AI Software Engineering

Iterative self-refinement is a popular inference-time reliability technique, but its effectiveness in code-mode tool use depends heavily on the structure of the feedback signal: unstructured critique helps inconsistently across models, and even revision with real execution feedback improves only modestly. The dominant failures are inter-tool contract violations (wrong output shape, incorrect tool routing, broken argument provenance) that run to completion without raising errors, making runtime feedback insufficient. We introduce RubricRefine, a training-free method for pre-execution contract checking that generates task- and registry-specific rubrics, scores candidate code against explicit contract checks, and iteratively repairs failures before any execution occurs. RubricRefine reaches $0.86$, averaged across seven models, on M3ToolEval with zero execution attempts, improving over prior inference-time baselines at lower latency than rubric-guided reranking. Performance remains flat on the predominantly single-step API-Bank, consistent with the method's reliance on inter-tool contract structure. Results on AppWorld demonstrate that our method maintains an advantage in the multi-turn setting. Because the rubric is derived from the supplied tool documentation, the method's advantage survives incomplete documentation but reverses under incorrect documentation. A rubric-category ablation identifies which rules are load-bearing, and top-bin calibration enables early stopping even where aggregate calibration is poor.

Understanding human mental states from natural behavior is crucial for intelligent systems in the real world. However, most current research focuses on predicting isolated mental state labels, lacking structured annotations of complex interpersonal interactions. To support structured analysis, we introduce MOTOR-Bench, a carefully-designed benchmark with a real-world dataset MOTOR-dataset, containing 1,440 multimodal video clips in collaborative learning scenarios, reflecting key real-world data challenges including natural class imbalance, visual noise, and domain-specific language. Each sample is labeled by educational experts based on self-regulated learning theory. We further evaluate several state-of-the-art multimodal large language models and multi-agent systems in a zero-shot setting on our MOTOR-Bench. However, their performance on this task remains limited, suggesting that existing methods still struggle with structured reasoning from observable behavior to deeper mental states. To address this challenge, we propose a reasoning multi-agent framework, named MOTOR-MAS. It coordinates multiple agents through a structured agent coordination mechanism to infer explicit behaviors, internal cognitions, and psychological emotions. Experimental results show that our MOTOR-MAS outperforms the best single-model benchmark by 15.93 points in Macro-F1 scores for the three labels of behavior, cognition, and emotion, and outperforms the general multi-agent benchmark by 10.2 points in internal cognition prediction.

We introduce a red-teaming methodology that exposes harder-to-catch attacks for coding-agent monitors, suggesting that current practices may under-elicit attacks and overstate monitor performance. We identify three challenges with current red-teaming. First, mode collapse in attack generation, which we reduce with a novel attack taxonomy for broader coverage. Second, a conceive-execute gap: frontier LLMs can propose strong attack ideas or execute them, but not all at once. We mitigate this by decomposing attack construction into strategy generation, execution, and post-hoc trajectory refinement. Third, manual elicitation is costly to scale, which we address with our semi-automated red-teaming pipeline. Applied to BashArena, an AI control setting for tool-using coding agents, this pipeline produces MonitoringBench, a benchmark of 2,644 attack trajectories for evaluating monitor capabilities and failure modes. Our pipeline produces more diverse and stronger attacks: Opus-4.5 monitor's catch rate falls from 94.9% on elicited-only Opus attacks to 60.3% on our best refined attacks, with larger drops for several mid-tier monitors. Attacks optimized against three development monitors generalize to ten held-out monitors, with catch rates generally increasing with monitor capability. Using this benchmark, we provide a snapshot of the current monitor capabilities and find that frontier monitors often detect suspicious actions but fall for persuasion or fail to calibrate suspiciousness scores appropriately, suggesting tractable paths for improvement. MonitoringBench provides both a static benchmark for current tool-use monitors and a reusable methodology for refreshing these evaluations as agents and monitors improve.

As generative AI and low-code workflow platforms become routine in software practice, a key educational question is whether the next generation of computer engineers will accept these tools as useful, usable, and worthy of sustained engagement. This paper reports a mixed-methods, cross-sectional study of undergraduate computer engineering students' acceptance of AI automation tooling, instantiated through the open-source platform n8n across three identically scripted workshops in Thailand (n = 103). A 12-item, five-point Likert instrument mapped to six TAM/UTAUT constructs - Performance Expectancy (PE), Effort Expectancy (EE), Behavioral Intention (BI), Self-Efficacy (SE), Hedonic Motivation (HM), and Output Quality (OQ) - was complemented by inductive thematic analysis of open-ended feedback. Analyses combined ordinal reliability estimation, bootstrap confidence intervals, non-parametric tests, multiple-comparison-controlled correlations, polychoric dimensionality diagnostics, a common-method-bias check, and between-session comparisons. Acceptance was favorable across all six constructs with large effect sizes, with PE emerging as the strongest construct and HM as the weakest. Dimensionality diagnostics further revealed that canonical TAM/UTAUT sub-facets collapsed into a single general acceptance factor in this short-form post-workshop context, a finding with important methodological and theoretical implications. Qualitative themes converged with the quantitative profile regarding usefulness and enthusiasm but diverged on output quality, revealing a small yet articulate reliability-skeptical minority. The findings support the curricular adoption of AI automation tooling in undergraduate computing education and identify three theory-grounded instructional levers: instruction-sequencing scaffolds, self-efficacy supports, and trust-calibration interventions.

LLM/VLM-based digital agents have advanced rapidly thanks to scalable sandboxes for coding, web navigation, and computer use, which provide rich interactive training grounds. In contrast, embodied agents still lack abundant, diverse, and automatically generated 3D environments for interactive learning. Existing embodied simulators rely on manually crafted scenes or procedural templates, while recent LLM-based 3D generation systems mainly produce static scenes rather than deployable environments with verifiable tasks and standard learning interfaces. We introduce SimWorld Studio, an open-source platform built on Unreal Engine 5 for generating evolving embodied learning environments. At its core is SimCoder, a tool/skill-augmented coding agent that writes and executes engine-level code to construct physically grounded 3D worlds from language/image instructions. SimCoder self-evolves by using verifier feedback (e.g., compilation errors, physics checks, VLM critiques) to revise environments and autonomously add reusable tools and skills to its library. Generated worlds are exported as Gym-style environments for embodied agent learning. SimWorld Studio further enables co-evolution between environment generation and embodied learning: agent performance feedback guides SimCoder to generate adaptive curricula near the learner's capability frontier, so that environments become increasingly challenging as the embodied agent improves. Three case studies on embodied navigation show that self-evolution improves generation reliability, generated environments substantially improve embodied agent performance that generalizes to unseen benchmarks, and co-evolution yields an 18-point success-rate gain over fixed-environment learning and a 40-point gain over an untrained agent.

Execution-based evaluation of LLM-generated code implicitly treats successful execution as a proxy for correctness. In scientific simulation, this proxy is insufficient: a generated input file can run, mesh, and converge while encoding governing equations that differ from the user's intent. We call this mismatch between intended physics and generated code the comprehension-generation gap. We instantiate this in MOOSE, where Kernel and BC objects map compositionally to weak-form residual terms, enabling deterministic reconstruction of the encoded PDE and comparison against an intended contract. We formalize this comparison as the Intent Fidelity Score (IFS), a structural metric covering governing terms, BCs, ICs, coefficients, and time scheme. Building on IFS, we develop a PDE-grounded refinement loop that uses deterministic violation reports to correct generated code iteratively. We evaluate on MooseBench, a 220-case multiphysics benchmark with PDE-level ground truth released with this work. On this benchmark, our method consistently improves mean IFS over direct generation, with gains concentrated on hard cases. On the subset where direct generation falls below IFS 0.7, refinement adds +0.22 to +0.41 absolute IFS. In the deployment audit, execution-only repair improves execution success while leaving 39-40% of all 220 cases runnable but still solving the wrong physics across the three main deployment-audit models, exposing executability and intent fidelity as separable failure modes. Static proof-of-concept experiments on four PDE-oriented DSLs (UFL/FEniCS, FreeFEM, FiPy, and Devito) suggest that the reconstruction-and-comparison pattern extends beyond MOOSE. These findings reinforce that executable simulation code should be verified against the mathematical structure it is intended to encode, not accepted on execution alone.

