Papers

As small language models (SLMs) are increasingly deployed on resource-constrained and on-device platforms, including as components of agentic systems, the integrity of locally stored model parameters becomes an important safety concern. We investigate whether safety-sensitive behavior in LLaMA-2-7B-Chat is concentrated within a sparse subset of parameters, creating a reduced fault surface for targeted analysis. We study two complementary localization methods: low-rank safety-associated subspace analysis and parameter-level safety–utility importance filtering. Both approaches reveal highly non-uniform safety sensitivity across the network, with the MLP down_proj consistently emerging as a prominent safety-sensitive component and o_proj providing a smaller contribution. Using parameter-level localization, modifying only 0.19% of model weights in down_proj yields 53% Basic ASR and 56% GCG ASR, while tinyBenchmarks accuracy remains at 51.6% compared with a 52.2% unmodified baseline. These results motivate targeted fault analysis and selective integrity protection for language models deployed in resource-constrained, on-device, and agentic settings.

The Go programming language provides a lightweight abstraction for concurrent programming through goroutines, which are prone to deadlocks. Go includes a runtime detector that aborts execution when all threads are blocked (a global deadlock). However, due to nondeterministic thread scheduling, this runtime mechanism only detects global deadlocks that manifest during execution and cannot identify partial deadlocks, where a subset of goroutines is permanently blocked while at least one remains runnable. Statically detecting local deadlocks is essential for developing dependable concurrent software. While several tools statically detect deadlocks in concurrent programs, few assist developers in fixing them. Detecting and resolving partial deadlocks requires reasoning about complex interleavings and communication patterns, an inherently challenging task. In this paper, we present GoDDaR, a tool that detects unobserved global or partial deadlocks in Go programs and suggests concrete fixes. GoDDaR translates Go source code into an intermediate representation reflecting message-passing communication events and composition patterns. Partial deadlocks are identified through symbolic analysis over this representation. To resolve detected deadlocks, our algorithms transform the intermediate representation to eliminate problematic synchronization patterns, allowing GoDDaR to generate fix suggestions for the original Go source code as a diff. We evaluate GoDDaR on a benchmark suite of representative deadlock examples from literature and git repositories to validate algorithm correctness and compare performance against the state of the art. Results demonstrate that GoDDaR is competitive with top approaches in partial deadlock detection and advances the state of the art in automated deadlock fixing.

Context: Psychological safety is an important human and behavioral factor in software development teams, supporting collaboration, knowledge sharing, interpersonal risk-taking, and learning. However, evidence in software engineering remains fragmented across team processes, performance outcomes, contextual conditions, barriers. Objective: This study maps literature on psychological safety in software engineering, examining its conceptualization, associations with team performance and processes, contextual influences, barriers, and strengthening strategies. Method: We conducted a systematic mapping study following established software engineering guidelines. We analyzed 112 primary studies published between 2006 and June 2026 using descriptive statistics and thematic analysis across six research questions. Results: Psychological safety emerges as a multidimensional, context-dependent, team-level construct characterized by interpersonal risk-taking, open communication, collaboration, learning, trust, and supportive interaction. It is predominantly associated with productivity, software quality, innovation, team satisfaction, collaboration, communication, and decision-making. These relationships are shaped by leadership, organizational culture, work environment, trust, and sociocultural and individual conditions. Recurring barriers include communication problems, organizational constraints, leadership issues, diversity and inclusion challenges, and workload pressures. Although diverse practices are reported, evidence of their effectiveness and long-term sustainability remains limited. Conclusion: Psychological safety is a multidimensional, context-dependent team-level construct associated with team interaction and performance. This study highlights the need for longitudinal, context-sensitive research on psychological safety interventions in software development environments.

