-as-judge on the adversarial issue descriptions resulted in an average detection accuracy of only 62.3%. Post-repair detection on adversarial APR patches using static analysis tools and LLM-as-judge achieved average detection accuracies of only 39.4% and 55.4%, respectively. We conclude that autonomous APR agents cannot be trusted yet in production deployment, given their susceptibility to adversarial attacks.

Context: Conducting effective code reviews is increasingly challenging due to the growing complexity of software systems and the accelerated code generation by AI coding agents. LLM-based approaches for code reviews have shown promising results in identifying defects and improving code quality. However, existing approaches rarely consider project-specific contextualized knowledge, and few have been evaluated in industrial settings. Objective: In this study, we propose a multi-agent-based solution that provides multifaceted assessments of code changes. Method: Following the Design Science Research Process, we developed and evaluated our solution in an industrial setting. Our solution combines specialized agent skills with context-specific knowledge to identify antipatterns in code changes across four dimensions: readability, maintainability, reliability, and performance. Using our solution, we generated reviews for several code commits and identified more than 200 issues. These issues were then manually validated by the developers of the case company for their correctness and importance. Results: The evaluation results show that our solution achieves 96% accuracy in correctly identifying issues in the investigated code commits. Furthermore, around 69% of the correctly identified issues were rated as important, with approximately 33% rated as severe issues that must be fixed and 36% as important issues that should be fixed. Qualitative feedback from developers corroborates these findings and highlights the usefulness of the generated reviews. Conclusion: Our findings provide empirical evidence from an industrial evaluation that combining specialized agent skills with context-specific knowledge yields accurate, practically useful code reviews.

The rapid adoption and evolution of AI are changing software engineering work and requiring professionals to repeatedly adapt their knowledge, practices, and skills. Although technological adaptation has long characterized software development, less is known about how these new and recurring pressures manifest as technostress. This preliminary exploratory study investigates AI related technostress among software professionals. We conducted a survey and performed a thematic analysis of responses from 121 software professionals across 26 countries reporting their recent experiences with AI at work. Our findings suggest that AI related technostress emerges not only from adapting to rapidly changing technologies, but also from having to manage the work, technical responsibilities, and professional changes that accompany their adoption. This characterization shows that AI introduces pressures beyond learning and using new tools, affecting how software professionals perform and remain accountable for technical work and how they prepare for the future of their careers.

An artificial organ carries failure consequences on the scale of an aircraft or a reactor, but the software driving it is rarely held to the same standard. Teams building them rely on testing, which only reaches the failure modes someone thought of in advance. In a pump or controller that runs inside a patient for months, the dangerous cases are the ones nobody anticipated. Formal verification closes that gap. Applied to the device's software, it proves the code meets its specification for every execution that specification allows, and where a proof fails, it returns the exact input sequence that breaks it. The same methods already protect rail, aviation, and nuclear control systems, and they extend the IEC 62304 lifecycle that a manufacturer already follows rather than replacing it. In this paper, we explore how to apply formal verification to artificial organs, stage by stage, and what each technique actually guarantees about the device.

The enforcement of essential boundary conditions is a fundamental challenge in unfitted boundary methods. This paper presents a non-intrusive, black-box strategy for imposing such conditions in unfitted meshes. The approach is intended for situations where the user does not have access to the solver's source code or its mathematical formulation, which is often the case when using commercial software. The proposed algorithm allows solvers originally designed for body-fitted meshes to be used in unfitted cases, provided that four conditions are satisfied: (i) the solver must support user customization by means of scripting, (ii) allow the imposition of Dirichlet boundary conditions at the node level through scripting, (iii) permit the deactivation of elements outside the physical domain, and (iv) provide access to the solution gradient within active elements. The last condition can also be satisfied by externally reconstructing the gradient from nodal values and connectivity information, provided the element formulation is known, making it optional in practice. These requirements are very fair demands and are satisfied by the vast majority of production-ready, possibly commercial, codes. In the current work, we show the application of this non-intrusive algorithm in the context of the Finite Element Method (FEM) and Isogeometric Analysis (IGA) discretizations, demonstrating optimal $L^2$-norm error convergence. This is demonstrated using the Kratos Multiphysics code (release v10.1) from the user API, simply leveraging the capabilities mentioned above.