LLM code-generation pipelines often sample multiple candidates and select one final answer without access to a complete oracle. Existing pipelines mix textual voting, ranking, and execution-based agreement, but the relative contribution of each component remains unclear. We study 18 configurations across different models, thinking levels, and benchmarks, comparing output-pattern majority voting, weighted voting, MBR-Exec, and SemanticVote - a method that clusters candidates by execution fingerprints on LLM-generated inputs. Three findings emerge. (1) The best execution-based selector exceeds output-pattern majority voting by 19-52 percentage points on every configuration, with every execution-based selector exceeding it by at least 18 points. (2) Once candidates are executed on diverse inputs, aggregation rule has limited effect: SemanticVote, weighted voting, and MBR-Exec are statistically indistinguishable across all 18 configurations. The largest factor is input quality: sketch-based input generation consistently outperforms direct LLM generation by 0.6-2.1 pp and random fuzzing by up to 11.3 pp. (3) Thinking level interacts differently with selection families: deeper thinking improves majority voting by 12 pp but execution-based methods stay flat or degrade as candidate diversity falls. These results frame inference-time code selection as a signal-quality problem rather than an aggregation-rule problem: when oracles are unavailable, the behavioral evidence matters more than the aggregation rule.

Large language models can generate useful code from natural language, but their outputs come without correctness guarantees. Verifiable code generation offers a path beyond testing by requiring models to produce not only executable code, but also formal specifications and machine-checkable proofs. Progress in this direction, however, is difficult to measure: existing benchmarks are often small, focus on only one part of the pipeline, lack ground-truth proofs or rigorous specification validation, or target verification settings far from mainstream software development. We present VeriContest, a benchmark of 946 competitive-programming problems from LeetCode and Codeforces for verifiable code generation in Rust with Verus. Each problem pairs a natural language description with expert-validated formal specifications, judge-accepted Rust code, Verus-checked proofs, and positive and negative test suites. VeriContest is constructed through a three-phase pipeline that scales from manually verified seed problems to semi-automated expansion with human-in-the-loop review. To further strengthen benchmark quality, we use testing as an additional quality-assurance layer for validating postcondition completeness. VeriContest supports isolated and compositional evaluation of specification generation, code generation, proof generation, and end-to-end verified program synthesis. Evaluating ten state-of-the-art models reveals a sharp gap between coding ability and verifiable code generation: the strongest model reaches 92.18% on natural-language-to-code generation, but only 48.31% on specification generation, 13.95% on proof generation, and 5.29% end-to-end. These results identify proof and specification generation as the central bottlenecks for models and establish VeriContest as a rigorous platform for measuring and training future systems that generate code with machine-checkable correctness.

Local LLM-based coding agents increasingly work in settings where correctness is earned through execution feedback, persistent state, and bounded repair, not through a single fluent answer. Static retrieval, long-context prompting, self-refinement, execution-feedback repair, and reinforcement learning over model weights each address part of this setting, but they do not jointly provide validation-grounded episodic memory, adaptive retrieval-action selection, delayed credit assignment, and structural skill reuse around a frozen local model. We introduce PYTHALAB-MERA, a lightweight external controller for local validation-conditioned code generation. The frozen language model proposes complete source files; the controller decides which memory records and AST-derived skills should enter the next prompt, validates each candidate through a fail-fast pipeline, converts validation outcomes into bounded shaped rewards, and propagates delayed credit through TD(lambda)-style eligibility traces. We evaluate the implementation as a local CLI artifact on reinforcement-learning coding tasks with strict validation gates. In the measured hard RL setting with three tasks, three repetitions, and a three-attempt budget, PYTHALAB-MERA passed 8/9 strict validations; the self-refinement baseline and the investigated GRACE extension each passed 0/9. These results support a deliberately bounded claim: in this recorded setting, the external memory-and-retrieval controller improved validation success. They do not establish general-purpose code synthesis, state-of-the-art performance, formal program correctness, or formal safety.

LLM coding agents now generate code at an unprecedented scale, yet LLM-generated code introduces cybersecurity vulnerabilities into codebases without human involvement. Even when frontier models are explicitly asked to write secure production code with relevant weaknesses to avoid in context, we find that they still produce verifiable vulnerabilities on average 23% of the time across a corpus of 250 benign coding prompts. We introduce SecureForge, an automated pipeline that both audits security risks of frontier models and produces auditing-informed secure system prompts that reduce output security vulnerabilities while maintaining unit test performance. SecureForge first identifies benign prompts that produce statically detectable vulnerabilities, and then amplifies them into a large synthetic prompt corpus of diverse scenarios using a Markovian sampling technique to jointly maintain error rates and prompt diversity. This corpus is then used to iteratively optimize the system prompts to reduce output security vulnerabilities. On frontier models, SecureForge yields a statistically significant Pareto improvement in both unit test success and output security, with output vulnerabilities reduced by up to 48%. The resulting system prompts transfer zero-shot to in-the-wild coding agent prompts, without any exposure to real user prompt distributions during optimization.

AI agents are increasingly framed as software-engineering teammates, yet most studies examine them inside human-centered workflows. Little is known about the discourse autonomous AI agents produce when they interact mainly with one another. This paper examines what autonomous agents discuss on MoltBook, how that discourse is organized, and how it differs from human developer discourse. We combine human open coding of a 500-post sample, a concentration-plus-check topic-analysis pipeline over 4,707 English-filtered MoltBook technology posts, and a matched comparison with 5,211 human-generated GitHub Discussions posts. MoltBook technology discourse spans 12 recurring themes, led by Security and Trust (27.4%). At the community level, activity is highly concentrated: the largest submolt accounts for 63.5% of posts (Gini = 0.88), yet a stability-aware BERTopic pipeline still identifies 32 non-outlier sub-topics. Relative to the GitHub Discussions baseline, MoltBook discourse contains fewer concrete, context-rich cues such as code-formatted artifacts, environment details, runtime failures, and reproduction steps. Social mimicry appears only in limited form, while idealization is reflected mainly through lower hedging. Overall, AI-only technical discourse is coherent but selective. It repeatedly returns to security and trust, memory and context management, tooling and APIs, debugging and error handling, workflow automation, and infrastructure/ops, while omitting much of the project-local and runtime detail common in human developer discourse. This may reflect fewer environment-specific failures, reproduction steps, and other grounding cues in MoltBook.

We introduce SWE Atlas, a benchmark suite for coding agents spanning three professional software engineering workflows: Codebase Q&A (124 tasks), Test Writing (90 tasks), and Refactoring (70 tasks). SWE Atlas differs from prior SWE benchmarks in three key ways: it targets underrepresented but practically important task categories, uses comprehensive category-specific evaluation protocols, and adopts under-specified, agentic task formulations that better reflect real-world usage. Its evaluation framework combines programmatic checks with rubric-based assessment. This goes beyond functional correctness, evaluating software engineering quality, including test and refactor completeness, maintainability, reusable abstractions, and codebase hygiene. We evaluate a range of frontier and open-weight models on SWE Atlas and find that GPT-5.4 and Opus 4.7 achieve the strongest overall performance, while even the best open-weight models score poorly. Our analysis suggests that top models rely on extensive codebase exploration and runtime-driven reasoning. However, even top models consistently struggle with subtle edge cases, complex runtime analysis, and adherence to software engineering best practices. Overall, SWE Atlas provides a complementary evaluation suite for measuring both correctness and engineering quality in coding agents.

Mechanistic interpretability papers increasingly use causal vocabulary: circuits, mediators, causal abstraction, monosemanticity. Such claims require explicit identification assumptions. A purposive audit of 10 papers across four methodological strands finds no dedicated identification-assumptions section and a recurring pattern: validation metrics such as faithfulness, completeness, monosemanticity, alignment, or ablation effects are reported as causal support without stating the assumptions that make them identifying. A two-human-coder audit on $n=30$ reproduces the direction of the main finding: dedicated identification sections are absent, and validation-metric substitution is common, though exact Dim B/D counts are coding-rule sensitive. The paper proposes a disclosure norm: state whether the claim is causal, name the identification strategy, enumerate assumptions, stress at least one, and explain how conclusions shift if assumptions fail. Validation is not identification.

The Danish Technological Institute (DTI) focuses on transferring advanced technologies (including robots) to the industry and the public sector. One key application is laptop refurbishment using specialized robots, aimed at promoting reuse, reducing electronic waste, and supporting the European Circular Economy Action Plan. The software of such robots often includes features that use object detection models to detect objects for various purposes, such as identifying screws for laptop disassembly or detecting stickers to remove them. Ensuring the robustness of such models to small input variations remains a critical challenge, and addressing it is important to avoid potential damage to laptops during refurbishment. In this paper, we propose PROBE, a search-based robustness testing approach that leverages multi-objective optimization to identify minimal, localized perturbations that expose failures in object detection models used in the software of laptop refurbishing robots. PROBE employs NSGA-II to systematically explore the perturbation space, optimizing for failure induction considering both localization and confidence, and perturbation magnitude, while enabling the discovery of diverse failure cases. Results show that PROBE is 3$\times$ to 7$\times$ more effective than random search in generating failure-inducing perturbations, while requiring smaller perturbation magnitudes, and that the generated perturbations transfer across models. We further show that metamorphic relations provide additional insights into model robustness, enabling the assessment of stability even in non-failing cases.