Modern software-intensive systems increasingly incorporate GenAI components, including LLM and agentic subsystems, which introduce novel and compounding sources of uncertainty across system layers. The self-adaptive systems community has made significant strides in understanding and managing uncertainty. The intrinsic characteristics of GenAI, including probabilistic outputs, hallucinations, context window limitations, and memory staleness, demand a re-examination of existing frameworks and mitigation strategies for dealing with uncertainty, and especially, the interactions among uncertainty occurrences and manifestations. This position paper posits an initial conceptual framework that establishes preliminary guidelines for characterizing and mitigating uncertainty interactions in GenAI-based software-intensive systems. We argue that mitigation must be considered across the full software lifecycle, encompassing requirements analysis, design-time decisions, and run-time adaptations, which implies the unfeasibility of decoupling it from monitoring and analysis at execution. We introduce the notion of a mitigation function that maps uncertainty interaction categories, involved uncertainty types, system design characteristics, criticality, and mitigating architectural tactics to impacted quality attributes and corresponding tradeoffs. As a proof of concept, we apply the framework to three illustrative use cases: LLM serving, AI-driven software operations, and agentic cloud management.

As coding agents increasingly undertake real-world work autonomously, judging whether their risk treatments are warranted has become important. Existing work evaluates related agent behaviors from separate perspectives, but lacks a systematic framework for unifying these behaviors. To bridge this gap, we introduce ParanoiaEval, the first benchmark for unified evaluation of risk-treatment capabilities in coding agents. Grounded in the well-established Avoidance-Transfer-Mitigation-Acceptance framework in software engineering risk management, ParanoiaEval operationalizes its 4 fundamental treatments for coding-agent settings and contains 200 evidence-controlled repository-level task pairs, each differing only in treatment-defining evidence. We further introduce dedicated metrics for risk-treatment violations and evidence responsiveness, using a human-calibrated agentic judge for reliable evaluation. Large-scale experiments on 8 representative models and a post-hoc human study reveal that (I) unnecessary risk treatment occurs in 11.2%-58.7% of runs despite explicit evidence, with substantial variation across agent configurations; (II) stronger task capability does not ensure more appropriate risk treatment, while treatment violations substantially harm developers' experience, establishing risk treatment as an independent capability dimension; and (III) agents exhibit systematic patterns consistent with established risk-management findings, suggesting that knowledge from human practice can guide the diagnosis and improvement of this capability.

Software-engineering agents can enable people without formal software training to build systems they could not otherwise implement and simultaneously can produce more code than even experts can meaningfully inspect. In both cases, exhaustive code review is not reliable as the sole basis for human control. We report a case study of a production healthcare platform built through coding agents and governed by an operator without formal software-engineering training. Over time, its workflow grew into a human-led meta-agent system where one agent wrote code, other agents supervised and reviewed it, and project rules carried lessons forward. The operator found that tests, monitors and reviewing agents used to supervise the system were fallible. Some monitors measured proxies rather than outcomes, some audits failed silently, missing checks disappeared from reported results and one automated repair caused operational disruption. In this case, human control depended on keeping the intended outcome, the evidence used to judge it, the agents' permissions and the final human decision were all tied to the same underlying objective.

Recent game design agents have made substantial progress in generating playable games. However, program correctness does not ensure an enjoyable experience for players. We present Recursive Game Creator, an experience-oriented harness to advance agentic game development from rough game prototypes into entertaining games. Recursive Game Creator organizes recursive development around four components: Designer, Builder, Player, and Reviewer. The Designer translates user instructions and Reviewer's feedback into detailed plans. The Builder turns these plans into candidate games. The coding-native Player creates and executes reusable policies through programmatic interfaces to efficiently collect diverse gameplay trajectories, mitigating evaluation bias caused by slow GUI-based collection. The Reviewer uses carefully designed trajectory-based metrics to induce player preferences, integrating with visual evidence and explicit textual preferences to evaluate games against game-specific criteria. Finally, the Reviewer accepts the better version and provides improvement reviews for the next round, closing the recursive loop. Our method achieves state-of-the-art overall performance of 77.89 on GameCraft-Bench. On GameASG-Bench, it achieves a strict task success rate of 53.2%, a 34.1% improvement over the same-model baseline, and the highest mean runtime-check pass rate at 93.4% among compared methods. A user study shows longer playtime and higher ratings. Code is coming soon.