AI agents increasingly execute long-running workflows that externalize effects through independently supplied tools. Under retries, speculative execution, concurrency, and partial failures, the resulting external state may be inconsistent with the workflow's intended resolution: required effects may be missing or duplicated, aborted effects may survive, and committed effects may depend on provisional state that is later withdrawn. Advanced transaction models address related failures, but assume that lower-level operations expose the semantics they depend on: whether an effect occurred, whether it can be compensated, staged, or safely reordered. Shared agent-tool interfaces usually do not. We contribute an effect-history model that separates events in the external world from the runtime's observations of them, and a catalog of eight recurring external-effect anomalies. From the catalog we derive the boundary capabilities required to exclude each anomaly in general, and four points where black-box tool invocation alone cannot provide a general guarantee. We then ask how much of this is expressible in a widely used shared tool interface, measuring the use of the standard annotation vocabulary across 98,291 tools exposed by registered Model Context Protocol (MCP) servers. The fields are widely emitted but provide only coarse call-level hints, and none of the required capabilities is fully expressible. These results motivate reusable transactional contracts at the tool boundary.

Human evaluation provides a direct measure of the quality of LLM-generated web applications. However, fitting human judgments through automated evaluation remains challenging. Static benchmarks can credit functionality that exists in source code but is unreachable at runtime. Interactive benchmarks exercise the application, yet incomplete exploration can cause them to miss implemented functionality and confound application defects with agent execution failures. To address these limitations, we propose WebCraftBench, an interactive benchmark for evaluating web application generation from a software testing perspective. WebCraftBench instruments each generated application and uses code coverage to guide an agent in exploring its functionality through user-simulated interactions. It then abstracts the interaction trace into a state-transition graph and evaluates the application along three dimensions: visual aesthetics, usability, and requirement alignment. By separating exploration from scoring, WebCraftBench collects runtime evidence without constraining exploration to predefined acceptance criteria. WebCraftBench comprises 369 real-world user requirements and 5,088 acceptance criteria. Evaluation of 17 frontier LLMs reveals distinct strengths across the three dimensions, with no model leading on every dimension. On 197 validated sessions sampled from an internal arena, WebCraftBench achieves 85.3% agreement with human preferences, with agreement generally increasing as the score difference between paired applications grows. Further experiments show that coverage guidance improves exploration coverage and the model rankings remain stable when the judge model is replaced.

Vibroacoustic analysis often requires coupling structural and acoustic solvers based on different numerical formulations and discretizations, making monolithic implementations intrusive and limiting software modularity and reuse. This work presents a partitioned co-simulation framework for exterior vibroacoustic analysis that couples an Isogeometric boundary representation analysis (IBRA) structural solver with an isogeometric boundary element method (IGA-BEM) acoustic solver. The methodology operates directly on the computer-aided design (CAD) boundary representation, preserving the exact geometry throughout the analysis and supporting both weak and strong coupling between non-conforming discretizations. A key contribution is the extension of the Aitken dynamic relaxation and Interface Quasi-Newton with Inverse Least-Squares (IQN-ILS) convergence accelerators to complex-valued interface quantities, allowing the coupling iterations to account directly for both amplitude and phase information. The approach is validated using one-way and two-way coupled vibroacoustic benchmark problems involving thin-shell structures and exterior acoustic domains. The results show excellent agreement with monolithic reference solutions, while the proposed complex-valued convergence accelerators improve the robustness and convergence behavior of the strongly coupled solution procedure without compromising solution accuracy. These results demonstrate that the proposed approach provides an accurate, robust, and modular approach for CAD-integrated frequency-domain vibroacoustic analysis.

C-to-Rust translation remains challenging due to the substantial semantic gap between the two languages. Recent experience-enhanced LLM translators improve translation quality by learning reusable insights from prior failures and repairs. Yet learned insights do not automatically constitute reusable translation knowledge: derived from sparse, program-specific traces, they often contain missing conditions, narrow applicability boundaries, or overlooked corner cases. This limits their robustness and generalizability in new translation scenarios. We present TRAIL, an adversarial agentic learning framework for robust C-to-Rust translation. TRAIL employs two collaborating agents: a Translator that derives candidate insights from translation failures and accepted repairs, and a Challenger that actively searches for weaknesses, gaps, and boundary cases through adversarial challenges. To improve the robustness of individual insights and the completeness of insight collections, TRAIL performs adversarial learning at two levels. Individual-insight adversarial learning repeatedly stress-tests each insight to refine its applicability conditions and constraints, while compositional insight adversarial learning strengthens groups of related insights by exposing conflicts, gaps, and uncovered corner cases. By challenging insights and their compositions with executable counterexamples, TRAIL transforms trace-specific experience into robust, reusable, and generalizable translation knowledge. We evaluate TRAIL on two project-level benchmarks, CRUST-Bench and SmartC2Rust-Bench. Compared with the strongest LLM-based baseline, TRAIL achieves average relative improvements of 23.1% in syntax accuracy and 15.9% in semantic accuracy. Furthermore, the adversarially refined insights transfer effectively across benchmarks, demonstrating strong generalizability across diverse C-to-Rust translation tasks.