LLM-based game generation promises to turn natural-language specifications into executable games, but progress is limited by the lack of reliable automated verification. Unlike conventional code generation, game correctness is defined over long-horizon interaction: a game may appear correct while violating core mechanics such as state updates, interaction rules, and phase transitions. Existing Agent-as-a-Verifier approaches collapse verification into open-ended gameplay, making verdicts reachability-bound, time-consuming, coverage-limited, and sensitive to the agent's gameplay ability. We present GameGen-Verifier, an automated verification paradigm for LLM-generated games that decomposes a specification into verifiable keypoints and grounds them into independent verification units. Each unit patches the game runtime into a concrete target state, executes a bounded interaction, and judges the outcome against the keypoint assertion. We implement GGV-Harness, a scalable agentic harness providing concurrency management, runtime isolation, and fault recovery. On VeriGame, our dataset of 100 games across seven genres, GameGen-Verifier achieves up to 92.2% accuracy against human judgments versus 58.8% for the coverage-enforced Agent-as-a-Verifier baseline, while reducing wall-clock time by up to 16.6x.

Qualitative analysis plays a pivotal role in understanding the human and social aspects of software engineering. However, it remains a demanding process shaped by the subjective interpretation of individual researchers and sensitive to methodological choices such as prompt design. Recent advancements in Large Language Models (LLMs) offer promising opportunities to support this type of analysis, although their reliability in reproducing human qualitative reasoning under varying prompting conditions remains largely untested. This study presents a controlled empirical evaluation of three LLMs -- Claude Haiku, DeepSeek-Chat, and Gemini 2.5 Flash -- across two prompt engineering strategies (zero-shot and multi-shot closed coding), using Cohen's kappa as the primary agreement metric over ten independent runs per configuration. Results suggest that multi-shot prompting significantly improves agreement for Claude Haiku (Delta kappa = +0.034, Wilcoxon p = 0.004) but not for DeepSeek-Chat or Gemini 2.5 Flash. Intra-model stability varies substantially -- DeepSeek-Chat and Claude Haiku exhibit the lowest variance (SD approx. 0.017), while Gemini 2.5 Flash is the least stable (SD = 0.038). A systematic over-prediction of "Sharing Negative Feedback" is identified across all models (bias ratios up to 5.25x), alongside consistent under-prediction of "Expressing Concerns." Collectively, these findings provide empirical evidence for prompt engineering guidelines in LLM-assisted qualitative coding for software engineering research.

The integration of machine learning (ML) into complex software systems has increased challenges in collaboration and communication (CoCo) of the teams building these systems. ML engineering (MLE) teams often involve diverse roles, ML engineers, data scientists, software engineers, and domain experts, each bringing unique goals, experiences, and jargon. These interdisciplinary dynamics can make it challenging to deploy, reproduce, and maintain ML-enabled systems over the long term. Previous studies have uncovered several CoCo challenges and practices, but most have focused on software-centric companies, leaving limited empirical understanding of how these dynamics unfold in hardware-centric contexts. In hardware-centric environments, CoCo challenges are shaped by additional constraints such as strict data governance, long development cycles, and tight coupling with physical processes, which amplify coordination complexity and reduce flexibility. To strengthen empirical understanding in such settings, we present a qualitative investigation of MLE teams within a global semiconductor company, where ML-enabled systems and manufacturing processes introduce additional complexity. We interviewed 12 practitioners regarding CoCo practices, tools, challenges, and approaches. Through analysis, we identified 16 recurring challenges, with unclear roles and responsibilities emerging as the most critical, and common practices and recommendations practitioners considered effective in mitigating CoCo problems. While grounded in a single organizational context, our findings align with known issues in interdisciplinary ML-enabled systems development, but also demonstrate how these challenges manifest differently under hardware-driven constraints. Our results highlight directions for future research and tool support to strengthen CoCo in MLE projects and ensure the success of ML-enabled systems.

Code-agent RL often receives weak feedback: rollout-time signals are reliable and executable, but capture only necessary or surface conditions for task success rather than the target semantic predicate. Using agentic compile-fix as the setting, we study signal reshaping for standard GRPO under such feedback. Our central claim is that GRPO's within-group comparison is meaningful only after three kinds of signals are reshaped: outcome rewards recover semantic ranking, process signals localize intra-trajectory credit, and rollouts from the same prompt remain execution-comparable. We operationalize these conditions with a minimal signal-reshaping construction that leaves GRPO's group-normalized advantage construction unchanged: compile-and-semantic layered rewards reshape trajectory ranking, step-level process scores outside group reward normalization reshape within-trajectory update strength, and failure-cause-aware rollout governance reshapes within-group comparability. Experiments show a clear end-to-end gain: full signal-reshaped GRPO improves strict compile-and-semantic accuracy from the base model's zero-shot $0.385$ to $0.535$. Controlled comparisons further explain the source of this gain: binary rewards remove the compile-only middle tier and degrade trajectory control; on top of layered rewards, process-score weighting further improves accuracy from $0.48$ to $0.53$ and reduces average evaluation steps from $23.50$ to $17.02$. As a boundary comparison, privileged-prompt token-level distillation mainly optimizes local distributional alignment; in long tool-use trajectories, this signal is diluted by non-critical tokens and cannot replace outcome semantics, process credit, or within-group comparability.

Beyond training-time optimization, scaling test-time computation has emerged as a key paradigm to extend the reasoning capabilities of Large Language Models (LLMs). However, most existing methods adopt a rigid Planning-before-Trial (PbT) policy, which inefficiently allocates test-time compute by incurring planning overhead even on directly solvable problems. We propose Planning-after-Trial (PaT), an adaptive policy for code generation that invokes a planner only upon verification failure. This adaptive policy naturally enables a heterogeneous model configuration: a cost-efficient model handles generation attempts, while a powerful model is reserved for targeted planning interventions. Empirically, across multiple benchmarks and model families, our approach significantly advances the cost-performance Pareto frontier. Notably, our heterogeneous configuration achieves performance comparable to a large homogeneous model while reducing inference cost by approximately 69%.

Generative modeling over discrete structures underpins applications across deep learning, from biological sequence design and code generation to large language models, yet generation often remains sequential, relying on autoregressive decoding or iterative refinement. In this work, we introduce Coupling Models(Coupling Models), a one-step discrete generative model that learns a direct coupling between discrete sequences and Gaussian latents. Unlike recent distillation methods that compress a pretrained multi-step sampler into a few steps, Coupling Model trains a purpose-built decoder to invert this coupling and generate samples in a single step. The model also avoids complex continuous flows over the simplex and hand-specified data-to-noise couplings. Empirically,Coupling Model improves the strongest one-step baselines in each domain: it reduces LM1B text-generation perplexity by 33% at its lowest-perplexity operating point, Fly Brain enhancer-design FBD by 18%, and MNIST-Binary FID by 46%. These results suggest that effective one-step discrete generation depends strongly on how data and noise are coupled before decoding. Code is available at https://github.com/pengzhangzhi/Coupling-Models.

Large Language Models for code generation frequently produce hallucinations in Fill-in-the-Middle (FIM) tasks -- plausible but incorrect completions such as invented API methods, invalid parameters, undefined variables, or non-existent imports. These failures pass superficial review yet introduce runtime errors. We introduce Delulu, a verified multi-lingual benchmark of 1,951 FIM samples across 7 languages and 4 hallucination types. Samples are curated through an adversarial pipeline: a frontier LLM generates plausible hallucinations, four diverse judge models evaluate them, embedding-based clustering mines progressively harder examples, self-contained Docker containers verify that golden completions compile while hallucinated variants produce the expected runtime error, and a final human-expert review removes any remaining biased or trivially decidable samples. We evaluate 11 open-weight FIM models from five families spanning 0.5B-32B parameters: a six-point Qwen2.5-Coder scaling slate, plus a cross-family slate (CodeLlama, DeepSeek-Coder-V2, StarCoder2). The strongest model reaches only 84.5% pass@1, no family exceeds 0.77 Edit Similarity, and every family produces hallucination-aligned completions on a non-trivial share of samples, confirming that the difficulty exposed by Delulu is task-intrinsic rather than family-specific. We release the benchmark, containers, and evaluation framework at https://github.com/microsoft/delulu.