Execution feedback lets coding agents revise programs and learn from their own corrections. A correction's learning weight should reflect both the transitions supported by its executions and the amount of evidence behind that support. We introduce Effective-Evidence Self-Distillation (EESD), which represents these quantities separately. Normalized execution relevance determines relative transition support and an effective pseudo-count mass; a Dirichlet posterior then produces an uncertainty-penalized weight for KL-anchored correction learning. Under a symmetric prior, changing mass preserves category ordering, and effective mass yields a supervised coefficient bounded by its matched fixed-mass counterpart. Across four model-domain history sweeps, increasing visible observations from one to eight reduces future-outcome NLL by 55.0-59.3%. At eight observations, effective mass achieves lower NLL than fixed mass in all four comparisons. In the primary matched DeepSeek/RunBugRun study, argmax predictions agree on all 3,000 examples, with the largest NLL gain under concentrated relevance. After one correction-learning round, DeepSeek/CodeARC all-tests Pass@1 increases from 15.0% to 20.4%, with a paired 95% source-bootstrap interval of [+2.8, +8.0] percentage points. The twelve-setting downstream evaluation establishes the model-domain scope of this update. These results show how separating evidence support from evidence mass changes probability estimation and correction learning in coding agents.

Smart contracts written in Solidity manage assets, permissions, and irreversible state changes, making code generation both useful and security-critical. Repository-level Solidity generation is challenging because models must synthesize complete contracts or libraries while preserving consistency across state variables, modifiers, events, inheritance, external calls, and access-control logic. We present RAPO-Sol, a two-stage training framework for repository-level Solidity code generation. First, Retrieval-Augmented Fine-Tuning (RAFT) augments each training input with similar Solidity examples, helping the model learn recurring contract-level patterns while remaining retrieval-free at inference time. Second, Direct Preference Optimization (DPO) trains the model to prefer reference contracts over close but semantically flawed alternatives. We construct rejected samples using Solidity Semantic-Anchor Perturbation (SAP), which perturbs validation statements, visibility modifiers, data-location keywords, context variables, payment operations, and low-level calls. Experiments on SolidityBench with CodeLlama-7B-Instruct, DeepSeek-Coder-6.7B-Instruct, and Qwen2.5-Coder-7B-Instruct show that RAFT consistently improves over supervised fine-tuning, while SAP-based DPO provides further gains in BLEU and SolidityScore. The full RAFT+DPO pipeline achieves the best performance across all three models, demonstrating complementary benefits from retrieval during training and Solidity-aware preference optimization without adding retrieval cost at inference.

Large Language Models have emerged as promising tools for software vulnerability analysis, but their effectiveness depends heavily on prompt design. Existing research primarily compares prompting strategies using aggregate performance metrics, providing limited insight into why models fail or how prompts can be improved systematically. We propose Failure-Driven Prompt Refinement (FDPR), a methodology that analyzes recurring model failures to guide evidence-based prompt refinement. Using the Damn Vulnerable Java Application (DVJA), we identify recurring failure modes, including false positives, false negatives, unsupported reasoning, and CWE misclassification, and translate them into targeted prompt refinements. We then evaluate the resulting prompt on the Juliet Test Suite and perform cross-model validation to assess generalizability. The results show that failure-driven refinement improves the reliability of LLM-based vulnerability analysis while yielding reusable prompt design principles. More broadly, this work demonstrates that recurring model failures provide a principled foundation for prompt engineering, enabling the systematic development of more reliable LLM-based vulnerability analysis systems.