Agentic artificial intelligence (AI) marks a new phase of digitalization: digitalization is beginning to act back upon its own technical production base. Whereas earlier phases aimed at digitizing analog information, automating processes, and building digital value networks, AI is increasingly taking over tasks in the development of digital systems themselves. In software engineering (SE) in particular, agentic AI systems can already plan, execute, check, and iteratively refine development tasks across multiple steps. Digitalization thus becomes recursive: digital systems no longer merely support the digitalization of other sectors, but are increasingly developed and evolved by digital systems themselves. The technical production base of digitalization thereby becomes the object of its own transformation. This changes not only the division of labor between humans and machines in SE, but also the role of SE as a whole. This chapter analyzes this socio-technical change and argues that SE is evolving from a primarily supporting engineering discipline into a central infrastructure of societal value creation as well as of technological and digital sovereignty.

Recently, the use of Large Language Models (LLMs) for different tasks in the Electronic Design Automation (EDA) life-cycle has been studied extensively, but an integrated view is lacking. Specifications are the foundation of this life-cycle, but they suffer from ambiguity when written in natural language, which especially affects the quality of LLM output. Formal specifications mitigate these ambiguities, but they come with their own challenges. On the other hand, Controlled Natural Language (CNL) specifications can serve as a middle-ground, reducing ambiguity while retaining interpretability. In this work, we propose an integrated view on the use of LLMs for EDA and establish an LLM-enabled behavior driven hardware development workflow. We introduce and define Formal Verification Gherkin Scenarios (FV Gherkin Scenarios), unlocking CNL specifications as the foundation for formally verified hardware designs via Formal Property Verification (FPV). Experimental evaluation shows that our workflow is able to outperform other established LLM-based methods by 2.48x in functional correctness of generated Register Transfer Level (RTL) designs and by 2.54x in formal coverage of generated assertions for FPV.

Automatic prompt optimization (APO) improves language-model programs by revising prompts from task feedback, yet it typically holds its training data fixed. Repeatedly optimizing against the same instances confines feedback to weaknesses already represented in those data, leaving related failure conditions unexplored. We therefore view each failure as a dual signal: it indicates both how the prompt should be revised and what new training evidence should be synthesized. We introduce FORGE, a failure-guided framework that co-evolves prompts and training data. FORGE abstracts imperfect executions into reusable failure modes and synthesizes new training data through four complementary mutation strategies. Verified instances are fed back into prompt search, allowing updated prompts to expose the next data needs. Across eight heterogeneous benchmarks, FORGE improves the aggregate score over the unoptimized baseline by 16.52 percentage points and outperforms all evaluated APO baselines. The synthesized data also transfer beyond FORGE: in a transfer study, they improve all nine APO comparisons by 2–9 points and all three GRPO comparisons by 4–8 points under matched optimization budgets. These results establish failures as a shared interface between prompt optimization and data synthesis, and show the benefit of jointly adapting what a model is instructed to do and what it learns from.

woma is a real-time foundation model for gastrointestinal endoscopy: a network trained without labels on about a million endoscopy frames, from which task models are fine-tuned. We contribute a systematic design for production. Requirements and pass marks were fixed before any run, eight candidates screened under pre-registered rules, self-supervised training taken to a stopping rule, then fine-tuning and deployment optimisation, all on one self-contained library, numbat. We also contribute woma itself with two fine-tuned models, every outcome reported met or missed. Our colonoscopy model finds and outlines polyps, names which colon segment is in view, suggests polyp type and grades bowel preparation. Our gastroscopy model names a station out of 22 protocol sites, flags and outlines lesions, and names one of seven findings. Every number was read on data never seen in training, and shipped weights were chosen on that record. In colonoscopy, 96% of polyps in a six-hospital PolypGen set are found at precision >=0.85, and 19 of 19 polyps across fifteen full REAL-Colon videos at 1.6 false alarms per procedure. In gastroscopy, landmark region is named correctly on 92% of frames from unseen patients, and 37 of 39 held-out neoplasia frames are flagged at specificity 0.91. On one workstation GPU every task runs over 1080p video at about 100 frames per second, faster than PyTorch, ONNX Runtime and TensorRT in all four precision regimes tested. TensorRT comes closest: one pass of our foundation model takes it 3 to 27% longer than ours, and we deliver 6 to 31% more frames per second from frame to results. A second build links no vendor library at all – our own kernels over Vulkan – so a site deploys two files and needs no toolkit, no cuDNN and no framework; in f32 it beats the CUDA build on the same card.