Architectural code smells erode software maintainability and are costly to repair manually, yet unlike localized bugs, they require cross-module reasoning about design intent that challenges both developers and automated tools. While large language model agents excel at bug fixing and code-level refactoring, their ability to repair architectural code smells remains unexplored. We present the first empirical evaluation of LLM agents on architectural code smell repair. We contribute SmellBench, a task orchestration framework that incorporates smell-type-specific optimized prompts and supports iterative multi-step execution, together with a scoring methodology that separately evaluates repair effectiveness, false positive identification, and net codebase impact. We evaluate 11 agent configurations from four model families (GPT, Claude, Gemini, Mistral) on 65 hard-severity architectural smells detected by PyExamine in the Python project scikit-learn, validated against expert judgments. Expert validation reveals that 63.1% of detected smells are false positives, while the best agent achieves a 47.7% resolution rate. Agents identify false positives with up to $κ= 0.94$ expert agreement, but repair aggressiveness and net codebase quality are inversely related: the most aggressive agent introduces 140 new smells. These findings expose a gap between current LLM capabilities in localized code transformations and the architectural understanding needed for cross-module refactoring. SmellBench provides reusable infrastructure for tracking progress on this underexplored dimension of automated software engineering. We release our code and data at https://doi.org/10.5281/zenodo.19247588.

The rise of Internet of Things (IoT) devices in the physical world necessitates voice-based interfaces capable of handling complex user experiences. While modern Large Language Models (LLMs) already demonstrate strong tool-usage capabilities, modeling real-world IoT devices presents a difficult, understudied challenge which combines modeling spatiotemporal constraints with speech inputs, dynamic state tracking, and mixed-initiative interaction patterns. We introduce MIST (the Multimodal Interactive Speech-based Tool-calling Dataset), a synthetic multi-turn, voice-driven code generation task that operates over IoT devices. We find that there is a significant gap between open- and closed-weight multimodal LLMs on MIST, and that even frontier closed-weight LLMs have substantial headroom. We release MIST and an extensible data generation framework to build related datasets in order to facilitate research on mixed-initiative voice assistants which reason about physical world constraints.

Large Language Model (LLM) agents demonstrate strong performance in autonomous code generation under loose specifications. However, production-grade software requires strict adherence to structural constraints, such as architectural patterns, databases, and object-relational mappings. Existing benchmarks often overlook these non-functional requirements, rewarding functionally correct but structurally arbitrary solutions. We present a systematic study evaluating how well agents handle structural constraints in multi-file backend generation. By fixing a unified API contract across 80 greenfield generation tasks and 20 feature-implementation tasks spanning eight web frameworks, we isolate the effect of structural complexity using a dual evaluation with end-to-end behavioral tests and static verifiers. Our findings reveal a phenomenon of constraint decay: as structural requirements accumulate, agent performance exhibits a substantial decline. Capable configurations lose 30 points on average in assertion pass rates from baseline to fully specified tasks, while some weaker configurations approach zero. Framework sensitivity analysis exposes significant performance disparities: agents succeed in minimal, explicit frameworks (e.g., Flask) but perform substantially worse on average in convention-heavy environments (e.g., FastAPI, Django). Finally, error analysis identifies data-layer defects (e.g., incorrect query composition and ORM runtime violations) as the leading root causes. This work highlights that jointly satisfying functional and structural requirements remains a key open challenge for coding agents.

Large language models (LLMs) are now largely involved in software development workflows, and the code they generate routinely includes third-party library (TPL) imports annotated with specific version identifiers. These version choices can carry security and compatibility risks, yet they have not been systematically studied. We present the first large-scale measurement study of version-level risk in LLM-generated Python code, evaluating 10 LLMs on PinTrace, a curated benchmark of 1,000 Stack Overflow programming tasks. LLMs tend to specify version identifiers when directly prompted at 26.83%-95.18%, while down to 6.45%-59.19% in creating a manifest file directly. Among the specified versions, 36.70%-55.70% of tasks contain at least one known CVE, and 62.75%-74.51% of them carry Critical or High severity ratings. In 72.27%-91.37% of cases, the associated CVEs were publicly disclosed before the model's knowledge cutoff. The statistics show all models converge on the same small set of risky release versions, indicating a systemic bias rather than isolated model error. Static compatibility rates range from 19.70% to 63.20%, with installation failure as the dominant cause. The dynamic test cases confirm the pattern by 6.49%-48.62% pass rates. Further experiments confirm that these failures are attributable to version selection rather than code quality, and that externally anchored version constraints substantially reduce both vulnerability exposure and compatibility failures. Our findings reveal LLM version selection as a first-class, previously overlooked risk surface in LLM-based development. We disclosed these findings to the community of the evaluated models, and several confirmed the issue. All the code and dataset have been released for open science at https://github.com/dw763j/PinTrace.

Autonomous agents based on Large Language Models (LLMs) are increasingly being utilized in complex software systems. However, reliability remains a significant challenge due to unpredictable failures such as hallucinations, execution errors, and inconsistent reasoning. This paper proposes a reliability-aware self-healing framework for LLM-based software agents. The framework integrates failure detection, reliability assessment, and automated recovery mechanisms. First, we define a taxonomy of failure types and introduce a quantitative reliability assessment model. Next, we propose a failure detection method that identifies abnormal agent behavior based on execution patterns and output consistency. Finally, we design a self-healing mechanism that dynamically recovers from failures through adaptive replanning and corrective prompting strategies. The proposed framework was implemented in a multi-agent workflow environment and evaluated using real-world task scenarios. Experimental results demonstrate that our approach significantly increases task success rates, reduces failure propagation, and enhances overall system robustness compared to existing methods. In particular, this study distinguishes itself by establishing an integrated monitoring system that combines the agent's internal reasoning process with external execution results. These findings are expected to contribute to securing the stability of advanced autonomous systems and lowering the barriers to LLM adoption in production environments.

Most coding-agent benchmarks ask whether generated code behaves correctly. That remains essential, but repository-level engineering is increasingly agent-managed: one agent writes a repository, and later agents inspect, audit, or extend it as working context. In that setting, a generated repository is not only an answer to a task but also a communication artifact for future work. Even when strong agents nearly satisfy the visible behavioral objective, repositories can differ in how clearly they expose the intended behavior and design choices behind that behavior. We introduce BUILD-AND-FIND, a protocol for evaluating whether downstream agents can recover those intended choices from generated repositories, and how much inspection that recovery requires. For each task, a builder sees a hidden repository specification and creates a codebase; a finder sees only the codebase and a specification-traced multiple-choice question bank. The protocol separates behavioral correctness from artifact-side recovery and reports recovery accuracy, repeatability, implementation coverage, and inspection effort. Accuracy and stability act as gates: effort is interpreted only when recovery succeeds reliably. Among artifacts from which the same intent can be recovered, lower effort by the same finder suggests that the artifact makes that intent easier to locate. Question-only and spec-only controls quantify generic priors and specification access, while audits separate omitted claims from finder failures and check whether correct answers cite artifact evidence. In the released high-prior task pack, recovery accuracy is near saturation, so inspection effort and finder-specific effects provide the main panel-local comparison.

When language model agents tackle complex software engineering tasks, they often degrade over long trajectories, which we define as agent drift. We focus on two recurring failure modes overthinking and overacting, i.e., where the agent repeatedly reasons over information it already has, and where it issues tool calls without integrating recent observations or acquiring new evidence. In this paper, we introduce TACT (Think-Act Calibration via activation Steering), to detect and mitigate agent drift in the residual stream before it surfaces as a behavioral failure. In specific, we label trajectory steps as overthinking, overacting, or calibrated, and find that their hidden states can separate linearly along two drift axes, pointing from calibrated behavior toward each failure mode (AUC $\approx$ 0.9). To mitigate agent drift, we project each step's activation onto these axes at test time and pull drifted ones back toward the calibrated region. Experiments show that TACT outperforms unsteered baselines across SWE-bench Verified, Terminal-Bench 2.0, and CLAW-Eval, lifting average resolve rate by $+5.8$ pp on Qwen3.5-27B and $+4.8$ pp on Gemma-4-26B-A4B-it while cutting steps-to-resolve by up to $26\%$. These gains frame agent drift as a steerable direction in the residual stream, and position TACT as a viable handle for reliable long-horizon agents.

Language models often generate reasoning before giving a final answer, but the visible answer does not reveal when the model's answer preference became stable. We study this question through a narrow computable object: \emph{finite-answer preference stabilization}. For a model state and specified answer verbalizers, we project the model's own continuation probabilities onto a finite answer set; in binary tasks this yields an exact log-odds code, $δ(ξ)=S_θ(\mathrm{yes}\midξ)-S_θ(\mathrm{no}\midξ)$. This target defines parser-based answer onset, retrospective stabilization time, and lead without relying on greedy rollouts or learned probes. In controlled delayed-verdict tasks with Qwen3-4B-Instruct, the contextual finite-answer projection stabilizes before the answer is parseable, with 17--31 token mean lead in the main templates and positive, shorter lead in a parser-clean replication. The signal tracks the model's eventual output rather than truth, is linearly recoverable from compact hidden summaries, is partly separable from cursor progress, and transfers as shared information without a single invariant coordinate. Diagnostics separate the measurement from online stopping, verbalizer-free belief, and causal answer control; exact steering shows local sensitivity of $δ$ but not reliable generation control.