Large Language Models (LLMs) are widely used to generate code. Although their functional plausibility keeps improving, the generated code often contains security vulnerabilities. The functionality-security gap captures code that passes functional tests but fails security tests. A recent longitudinal study of three model families concluded that LLMs become smarter but not safer, with the only considered open-weight family stagnating. Whether this holds for other (open-weight) families and particularly for compact models remains open. We present a longitudinal study of the gap across 32 LLMs from seven model families (five open-weight), covering three successive releases per family in flagship and compact variants. Using CWEval with 119 tasks in five programming languages and 31 CWEs, we compare trajectories across families, model sizes, and languages. Newer models do become safer in absolute terms, although no family closes the gap. Unlike prior work, we find that openness does not separate the families: every considered open-weight family narrows the gap significantly, while Gemini 3.1 Pro keeps a gap as wide as the one reported for Llama. Compact models usually produce less secure code than their flagship counterparts, with notable exceptions (e.g., Gemini 3.7 Flash). At the CWE level, we confirm persistent weaknesses such as log injection (CWE-117) and HTTP response splitting (CWE-113) and regressions in the newest proprietary models on memory and integer weaknesses, and show that the same CWE carries very different risk across languages. From these results, we derive implications for LLM vendors, researchers, and developers. In particular, developers should assume neither that upgrades improve security nor that proprietary models are more secure; they should rerun security checks after each model change and provide secure APIs in the model's context.

Awkward Array is a widely used library in high-energy physics (HEP) for representing and manipulating nested, variable-length data in Python. Previous CHEP contributions have explored GPU acceleration for Awkward Array, demonstrating the feasibility and performance benefits of CUDA-based backend while also identifying limitations related to irregular data access, fine-grained kernel launches, and composability of operations. In this contribution, we present recent developments that build directly on these earlier efforts by introducing a CUDA execution model for Awkward Array based on the Python CUDA Core Compute Libraries (CCCL). Using CCCL, we eliminate the need for custom CUDA kernels and can instead use a high-level Python interface. The CCCL-based approach also enables fusion of multiple Awkward operations into a reduced number of CUDA kernels, addressing kernel launch overhead observed in earlier GPU implementations. Lazy execution allows expression graphs to be constructed and optimized prior to kernel generation, improving performance for analysis workflows involving jagged arrays, combinatorial operations, and reductions. In contrast to earlier approaches, this design also emphasizes extensibility, allowing user-defined Python code to be incorporated into GPU execution paths with minimal boilerplate and without breaking existing analysis semantics. We present performance studies that demonstrate improvements over previously reported eager GPU execution strategies for representative HEP analysis patterns. These developments extend the GPU capabilities of Awkward Array toward a more composable and sustainable backend, aligned with the needs of Python-based analysis at the HL-LHC and beyond.

Automated Program Repair (APR) with language models is usually evaluated by whether a generated patch passes the test suite, which can hide differences in maintainability, security, and computational cost. We propose a Weighted Quality Index (QI), inspired by the ISO/IEC 25010 software quality model, that combines functional correctness, maintainability, security, and generation efficiency under configurable weighting schemes. We evaluate three dense Qwen2.5-Coder models (3B, 7B, 14B) and the 16B-parameter DeepSeek-Coder-V2-Lite Mixture-of-Experts (MoE) model (2.4B active parameters) on 40 QuixBugs and 90 Defects4J bugs, all run locally on identical hardware to control for infrastructure effects. Model rankings change with the weighting scheme, showing that single-metric evaluation can hide trade-offs. The MoE model shows almost no statistically significant difference in correctness from the 7B and 14B dense models (McNemar's exact test) while using 3-6 times fewer active parameters, whereas correctness increases significantly across the three dense scales. These results suggest that active parameter count can be a more informative lens than total parameter count for sparse code models.