Generative CAD models are expected to remain behaviorally correct after parameter edits, so increasing the number of edit checks is often treated as a direct route to more reliable evaluation. Under a fixed budget, however, auditing each program more thoroughly reduces the number of tasks and independent generations that can be evaluated, which can ultimately make model-level estimates less accurate. We study this phenomenon and the conditions under which it arises. We decompose behavioral evaluation into three evidence levels: task templates, stochastic generations, and within-program edits. We define an average failure risk that is invariant to audit depth, and combine three-level variance with measured execution costs to analyze the tradeoff between deeper edit auditing and broader independent coverage. Experiments across two CAD environments and five generation systems show that the value of deeper auditing depends on where evaluation uncertainty originates. When template heterogeneity or generation stochasticity dominates, additional edit checks can increase total estimation error; when within-program state variation is large and generation is expensive, deeper auditing is more valuable. Variance and cost estimates from calibration predict the direction of this change and provide a diagnostic basis for allocating evidence on held-out tasks. These results show that the thoroughness of program inspection can diverge from the reliability of model evaluation, and they help determine whether the next unit of budget should be spent on a new task, a new generation, or additional edit checks.

AI co-scientists could accelerate computational research, but over a long-running study the workflow also has to stay inspectable, resumable and reproducible, which requires persistent computational state and provenance. Here we present OpenAI4S, an open-source scientific research agent built around the principle of Code as Action, Science as Sessions. OpenAI4S combines a persistent computing runtime with research-session management: orchestration is handled through structured tool calls, while scientific actions are represented as complete code cells executed in persistent Python and R kernels. An append-only Action Ledger, per-cell execution records, versioned artifacts, environment records, and workspace checkpoints preserve how results were produced and support session recovery, branching, and extension. Configurable sandboxing, permission controls, and code and trajectory screening provide complementary safeguards. We evaluate OpenAI4S on 36 research scenarios spanning retrosynthesis, molecular dynamics, protein binder design, protein mutation, catalyst screening, and mineral spectroscopy, measuring scientific task accuracy, workflow completeness, and reproducibility of the resulting repositories. OpenAI4S achieves an overall score of 7.83, compared with 5.7–6.4 for a general-purpose coding harness evaluated with three frontier models, with the largest gains on long-horizon and computation-intensive workflows. These results suggest that integrating persistent execution with session-level provenance can improve the reliability of AI-assisted scientific workflows. Environment specification and full rerunnability remain weak for every evaluated system, ours included, so reproducibility is still an open problem for scientific agents. The system is available under the MIT license at \href{https://github.com/PKU-YuanGroup/OpenAI4S}{github.com/PKU-YuanGroup/OpenAI4S}.

Modern software development increasingly relies on using multiple programming languages. Some software packages are published to multiple package ecosystems such as NPM for JavaScript and PyPI for Python. Little is known about cross-ecosystem packages, especially regarding how they are structured. In this paper, we conduct a large-scale empirical study of over six million packages across six major ecosystems to understand 1) how prevalent cross-ecosystem packages are among all packages, 2) whether there are distinct source code architectural patterns that cross-ecosystem packages use, and 3) whether there are correlations between architectural patterns and project health metrics from GitHub. Results indicate that cross-ecosystem packages constitute a small but important, growing fraction of packages. We identify five distinct architectural patterns. For example, packages that implement code generation from a shared source file or use language bindings are associated with significantly higher community visibility and development activity. Based on our findings, we provide implications for package adopters, maintainers, and researchers. We envision our taxonomy being used for future investigations into several aspects of software development, such as the trade-offs between focusing on one language and translating to other languages using bindings, templating, and wrappers, versus using native code and native functions to support additional languages.