Large language model (LLM)-based coding assistants have made substantial progress, yet most systems remain reactive, requiring developers to explicitly formulate their needs. Proactive coding assistants aim to infer latent developer intent from integrated development environment (IDE) interactions and repository context, thereby reducing interaction overhead and supporting more seamless assistance. However, research in this direction is limited by the scarcity of large-scale real-world developer behavior data. Existing studies therefore often rely on LLM-simulated IDE traces, whose fidelity to real development behavior remains unclear. In this paper, we investigate this simulation-to-reality gap through a large-scale empirical study. We collect real IDE interaction traces from 1{,}246 experienced industry developers over three consecutive days using a custom Visual Studio Code extension, and construct paired LLM-simulated traces for controlled comparison. Our analysis shows that simulated traces differ substantially from real traces in behavioral diversity, temporal structure, and exploratory patterns. Based on the collected data, we introduce \textbf{ProCodeBench}, a real-world benchmark for proactive intent prediction. Experiments with representative LLMs, retrieval-augmented methods, and agentic baselines show that current approaches remain far from reliable under real IDE traces, suggesting that simulation-based evaluation can overestimate real-world performance. Finally, our training study shows that simulated data cannot replace real data, but can complement it when used before real-world fine-tuning. These findings highlight the importance of real developer behavior data for evaluating and training proactive coding assistants.

Multi-agent LLM systems for code generation face a fundamental routing problem: the optimal orchestration topology depends on the structural complexity of the code under modification, yet existing systems select topologies without consulting the codebase. We present Retrieval-Guided Adaptive Orchestration (RGAO), an architecture that closes this loop by extracting a structural complexity vector from a hierarchical code index before selecting the orchestration topology. RGAO operates within Code-Agent, a multi-agent framework whose sub-agents are governed by formal contracts with six-dimensional budget vectors. Our headline contribution is the composition of two previously separate lines of work -- complexity-conditioned LLM routing and formal resource algebras -- yielding a property neither admits alone: provable budget conservation under retrieval-conditioned dynamic topology selection. Concretely we contribute: (1) a complexity-conditioned topology router that reduces proxy-measured misrouting from 30.1% to 8.2%; (2) a budget algebra with a structural-induction conservation theorem; and (3) a hierarchical code retrieval engine. Empirical evaluation demonstrates sub-millisecond DAG construction and linear tree-index scalability.

Coding agents are rapidly changing the landscape of software development, moving from inline completion to autonomous systems that edit repositories, open pull requests, respond to issues, and run scheduled or webhook triggered routines across the development life cycle. The next generation is increasingly described as proactive and long-horizon: agents should notice relevant changes before the developer asks, connect signals across tools, decide when to interrupt, and carry preferences across sessions. Yet the field still lacks a clear account of what proactivity means for software development, how it differs from autonomy, what acceptance criteria proactive long-horizon tasks should satisfy, and which metrics determine whether unsolicited agent behavior is useful rather than merely active. Proactive coding agents should be evaluated by the quality and improvement of their insight policy: the policy that decides what matters next, what evidence supports it, whether to show it, and how to adapt after feedback. This view is grounded in the principles of mixed initiative interaction. We propose a three level taxonomy of proactivity (Reactive, Scheduled, and Situation Aware), compare contemporary coding agents against five practical criteria, and sketch an active user simulation protocol with three evaluation targets: Insight Decision Quality (IDQ), Context Grounding Score (CGS), and Learning Lift

The rapid adoption of AI coding agents has produced a dominant workflow pattern -- often called "vibe coding" -- that prioritizes speed of implementation over deliberate preparation. We argue that this approach creates a systematic alignment problem: agents that lack sufficient context produce code requiring extensive debugging and refactoring, consuming substantial development time. Drawing on the culinary concept of mise en place (everything in its place; abbreviated MEP), we propose a three-phase preparation methodology for agentic coding: (1) contextual grounding, where domain expertise and tacit knowledge are externalized into structured documents; (2) collaborative specification, where human-agent dialogue produces detailed design artifacts; and (3) task decomposition, where specifications are converted into structured, dependency-aware task records. We report on the application of MEP during a competitive hackathon, where roughly two hours of preparation enabled a rapid parallel implementation of a full-stack educational platform by concurrent AI agents. We introduce the concept of context fluency as an emerging developer skill -- the ability to create rich, structured context that agents can act on -- and connect it to established frameworks in backward design and tacit knowledge externalization. We conclude with a research agenda for empirically validating preparation-phase methodologies in AI-assisted software development.

Code translation is one of the core capabilities of LLMs. However, evaluating the correctness of translations remains difficult, as commonly used metrics such as BLEU measure only syntactic similarity, disregarding program semantics. We propose a novel evaluation methodology for code translation tasks, emphasizing semantic equivalence over surface-level string similarity. Our approach applies established compiler testing methodology to a new domain, allowing the assessment of an LLM fine-tuned for binary lifting tasks (i.e. decompiling binaries to higher-level representations). We introduce a semantic correctness score, defined as the proportion of translations that produce correct execution outcomes, and demonstrate its application by evaluating LLM-based and heuristic decompilers. Our findings show that LLM-based approaches significantly outperform heuristic ones, while BLEU scores show negligible correlation with semantic correctness (r = -0.127 to 0.354), demonstrating that syntactic metrics fail to predict functional accuracy.

We evaluate an initial coding-agent system for ARC-AGI-3 in which the agent maintains an executable Python world model, verifies it against previous observations, refactors it toward simpler abstractions as a practical proxy for an MDL-like simplicity bias, and plans through the model before acting. The system is intentionally direct: it uses a scripted controller, predefined world-model interfaces, verifier programs, and a plan executor, but no hand-coded game-specific logic. The agent-facing prompts, workspace, and controller contain no game-specific code, game-specific prompts, hand-coded heuristics, hidden solutions, or other game-specific information; the same agent and prompts are used across games. Because the coding agent has broad system access, we audit unintended information channels, describe earlier vulnerable harnesses, and explain how the current harness closes observed leakage channels while reducing benchmark-specific information exposure. We report results on the 25 public ARC-AGI-3 games. Each playthrough starts from a fresh agent instance and clean workspace, with no access to files or conversation state from earlier playthroughs. With GPT-5.5 high reasoning effort, the agent fully solved 15 games and achieved a mean per-game RHAE of 58.12%. With GPT-5.4 high reasoning effort, it fully solved 8 games and achieved a mean per-game RHAE of 41.29%. Performance on the private validation set, which is not yet available to us, remains to be tested. Overall, the results provide preliminary evidence that verifier-driven executable world models are a promising approach for ARC-AGI-3 agents. Full run artifacts are released with the code at https://github.com/astroseger/arc-3-agents-baseline1.

AI-assisted development tools enable rapid prototyping of services but often lack awareness of architectural constraints, infrastructure dependencies, and organizational standards required in production environments. Consequently, generated artifacts may exhibit brittle behavior and limited deployability. We propose a retrieval-augmented scaffolding approach that combines platform-based code generation with agentic clarification loops to expose and resolve architectural constraint ambiguities. By combining template retrieval with structured interaction, the method embeds production-relevant considerations during service scaffolding. Evaluation indicates improved architectural consistency and deployability compared to general-purpose AI code generation workflows, suggesting that constraint-aware retrieval is essential for aligning AI-assisted service development with production software engineering practices.

Large language models (LLMs) show strong potential for neural architecture generation, yet existing approaches produce complete model implementations from scratch -- computationally expensive and yielding verbose code. We propose Delta-Code Generation, where fine-tuned LLMs generate compact unified diffs (deltas) to refine baseline architectures rather than synthesizing entire models. Our pipeline iteratively fine-tunes the LLM via LoRA on curated architectures from the LEMUR dataset, with MinHash-Jaccard novelty filtering for structural diversity. We evaluate three 7B-class LLMs -- DeepSeek-Coder-7B, Qwen2.5-Coder-7B, and Mistral-7B -- across six datasets (CIFAR-10, CIFAR-100, MNIST, SVHN, ImageNette, CelebA) using a 22-cycle protocol (1,100 candidates per LLM). All three substantially surpass the full-generation baseline (50.6% valid rate, 42.3% mean first-epoch accuracy): DeepSeek-Coder reaches 75.3% valid rate and 65.8% mean accuracy; Qwen2.5-Coder 72.1%/64.6%; Mistral 66.6%/66.1%. On CIFAR-10, best first-epoch accuracies reach 85.5% (Mistral), 85.2% (DeepSeek), 80.6% (Qwen) -- well above 63.98% full generation and 71.5% for the concurrent approach of Gu et al. Output lengths are 30-50 lines versus 200+ for full generation (75-85% reduction). A 50-epoch study confirms the 1-epoch proxy preserves rankings (Mistral: Spearman $ρ$ = 0.926). Delta-based generation is a token-efficient, multi-domain, LLM-agnostic alternative to full-model synthesis for LLM-driven NAS.