Mathematical problem solving often requires deterministic computational steps that agents delegate to tools and implicitly trust. Yet tools can fail silently, returning plausible but incorrect results. How well can agents detect and correct corrupted tool call outputs? We study this through a controlled corruption framework where a hidden interceptor replaces tool call results with plausible incorrect information on targeted problems. We evaluate agents across 31 problems under four verification designs including no verification (baseline), mandatory same-context reflection, optional fresh-context verification, and optional structural verification. Without verification, corruption causes dramatic accuracy loss, from 100% down to 72.4%. Mandatory reflection fully recovers this performance to 100%. Optional verification improves accuracy only when models actively invoke it. Our results show that checking frequency is strongly associated with robustness differences, while unequal invocation prevents a controlled comparison of verifier quality. A supporting recovery experiment shows that full problem restart succeeds in 100% of cases after explicit detection. These findings demonstrate that verifier availability and verification policy are separate components of mathematical-agent reliability. Mandatory policies enforce verification while optional policies depend on the model's own choice to invoke it.

Repository-level software engineering (SWE) is a challenging long-horizon setting: agents must reason over extended interactions, use tools, and adapt to stateful environments. Recent work trains SWE agents with reinforcement learning methods such as Group Relative Policy Optimization (GRPO), which independently sample multiple trajectories per issue, test the resulting patches, and compare terminal rewards within a fixed group. However, this training setup does not reuse verifier feedback from failed patches as context for subsequent attempts, even though this feedback contains valuable diagnostic information about what went wrong. Training on recovery trajectories is challenging because the preceding outcome determines whether the next trajectory is generated, while the failed execution determines its conditioning context. We introduce FC-SWE, a failure-conditioned RL framework that incorporates recovery attempts into policy training. After a patch fails verification, FC-SWE restores the repository to its original task state and uses the failed patch and verifier feedback as context for a recovery trajectory. FC-SWE adapts GRPO to these chains of complete, multi-turn tool-use trajectories through two mechanisms. Trajectory-local rewards preserve each attempt's verifier outcome, preventing recovery success from rewarding an earlier failed patch. Active-set advantage estimation forms a comparison group from all initial and recovery trajectories actually executed for the same issue, so failed attempts remain in the group while unexecuted attempts are excluded. On all 500 SWE-bench Verified tasks under a verifier-assisted protocol, FC-SWE with Qwen3.5-4B and SWE-agent achieves 41.7% Resolved@1 and 52.8% Resolved@2, compared with 38.9% and 48.5% for GRPO. Although trained with at most two attempts per chain, FC-SWE reaches 70.7% Resolved@11 under an eleven-attempt test-time budget.

The Walloon Region commissioned this study to improve deaf people's access to public services for the new millennium. It focuses on sign language users, about 25,000 adults in the French-speaking Community, for whom written French is close to a foreign language. The core problem is a severe shortage of interpreters: only about twenty work in French-speaking Belgium, so appointments take weeks to arrange and emergencies cannot be covered. The study assessed three options. The recommended one, remote video interpretation, could be deployed at the time of writing: a professional interpreter joins the deaf person and the employee by videoconference, saving travel time and enabling an emergency service. Similar services already ran in Sweden, Finland, the Netherlands and France. Prototype tests in May 2003 were a clear success and showed that interpretation needs at least CIF video above 256 kbps, ideally 384 kbps. The system suits simple administrative tasks better than emotional, medical or legal situations. The second option, fully automated interpretation, was not yet feasible, although partial systems using speech recognition and signing avatars could already serve kiosks, websites and routine procedures. The third option looks further ahead: UMTS and WiFi could eventually support mobile signed video calls and remote interpretation, provided quality of service is guaranteed. The main recommendation is a first pilot in real conditions before any wide rollout, supported by high-bandwidth links as part of e-government modernisation. The system is meant to relieve interpreters, not replace them, so their training, status and numbers should improve. The authors also call for digital training for deaf people, awareness among public-service staff, more sign language content online, and a multidisciplinary avatar project with Belgian, French and European partners.