Repository-level repair requires not only correct patches but also inspectable records that explain how issue requirements are translated into code changes and post-edit evidence. We contribute THEMIS, a stage-aware repair workflow that externalizes this requirement-to-repair process through semantic interpretation, a runtime requirement-code graph, graph-derived Developer guidance, retained repair rationale and patches, and post-edit audit records. A retrospective audit of 300 SWE-bench Lite cases demonstrates that these artifacts provide broad support for cross-stage inspection: a complete Developer rationale is available for 288 cases, and 214 cases (71.3%) retain a complete audited field set connecting the selected stages. The retained records further enable systematic measurement of cross-stage correspondence: target symbols recur in 62.6% of Developer rationales and in 62.8% of patches, rising to 75.8% when related symbols are included. In a paired 100-case comparison, the relational workflow resolves 19 cases versus 9 for the direct same-input condition; because the two conditions also differ in Analyzer output, graph-derived distillation, and Judge records, we report this as preliminary, workflow-level evidence rather than a causal effect of the graph component. Together, these results show that THEMIS makes otherwise implicit requirement-to-repair transitions inspectable, enabling systematic examination of how repair decisions persist, align, and evolve across stages.

Enterprises deploying AI for supply chain decisions commonly default to the largest available language model, a procurement heuristic that neglects both empirical performance and environmental cost. We benchmark six large language models across 520 supply chain tasks, simultaneously measuring decision quality and estimated generation-related operational carbon. Drawing on the Technology-Organization-Environment (TOE) framework, we develop a Carbon-Aware AI Procurement Framework (CAAPF), a Green IS design artifact that operationalizes sustainable AI governance for enterprise procurement. Within this bounded sample, quality spans 0.497-0.723, and the models with the largest disclosed parameter totals do not achieve the highest scores. The design does not isolate size, provider, architecture, or benchmark-construction effects. A category-by-tier calibrated GreenRoute proof of concept reaches 0.733 mean out-of-sample quality at an estimated 0.402 gCO2/task. Static Haiku reaches 0.699 at 0.022 gCO2/task, while Sonnet reaches 0.723 at 0.401 gCO2/task, demonstrating that the preferred strategy depends on the organization's quality requirement. Our "benchmark first, select green" principle suggests that environmental responsibility and decision quality can be mutually reinforcing, contributing to sustainable digital infrastructure governance aligned with SDG 12 and SDG 13.

The integration of Large Language Models (LLMs) into automated code optimization introduces a critical reliability risk we term the Efficiency Hallucination: an LLM's tendency to issue non-functional mutations with unsubstantiated performance claims on already-optimized code. This is driven by the Evaluation Trap, wherein binary benchmarks incentivize unnecessary modifications over safely abstaining. We present a validation framework using classification penalty methods, evaluated across 180 optimization runs on nine models (GPT, Claude, Gemini) using EffiBench. Under standard prompts, models exhibit a 100% over-edit rate on optimal code. Our guardrail raises correct abstention from 0% to to 44.4%, preserving a 100% edit rate on sub-optimal code with zero false abstentions. Calibration is uneven: GPT-5.4 Mini approaches near-perfect abstention, and simple code is recognized more reliably than complex code. Our framework offers a training-free mechanism to mitigate LLM overconfidence before deployment in production.

The software status quo is to use one system to process many different kinds of inputs. In contrast, we propose hyperspecialization: creating new software that is optimized for a single class of inputs. Hyperspecializing manually is anywhere from expensive to impossible. We conjecture that coding agents make automated hyperspecialization cheap, effective, and safe for problems with measurable performance and checkable output. This paper explores one such problem, SAT solving, by synthesizing hundreds of workload-specific SAT solvers at an average cost of \$37 each. Our specialists outperform their competition-winning, general-purpose cousins by 5$\times$ on average, and by over $10\times$ on a quarter of benchmark families. A general-purpose solver constructed from over a hundred of our prototype hyperspecialists won the SAT track at the 2026 SAT Competition.

As conversational AI systems increasingly operate in sensitive domains, the central challenge shifts from usability to trust calibration, ensuring that users rely on systems neither too much nor too little. Systems that provide advice or interpretations risk encouraging inappropriate reliance, particularly when users perceive AI outputs as authoritative. We present CASELy, a conversational agent explicitly designed to limit its own authority through non-advisory Socratic dialogue. The agent asks reflective questions grounded exclusively in user input and refuses to provide advice, recommendations, or interpretations. This design operationalizes trust calibration by constraining agent agency rather than optimizing capability. In a pilot randomized controlled study with higher education students, participants interacting with the Socratic dialogue reported substantially higher user experience (UEQ-S overall = 1.50) compared to a non-dialogue control (0). Qualitative findings identify three mechanisms supporting calibrated trust: transparency through visible grounding, preservation of user decision authority, and reduced fear of judgment. We argue that appropriate reliance can be achieved through interactional constraints, offering a design pattern for trustworthy conversational AI in sensitive contexts.