Large language models (LLMs) frequently generate defective outputs in code generation tasks, ranging from logical bugs to security vulnerabilities. While these generation failures are often treated as model-level limitations, empirical evidence increasingly traces their root causes to imperfections within the training corpora. Yet, the specific mechanisms linking training data quality issues to generated code quality issues remain largely unmapped. This paper presents a systematic literature review of 114 primary studies to investigate how training data quality issues propagate into code generation. We establish a unified taxonomy that categorizes generated code quality issues across nine dimensions and training data quality issues into code and non-code attributes. Based on this taxonomy, we formalize a causal framework detailing 18 typical propagation mapping mechanisms. Furthermore, we synthesize state-of-the-art detection and mitigation techniques across the data, model, and generation lifecycles. The reviewed literature reveals a clear methodological shift: quality assurance is transitioning from reactive, heuristic-based post-generation filtering toward proactive, data-centric governance and closed-loop repair. Finally, we identify open challenges and outline research directions for developing reliable LLMs for code through integrated data curation and continuous evaluation. Our repository is available at https://github.com/SYSUSELab/From-Data-to-Code.

We present CodeEvolve, an evolutionary framework for improving program performance and code quality with Large Language Models (LLMs). CodeEvolve extends OpenEvolve with runtime-guided target selection, Monte Carlo Tree Search (MCTS), automated code refinement, and language-specific evaluation pipelines for Java and Salesforce Apex. The system uses Java Flight Recorder (JFR) profiles to build weighted component graphs and select optimization targets that account for most execution cost, reducing reliance on manual bottleneck identification. For each target, CodeEvolve generates candidate edits, evaluates them through build validation, unit tests, performance checks, static analysis, and LLM-based review, and retains only variants that preserve functional correctness. Across real-world optimization tasks, CodeEvolve improves performance and code metrics while maintaining correctness. On a large enterprise Java codebase, it achieves an average speedup of 15.22$\times$ across seven hotspot functions and outperforms single-pass LLM optimization on five of them. An ablation study on Apex optimization shows that the full MCTS-augmented configuration produces 19.5 valid programs out of 20 on average, indicating that search, filtering, and refinement each contribute to more reliable optimization.

The emergence of "vibe coding" platforms, where users describe applications in natural language and AI agents autonomously generate full-stack software, has created a need for rigorous evaluation beyond code-level benchmarks. In order to assess them as virtual software development agencies on understanding business requirements, making architectural decisions, writing production code, handling iterative modifications, and maintaining business readiness, we introduce SWE-WebDev Bench, a 68-metric evaluation framework spanning 25 primary and 43 diagnostic metrics across seven groups, organized along three dimensions: Interaction Mode (App Creation Request (ACR) vs. App Modification Request (AMR)), Agency Angle (Product Manager (PM), Engineering, Ops), and Complexity Tier (T4 multi-role SaaS, T5 AI-native). Our evaluation (six platforms, three domains, 18 evaluation cells) reveals four recurring shortcomings in the current generation of AI app builders: (1) A specification bottleneck, where platforms compress rich business requirements into oversimplified technical plans, (2) A pervasive frontend-backend decoupling, where visually polished UIs mask absent or broken backend infrastructure, (3) A steep production-readiness cliff, where no platform scores above 60% on engineering quality and post-generation human effort varies substantially across platforms and (4) Widespread security and infrastructure failures, with no platform exceeding 65% Security Score against a 90% target and concurrency handling as low as 6%. These observations are descriptive of our sample and require larger-scale replication to establish generality. We release SWE-WebDev Bench as a community benchmark to enable such replication and help platform builders identify and address these gaps. Code and benchmark resources are available at: https://github.com/snowmountainAi/webdevbench and https://webdevbench.com/.

AI coding assistants and autonomous agents are becoming integral to software development workflows, reshaping how code is produced, reviewed, and maintained. While recent research has focused mainly on the capabilities and impacts of productivity of these systems, much less attention has been paid to accountability: who is responsible when agents generate, modify, or recommend code? In practice, accountability is defined through the Terms of Service (ToS) and related policy documents that govern the use of AI-powered development tools. In this vision paper, we present a comparative analysis of the Terms of Service for widely used AI coding assistants and agent-enabled development tools. We examine how these documents allocate ownership, responsibility, liability, and disclosure obligations between tool providers and software developers, and we identify common patterns and divergences between providers. Our analysis reveals a consistent tendency to shift responsibility for correctness, safety, and legal compliance onto users, as well as substantial variation in how providers address issues such as indemnification, data reuse, and acceptable use. Based on these findings, we argue that existing policy frameworks are poorly aligned with increasingly agent-mediated and autonomous software development workflows. We outline a research roadmap for accountable agents in software engineering, identifying challenges and opportunities for modeling responsibility, designing governance artifacts, developing tooling that supports accountability, and conducting empirical studies of developers' perceptions and practices.

Large Language Model ensembles improve reasoning accuracy, but only up to a performance boundary beyond which additional deliberation degrades accuracy. We introduce DASE (Deliberative Adaptive Stopping Ensemble), a stopping heuristic for iterative ensemble deliberation that commits early on genuine consensus and applies a global-frequency fallback on fragmented evidence. We make three contributions. (1) DASE produces a commit-type routing partition that generalises across benchmarks and is complementary to verbalized single-call confidence. On GPQA-Extended (N=546, 70B ensemble), the partition yields a 39.5 pp routing gap (right-wall 81.1% vs. left-wall 41.5%). On AIME 2010-2023 (N=261, 120B ensemble, 3 seeds), right-wall commits reach 98.3% accuracy vs. left-wall 72.8% (25.5 pp gap), statistically equivalent to Opus 4.6 Standard verbalized confidence at matched coverage (25.7 pp gap; bootstrap p=0.873); the two mechanisms disagree on 37% of routing assignments. (2) Adaptive stopping, not injection bandwidth, drives accuracy. On AIME-300, bandwidth accounts for only 0.3 pp (ns). On GPQA-Extended at the 120B tier, sparse injection ($\approx15$ tokens/worker/round) achieves 70.9% with a 30.7 pp routing gap; dense injection ($\approx600$ chars/worker/round) achieves 72.2% but with halved right-wall coverage and a narrower 18.9 pp gap. (3) Injection-based methods exhibit an inverted-U accuracy-vs-inference trajectory; this pattern is hypothesis-generating.

SemEval-2026 Task 13 investigates machine-generated code detection across multiple programming languages and application scenarios, asking participating systems to generalize to unseen languages and domains. This paper describes our participation in Subtask A (binary classification) and explores both pretrained code encoders and lightweight feature-based methods. We design ratio-based features that are less sensitive to snippet length. To support the extraction of descriptiveness-related signals, we use parsing engines and a programming-language classifier. Additionally, we train a separate code-vs-text line classifier to identify raw natural language segments embedded within samples. We combine a shallow decision tree with heuristic rules derived from data analysis to produce the final predictions. Our approach is computationally efficient, requires only CPU resources for training, and achieves near-instant inference time, offering a lightweight alternative to large pretrained models.

Coding agents often pass per-prompt safety review yet ship exploitable code when their tasks are decomposed into routine engineering tickets. The challenge is structural: existing safety alignment evaluates overt requests in isolation, leaving models blind to malicious end-states that emerge from sequenced compliance with innocuous-looking requests. We introduce MOSAIC-Bench (Malicious Objectives Sequenced As Innocuous Compliance), a benchmark of 199 three-stage attack chains paired with deterministic exploit oracles on deployed software substrates (10 web-application substrates, 31 CWE classes, 5 programming languages) that treats both exploit ground truth and downstream reviewer protocol as first-class evaluation axes. On this benchmark, nine production coding agents from Anthropic, OpenAI, Google, Moonshot, Zhipu, and Minimax compose innocuous tickets at 53-86% end-to-end ASR with only two refusals across all staged runs. In a matched direct-prompt experiment over four frontier Claude/Codex agents, vulnerable-output rates fall to 0-20.4%: Claude primarily refuses, while Codex primarily hardens rather than emitting the vulnerable implementation - ticket staging silences both defense modes simultaneously. Downstream, code reviewer agents approve 25.8% of these confirmed-vulnerable cumulative diffs as routine PRs, and a full-context implementation protocol closes only 50% of the staged/direct gap, ruling out context fragmentation as the sole explanation. As a deployable but non-adaptive mitigation, reframing the reviewer as an adversarial pentester reduces evasion across the evaluated reviewer subset; pentester framed evasion ranges from 3.0% to 17.6%, and an open-weight Gemma-4-E4B-it reviewer under this framing detects 88.4% of attacks on the dataset with a 4.6% false-positive rate measured on 608 real-world GitHub PRs.