Large language models (LLMs) equipped with terminal access have demonstrated strong capabilities in automating software engineering tasks. However, existing agents remain brittle on long-horizon workflows, where they must repeatedly reconstruct program state scattered across source files, configurations, tests, dependencies, and runtime behavior, leading to increasingly long interaction histories, context explosion, and semantic drift. Large repositories further complicate the identification of task-relevant components. To address these challenges, we introduce Dev-Primitives (Development Primitives), a modular and executable abstraction that transforms repository components from passive software artifacts into active participants in software engineering. Each Dev-Primitive pairs a repository artifact with a resident LLM, which gives the artifact an agent-native interface grounded in its own implementation and dependencies, enabling natural-language reasoning, inter-component communication, and localized self-modification. Building on Dev-Primitives, we propose HERMES, a Harness Engineering framework for software engineeRing via Modular Executable Dev-PrimitiveS, which instantiates these primitives at repository scale through a dependency-aware dynamic activation mechanism and a bug diagnosis mechanism that maps execution evidence back to the components that must be revised. Extensive experiments on four software engineering benchmarks demonstrate that HERMES outperforms matched baseline harnesses by 12.4% on average. Moreover, when paired with strong activation and diagnosis models, HERMES, even with Qwen3-8B Dev-Primitives, remains within 4.5% of the homogeneous GPT-5.6 Sol configuration across all four benchmarks, while reducing inference cost by 26.2% on Terminal-Bench 4.0, highlighting the importance of harness design in software engineering agents.

Code generation models have been increasingly used in software development, but their development raises ethical-sourcing concerns involving intellectual property, privacy, fairness, labour practices, and environmental impact. Although prior work has defined ethical-sourcing criteria for code generation, it remains unclear how much evidence existing models disclose and where that evidence can be found. We introduce ES-Trace, a framework for ethical-sourcing disclosure audits that traces disclosed evidence beyond model cards using the Model Documentation Traceability Graph (MDTG), which represents relationships among models, versions, and documentation artifacts. We apply ES-Trace to 26 models from 10 publishers across 77 documents and 20 ES-CodeGen aspects. Model-card-only auditing yields a mean score of 1.77/5, while resolving the declared references increases it to 2.82/5, with most of the increase arising from documents that the publisher declares in structured metadata. The key findings of our study include: (1) social and labour-related aspects remain poorly documented, even when expanding the audit to the full documentation scope, (2) resolving documentation references substantially increases observed disclosure, raising the mean score from 1.77/5 to 2.82/5, (3) model-card-only audits can mischaracterize release-level disclosure changes, and (4) documentation mismatches can associate evidence with the wrong model or version, highlighting the need for explicit model–version binding and consistency across documentation artifacts. Our study calls for reference-aware ethical-sourcing disclosure audits, explicit model–version binding and consistency across documentation artifacts, and stronger documentation of currently underreported social and labour-related aspects.

Changes produced by coding agents can pass functional tests while leaving repository contribution requirements unmet. Following repository-specific norms requires identifying guidance dispersed across repository sources and interpreting its conditions and exceptions. Retrieval and documentation approaches supply general context, but agents must still determine which norms apply. We introduce RepoNorm to acquire explicit and implicit repository norms independently of coding tasks. It checks norm content and applicability using repository evidence, consults Git history when needed, and delivers norm packages to existing coding agents. Our evaluation uses three coding models and 121 tasks from RepoNormBench. Against the baseline with no additional generated guidance (Raw), relative improvements are 7.42-10.77% for Overall Norm Compliance Rate (NCR), 31.64-45.44% for Contribution NCR, and 11.34-17.69% for Prompt-omitted NCR. All three coding models also obtain higher values on these NCR measures with RepoNorm than with CodeWiki documentation. Functional success rates show observed gains of 5.79-9.09 percentage points over Raw; the paired comparisons do not reach the significance threshold. Sampled precision is 86% with RepoNorm's default configuration.