Scientific autoformalization turns verbal accounts into executable mathematics, but executable code does not settle which model has been constructed. We examine two sources of structural uncertainty: the formalizer that generates a response law, and the recurrence that turns that law into trajectories. In secondary analyses of an openly archived crossed experiment, we studied 320 response maps generated by two pinned language-model formalizers from five engineered cognitive accounts within one sparse quadratic grammar and 16 randomized blocks. With whole blocks held out, source-account identity was recovered at 78.8% accuracy (chance 20.0%) and formalizer identity at 96.3% (chance 50.0%; both p < 0.001). Program size was the stronger single feature family; a pre-specified exploratory comparison found no stable source-account predictive gain from local geometry beyond size. Holding every response map fixed, we then evaluated five recurrence families spanning 33 configurations and 1,013,760 finite-horizon trajectories. Added feedback, projection and leak produced sharply different outcome distributions. The consequential distinction was which comparisons survived: median cross-recurrence rank concordance was 0.73 for endpoint magnitude but 0.05 for settling, among the configuration pairs with defined rankings. Thus a common mathematical language did not erase translation provenance, and robust ordering under one observable did not transfer to another. Scientific autoformalization is usefully studied as model-space construction: the generated ensemble and its dynamical embedding are both part of the specification supporting a scientific claim.

Automated unit test generation tools like EvoSuite perform well on general-purpose software but often struggle with domain-specific software such as Natural Language Processing (NLP) libraries, where inputs must follow semantic, syntactic, and structural constraints. Large Language Models (LLMs) can generate domain-relevant test code, but tests produced by LLMs alone often fail to compile or achieve sufficient coverage. We propose LLMSuite, a hybrid test generation framework that integrates self-refinement prompting with class-level LLM reasoning into the search-based testing process. In this mechanism, the LLM iteratively improves its test snippets based on feedback from previous generations. This enables the model to produce increasingly precise, domain-consistent code fragments that steer the evolutionary search toward exercising complex and otherwise hard-to-reach behaviors. When no objective improves over multiple generations in the underlying evolutionary algorithm, these refined snippets are parsed and injected into EvoSuite's population to expand the search space. To support our evaluation, we constructed a new dataset comprising 100 classes drawn from five widely used Java NLP projects. We also re-implemented CodaMOSA, a recent hybrid SBST-LLM technique, in Java to enable a direct comparison. Across this dataset, LLMSuite improves branch and line coverage by approximately 10% and 8%, respectively, and achieves an 11% higher mutation score than CodaMOSA-J. Compared to EvoSuite, LLMSuite yields roughly 15% higher branch and line coverage and 5% higher mutation score. Against an LLM-only baseline, it improves structural coverage by 36% and mutation score by about 24.7 percentage points. Finally, LLMSuite complements manually written test suites by exercising domain-specific behaviors that are often left untested.

Multi-tenant tools commonly accept a tenant identifier and validate it against the caller's entitlement. For a large language model (LLM) agent, that pattern delegates resource selection to a process whose context may contain attacker controlled instructions. We formalize this stochastic deputy problem and present a structural defense: remove tenant identity from the Model Context Protocol (MCP) tool schema, bind scope to a verified credential, and enforce it below the agent. In a 373-trial ablation across eight model configurations and two transports, a correctly validated tenant parameter served every out-of-scope attempt: 26 of 26, or 26 of 41 plausible-pretext trials overall. With the parameter removed, no tool signature could express the read. Twelve of 56 trials instead escaped the interface by forging writable scope, showing that interface invariance requires cryptographically protected context. On a production dataset containing multiple GBs of data, set-valued scope caused a measured $57\times$ latency ratio under function-wrapped membership predicates; a JSON_TABLE lateral join recovered index access where the tenant key was indexed. The evaluation also exposes deployment limits, including an entitlement-size query-planner cliff and incomplete index coverage. The result is a tenant-isolation argument that depends on enforceable interfaces and credentials rather than model compliance.