This paper analyzes the strategic education process aimed at transitioning traditional software development squads into hybrid structures centered on collaborative work between humans and Artificial Intelligence (AI). In a context where human-AI collaboration can significantly increase productivity, this study explores how the upskilling of XPTO professionals, referred to as AI Advocates, acts as a catalyst for cultural and technical transformation. The objective is to present an experience report on the education and enablement process of AI Advocates within a private Brazilian technology company, highlighting key lessons learned and identified challenges.

Large language models (LLMs) are widely recognised for their applications in natural language generation and are increasingly used for code generation tasks. However, concerns about bias in their generated outputs remain significant. This paper focuses on GPT-4o and Gemini, mainstream tools for code generation, and proposes a framework for evaluating bias in LLM-generated code, specifically examining the influence of protected attributes, prompts and web-search capability. We use two metrics: the code bias score (CBS) and the attribute change ratio (ACR), to quantify the prevalence of bias and the degree of influence of different attributes, respectively. In addition, we investigate four lightweight mitigation strategies: Few-Shot, Chain-of-Thought, Few-Shot Chain-of-Thought, and Multi-agent, aimed at mitigating bias in generated code. Our findings reveal that bias remains prevalent across different protected attributes and datasets even after applying mitigation strategies, highlighting the need for more effective approaches to reduce bias in AI-driven code generation systems.

Turning ideas into full software projects from scratch has become a popular use case for language models. Agents are being deployed to seed, maintain, and grow codebases over extended periods with minimal human oversight. Such settings require models to make high-level software architecture decisions. However, existing benchmarks measure focused, limited tasks such as fixing a single bug or developing a single, specified feature. We therefore introduce ProgramBench to measure the ability of software engineering agents to develop software holisitically. In ProgramBench, given only a program and its documentation, agents must architect and implement a codebase that matches the reference executable's behavior. End-to-end behavioral tests are generated via agent-driven fuzzing, enabling evaluation without prescribing implementation structure. Our 200 tasks range from compact CLI tools to widely used software such as FFmpeg, SQLite, and the PHP interpreter. We evaluate 9 LMs and find that none fully resolve any task, with the best model passing 95% of tests on only 3% of tasks. Models favor monolithic, single-file implementations that diverge sharply from human-written code.

As autonomous agents become increasingly sophisticated, validating their sequential behavior presents a significant challenge. Traditional testing approaches require manual specification, exact sequence matching, or thousands of training examples. We present a novel algorithm that automatically learns correct behavior from just 2-10 passing execution traces and validates new executions against this learned model. Our approach combines dominator analysis from compiler theory with multimodal large language model-powered semantic understanding to identify essential states and handle non-deterministic behavior. The system constructs a generalized ground truth model using Prefix Tree Acceptors, merges traces through multi-tiered equivalence detection, and validates new executions via topological subsequence matching. In controlled experiments, our system achieved high accuracy in detecting product bugs and false successes using only 3 training traces. This approach provides explainable validation results with coverage metrics and works across diverse domains including UI testing, code generation, and robotic processes.

Automated program repair at repository scale requires an agent to locate a fault among thousands of files and synthesize a correct patch. Existing graph-based agents represent how a repository is organized into files, classes, and functions, but they do not model how variable values flow within a procedure, which leaves the agent without the semantic precision that function-level and line-level localization demand. We present ARISE (Agentic Repository-level Issue Solving Engine), a framework-agnostic toolset that builds a multi-granularity program graph, extending structural relationships down to statement-level nodes connected by intra-procedural definition-use edges, and exposes it through a three-tier tool API that mounts on any tool-use agentic framework. The central primitive is data-flow slicing, a queryable agent tool that traces in a single call which statements define or consume a variable of interest. On SWE-bench Lite (300 real GitHub issues across 11 Python repositories) with the open-source Qwen2.5-Coder-32B-Instruct backbone, mounting ARISE on SWE-agent as the host resolves 22.0% of issues (66/300), a 4.7 percentage-point gain over the unmodified SWE-agent baseline under the identical backbone and host. We show this gain is largely attributable to sharper localization, with Function Recall@1 (R@1) rising from 0.43 to 0.60 (a 40% relative gain) and Line R@1 from 0.26 to 0.41 (a 58% relative gain). Controlled ablations attribute the improvement to the data-flow graph rather than the tool schema, and we further mount the same toolset on a second host framework to study its portability. Decoupled from any single scaffold, the graph builder and slicing API form a drop-in toolset for future repair research.

The promise of Large Language Models in automated software engineering is often measured by functional correctness, overlooking the critical issue of long term maintainability. This paper presents a systematic audit of technical debt in AI-generated software, revealing that AI does not eliminate flaws but rather introduces a distinct machine signature of defects. Our multi-scale analysis, spanning single-file algorithmic tasks and complex, agent generated systems, identifies a fundamental Reasoning-Complexity Trade-off: as models become more capable, they generate increasingly bloated and coupled code. This architectural decay is so pronounced that we establish a Volume-Quality Inverse Law, where code volume is a near perfect predictor of structural degradation. Crucially, we demonstrate that neither functional correctness nor detailed prompting mitigates this decay. These findings challenge the current paradigm of prompt-driven generation, reframing the central problem of AI-based software engineering from one of code generation to one of architectural complexity management. We conclude that future progress depends on equipping agents with explicit architectural foresight to ensure the software they build is not just functional, but also maintainable.

State-of-the-art Large Language Models (LLMs) excel in code generation at the function level. However, the output quality significantly declines when scaling to repository-level systems. Current workflows relying only on natural language prompts suffer from inherent ambiguity and a lack of verifiability. To address this, we propose structured spec-driven engineering (SSDE), a paradigm that leverages structured artifacts to guide LLM generation. We argue that structured specifications as LLM inputs make high-quality, repository-level code generation a tangible goal, while at the same time offering superior verifiability, leading to significant potential for improvement. We first investigate the feasibility of this vision through a pilot study generating Model-View-Controller (MVC) business logic for three software systems using five LLMs, and then highlight the potential, challenges, and future roadmap for SSDE.

Software engineering increasingly involves making high-stakes decisions under uncertainty, using signals from code, field data, and socio-technical processes. Recent AI-driven support (e.g., anomaly detection, predictive analytics, AIOps, as well as LLM-based agents) has amplified engineers' ability to detect patterns and synthesize content and recommendations, but many critical questions are interventional or counterfactual: What is the expected impact of changing a load-balancing strategy? Would an outage have been avoided under a different release plan? Correlational models answer "what tends to co-occur"; they struggle to answer "what would happen if we act." We propose Causal Software Engineering (CSE) as a future paradigm in which causal models and causal reasoning systematically inform activities across the software lifecycle, augmenting existing practices with explicit assumptions, uncertainty-aware effect estimates, and counterfactual diagnosis. We outline (i) a causal-first workflow view spanning development and operations, (ii) a staged roadmap for tools and organizational adoption, and (iii) an evaluation and benchmark agenda for measuring progress.

Molecular Vibe Coding, a paradigm where chemists interact with LLMs to generate executable programs for molecular tasks, has emerged as a flexible alternative to chemical agents with predefined tools, enabling chemists to express arbitrarily complex, customized workflows. Unlike general coding tasks, molecular coding imposes a distinctive challenge that LLMs should jointly equip programming, molecular understanding, and domain-specific reasoning capabilities. However, existing benchmarks remain disconnected. General code generation benchmarks such as HumanEval and SWE-bench require no chemistry knowledge, while chemistry-focused benchmarks such as S^2-Bench and ChemCoTBench evaluate knowledge recall or property prediction rather than executable code generation. To bridge this gap, we introduce MolViBench, the first benchmark tailored for Molecular Vibe Coding. MolViBench comprises 358 curated tasks across five cognitive levels, ranging from single-API recall to end-to-end virtual screening pipeline design, spanning 12 real-world drug discovery workflows. To rigorously assess generated code, we also propose a multi-layered evaluation framework that combines type-aware output comparison and AST-based API-semantic fallback analysis, which jointly measures executability and chemical correctness. We systematically evaluate 9 frontier coding LLMs and compare three real-world Molecular Vibe Coding paradigms, providing a practical and fine-grained testbed for diagnosing LLMs' coding capabilities in AI-accelerated molecular discovery.