A memory system can retire an obsolete value and later restore it merely because the same old statement appears again. A re-read of an old source and a genuine revert can produce the same observed sequence of values while requiring opposite current answers. We study this ambiguity on 130 extractor-selected atomic transitions derived from software fixes. In the ordinary transition condition, identity-based temporal memory reaches 98.5% model-judged accuracy with zero observed errors under a literal stale-value proxy. Appending a verbatim re-read of the old statement reduces accuracy to 10.8% and raises the stale-value rate to 88.5%. A guard that refuses to reactivate a previously retired value restores accuracy to 97.7% and reduces that rate to 0.8% in this constructed re-read condition. The guard cannot also recognize a legitimate revert without additional change provenance. Two supporting studies examine exposing retired history to the answer model and supplying current source for changed behavior. An exploratory extraction study over 707 software fixes provides scope context, not a universal coverage estimate. The design implication is to distinguish an observation of a value from evidence that the value changed. Selected inputs, aggregate-only answer records, related-family judges and a post-failure guard evaluation limit the conclusions to the retained experiments.

Coding agent harnesses mediate tool use and authorize actions, yet their security mechanisms and runtime effects remain incompletely characterized. We present HarnessSecurity, the first systematic empirical study and benchmark of open- and closed-source coding agent harnesses. First, we derive a ten-mechanism taxonomy and then assess 400 harness-mechanism cells using independent ratings by researchers and large language model (LLM) judges. We find that about half of confirmed mechanism implementations are opt-in, while closed-source harnesses exhibit substantial evidence gaps. Second, we introduce HarnessSecurity-Bench, a benchmark of 23 tasks across five attack surfaces without sacrificing legitimate task requirements. Using separate deterministic oracles to measure task utility and attack effects with security setting comparisons, we evaluate nine mechanisms across six leading harnesses: Claude Code, Codex CLI, Gemini CLI, gptme, Qwen Code, and GitHub Copilot. Under a controlled LLM baseline GLM-5.2, we conduct 2,500 trials, recording 81,155 tool calls and over 2.2 billion tokens. Enabling auto-approve increases utility and raises attack success from 29.2% to 95.6%. Network isolation and read-only mode reduce attack effects with substantial utility losses, while command allowlisting and command denylisting reduce attack effects with a small utility loss and a utility gain, respectively. Task-level cases show that restrictions on a shared capability can obstruct both legitimate and malicious operations, and that allowed tools or commands can leave unauthorized operations reachable through alternative execution paths. Harness providers should make security settings verifiable, test alternative execution paths to protected operations, and assess attack effects alongside task utility and execution costs.

Compiler-introduced security bugs (CISBs) arise when an optimization, lowering, or instrumentation decision changes a security-relevant property of the generated program. They are difficult to study because their evidence is distributed across issue reports, reduced tests, historical configurations, and compiler artifacts; a security-related report also does not imply that every associated reduction establishes a security-bearing compiler failure. We present CISB-Bench, an auditable dataset of 429 exact C-program rows mined from GCC and LLVM. Each row contains its C reduction, a standardized LLVM IR analysis bundle at -O0 through -O3, public provenance, a final binary label, and a primary mechanism or boundary annotation. Two reviewers independently labeled the fixed corpus, agreeing on 369 rows (86.0%, Cohen's kappa=0.662); the 60 disagreements were adjudicated. The final dataset comprises 280 CISBs and 149 hard non-CISB cases. The prediction task is to recover this reviewed exact-row label from the supplied artifacts; it is not a claim that standardized IR alone reproduces every historical compiler failure. We characterize the security mechanisms and evidence boundaries represented by the corpus, and demonstrate how its paired artifacts support source-only, IR-aware, and joint analyses. CISB-Bench provides a reusable, inspectable target for compiler-security mining and detection research.