Frontier software engineering agents have saturated short-horizon benchmarks while regressing on the work that constitutes senior engineering: long-horizon, multi-engineer, ambiguous-specification deliverables. This paper takes a position on what training data is needed to close the gap. The substrate for the next generation of SWE agents is neither larger GitHub scrapes nor more solo-agent trajectories nor -- sufficient by itself -- open human-AI dialogue logs. It is triadic data: synchronized capture of the human-human conversations where engineering context is formed, the human-AI sessions where that context is partially consumed, and the multi-week cross-functional work that surrounds both. We argue that the canonical instantiation of triadic data is two complementary products: long-horizon expert trajectories captured under stimulated-recall protocols, and simulated cross-functional companies -- instrumented teams of senior engineers, product managers, designers, and data scientists working through ambiguous deliverables on shared infrastructure. We further specify a four-tier evidence framework through which any such corpus -- triadic or otherwise -- must justify its quality to a fine-tuning researcher: mechanical verification, statistical corpus characterization, probe experiments, and pre-registered blind evaluation. We argue that this data is capturable in 12-18 months with methods already mature in adjacent fields, that it is the empirical key to four open questions in agent training, and that the field's near-term research agenda should include it explicitly.

Conventional commits provide a structured format for writing commit messages, which improves readability, software maintenance, and enables automation tools such as changelog generators and semantic versioning systems. Existing approaches to conventional commit classification typically rely on ML/DL models trained on large labeled datasets. In this paper, we investigated a training-free alternative by leveraging large language models (LLMs) through prompt engineering. Rather than building a task-specific classifier, we evaluate three prompting strategies, such as zero-shot, few-shot, and chain-of-thought, across three open-source LLMs of varying scale: Mistral-7B-Instruct, LLaMA-3-8B, and DeepSeek-R1-32B. Classification is performed directly on code diffs extracted from a balanced dataset of 3,200 commits mined from the InfluxDB repository, without any model fine-tuning. Our results show that few-shot prompting consistently achieves the highest accuracy, while chain-of-thought prompting does not yield additional gains for this classification task. Among the evaluated models, DeepSeek-R1-32B achieves the strongest overall performance, suggesting that model scale plays a meaningful role in conventional commit classification. These findings provide practical guidance for researchers and practitioners seeking to automate commit classification without the overhead of curating and maintaining labeled training data.

This paper describes the system submitted by team \textbf{Archaeology} to SemEval-2026 Task~13 on AI-generated code detection. The shared task consists of three subtasks; we participate in Subtask-A (binary classification: human-written vs.\ AI-generated code) and Subtask-B (11-class attribution of the generating model). Starting from a TF-IDF and Logistic Regression baseline, we fine-tune four pre-trained code models (CodeBERT, GraphCodeBERT, UniXcoder, and CodeT5+) with separate strategies for each subtask. For Subtask-A, we use leave-one-language-out cross-validation, code augmentation, chunked inference with trimmed-mean aggregation, and threshold calibration on a difficult dataset. For Subtask-B, we use sandwich token packing, class-balanced loss, and multi-seed ensembling with test-time augmentation. Our best submissions obtain macro-F1 scores of 0.737 on Subtask-A (6th/81 teams) and 0.422 on Subtask-B (7th/34 teams).

Large language model (LLM) coding agents increasingly operate over repositories, terminals, tests, and execution traces across long software-engineering episodes. Persistent memory is useful, but static vector stores or generic retrieval-augmented generation (RAG) are insufficient for reinforcement-learning (RL) code development, where small details can alter Bellman targets, terminal masks, gradient flow, or validation claims. This paper presents RL Developer Memory, a local-first, Model Context Protocol (MCP)-native developer-memory architecture for RL coding agents. It treats memory selection as a logged contextual decision process: issue_match ranks candidates and records telemetry, issue_feedback maps raw labels to bounded rewards, and issue_record_resolution links verified resolutions to earlier retrieval events. A deterministic ranker remains deployed, while a contextual-bandit residual policy runs in shadow mode and can affect canary behavior only through conservative off-policy-evaluation (OPE) gates. RL/control memories require theory-to-code metadata and review-gated governance. The system is evaluated on a deterministic 200-case benchmark with RL algorithm bugs, hard negatives, review-gated RL/control cases, and low-risk failures. In the same-commit comparison, deterministic control and full shadow/OPE both achieve 80.0% expected-decision accuracy and 100.0% hard-negative suppression; the full configuration adds learning telemetry rather than accuracy gain. Static validation passed 11/11 checks; dynamic integration passed 10/10 cases. The evidence reports limits: active learned-policy deployment and official-client MCP interoperability are unsupported, live full-configuration latency regresses, and 40 residual non-RL failures remain. The contribution is an auditable memory-control architecture with explicit claim boundaries, not a universal coding-agent improvement claim.

Maintaining reliable UI test suites in large-scale enterprise applications is a persistent and costly challenge. We present an industrial case study of a multi-agent autonomous testing system evaluated using anonymized execution data from a production-like enterprise UI testing prototype. The application features several hundred dynamic UI elements per screen. Built on a large language model with LangGraph orchestration, Playwright execution, and a RAG knowledge base, the system evolves from human-directed testing toward High-autonomy feature discovery and test execution: given no explicit test targets, it discovers over 100 testable features across 10 UI screens, dynamically expands coverage by an additional 15--30 features through runtime DOM analysis, and iteratively repairs failing tests without human intervention. We analyzed 300 consecutive autonomous execution reports encompassing 636 individual test-case executions across 10 distinct scenario families. The system achieved a 70% repair convergence rate at the scenario-family level, with a mean of 3.4 repair iterations to convergence. However, only 10% of scenario families succeeded on first attempt, 38% of reports failed to produce any executable test artifact, and we documented concrete instances of assertion weakening and test-case deletion used as workaround mechanisms to achieve superficial convergence. Our findings show that unrestricted autonomy leads to unstable and often misleading outcomes, while constrained autonomy transforms such systems into operationally viable workflows. Rather than advocating full autonomy, our findings suggest that reliable autonomous testing in enterprise-scale settings requires explicit constraints, validation boundaries, and human oversight to preserve semantic correctness and operational trustworthiness.

Recent advancements in Large Language Models (LLMs) have demonstrated significant potential across a wide range of software engineering tasks, including software design, an area traditionally regarded as highly dependent on human expertise and judgment. However, there has been little research focusing on how LLMs are used in software design, nor on the associated benefits and drawbacks. This paper aims to bridge this gap by empirically investigating how software developers utilize LLMs in the context of software design. We conduct a mixed-methods study, combining a mining study of 291 developer-ChatGPT conversations shared on GitHub with a survey of 65 software practitioners. Our findings reveal nine distinct categories of design tasks supported by ChatGPT, including architecture design, data model design, and the use of design patterns. We further characterize developer-ChatGPT interactions, showing that developers primarily use ChatGPT for knowledge acquisition and design-related code generation, with most tasks situated at the detailed design level. The study identifies seven key benefits of utilizing LLMs in software design as perceived by developers, such as better technology selection and the early detection of design flaws. We also uncover six limitations, including the generation of overly lengthy and difficult-to-read outputs, the creation of inexecutable or incorrect code, and a heavy reliance on context that can lead to hallucinated results. These findings provide an evidence-based characterization of current LLM use in software design from both open-source and practitioner perspectives, highlighting a tension between perceived benefits and limitations, which lays a foundation for future research and the development of effective techniques and tools to integrate LLMs into software design practices.

Geometric Algebra (GA) presents challenges to learners due to its highly abstract mathematical structure and complex operational rules, as translating algebraic manipulations into concrete geometric interpretations is a non-intuitive process when developing related code. Currently, some existing GA software packages rely on manually written scripts for code generation and visualization, but their high learning curve hinders widespread adoption. Meanwhile, methods based on Large Language Models (LLMs) often produce logical errors when generating specific GA scripts, such as GAALOPScript, resulting in generally low accuracy. To address these issues, this study proposes GA-VisAgent -- a multi-agent interactive learning application for GA code generation and visualization -- building upon a Geometric algebra large language model (GAGPT). Integrating task planning mechanisms with ReAct reasoning strategies, GA-VisAgent can decompose complex operations into five standardized subtasks, including core operations like geometric products, rotations, and reflections. It supports natural language and mathematical formulas as input to automatically generate executable code, accompanied by interactive visualizations to aid user comprehension. Experimental results show that GA-VisAgent achieved a 90% code generation success rate across 40 typical Conformal GA tasks, representing a 70% improvement over GPT-4o. This application introduces an extensible new paradigm for teaching GA and developing visualization tools for related mathematical concepts. The online service for this project will be available at http://gagis.cn/gacrac.