Static-analysis checker synthesis requires agents to interpret a defect specification, inspect a repository, implement analyzer-specific logic, and refine the checker through repeated compilation and analysis feedback. Existing coding-agent benchmarks focus on tasks such as patch generation or vulnerability detection and rarely assess whether an agent can develop a working checker in a repository from start to finish. We introduce CheckerBench, an executable benchmark of 300 tasks derived from 297 CVEs across 167 repositories, 85 CWEs, and five language ecosystems. Each task includes vulnerable and fixed revisions, a pinned analysis environment, and a checker scaffold. We further introduce CheckerLab, a common evaluation framework that independently rebuilds submitted checkers and measures vulnerable-fixed diagnostic contrast, patch localization, false positives, and tool use. Across 21 model-harness configurations and three independent repeats per configuration, mean Pass@1 is 32.30%, while the best reaches 45.33%. These results show that reliable, reusable checker development remains challenging for current coding agents.

One practitioner we interviewed said their team writes "must" instead of "should" when instructing a coding agent, because the agent may treat "should" as optional. Small wording choices matter because agents often fill gaps in their instructions with their own assumptions. Spec-driven development (SDD) asks developers to write a specification, plan, and tasks before the agent writes code. SDD frameworks provide templates for these artifacts, but the templates do not help developers judge whether they have written enough or clearly enough. We studied what good SDD specifications contain. We scored the artifacts of 114 open-source SDD repositories against ISO/IEC/IEEE 29148 and derived practices from the highest-scoring ones. The resulting framework, EPIC, has 40 practices in 10 quality dimensions that guide developers in making expectations and decisions explicit in specifications, plans, and tasks for coding agents. The majority of SDD practitioners (N=15) endorsed every practice. Repositories in the top third of specification quality spent 11.8% of their commits on bug fixes, compared with 20.4% in the bottom third, and had a median of 4x as many contributors. Developers can use EPIC to find and fill the gaps in a specification before the agent does.

Large language models (LLMs) have become increasingly capable of generating code. However, achieving stronger code-generation performance still often relies on costly model adaptation, i.e., fine-tuning pretrained model parameters. Prior studies have shown correspondence between human code processing and neural models' attention or internal computation. Human-aligned learning approaches use cognitive signals to guide training, but typically adapt a large portion of the model, leaving training costs largely unchanged. Human cognitive signals may indicate not only what the model must learn from, but also where adaptation is most useful. We investigate whether human responses during code reading correspond to code-model behavior and can guide selective adaptation without sacrificing performance. We present CogAdapt, a cognition-informed framework for task-dependent sparse adaptation of code models. CogAdapt first learns transferable program-level and token-level priors from human Electroencephalography (EEG) and attention data, then combines these priors with the frozen model's response to each coding task to determine how much adaptation to allocate and which transformer blocks should receive updates. During fine-tuning, only the selected blocks are updated, while no new human recordings are required for inference. Across Qwen and GLM, we find consistent correspondence between human reading behavior and Mixture-of-Experts (MoE) computation. CogAdapt achieves the best pass@1 across both LiveCodeBench and BigCodeBench, including gains of 10.86 and 6.29 percentage points over matched regular fine-tuning on LiveCodeBench, while reducing gradient-eligible adaptation parameters by 86.21-87.21%. These results suggest that human comprehension signals can provide useful guidance for making code-model adaptation both more selective and more effective.

Systems engineers use several diagrams to describe the structure and behavior of systems. Engineers create these diagrams together to make sure that they use the same elements and remain consistent with one another. Large language models can generate diagrams as text or code, which makes it possible to create system diagrams automatically. However, their ability to generate coherent sets of diagrams is not well understood, and existing datasets and benchmarks do not directly measure this ability at scale. We introduce SEMAADB (Systems Engineering Modeling Assistant with AI Dataset and Benchmark), a dataset of 3,000 engineering contexts and 15,000 diagrams. Each context contains five connected SysML views: Requirement, Block Definition, Activity, State Machine, and Sequence. Here, a view is a diagram that presents one aspect of a system. We checked the diagram sets for consistency and valid rendering. A set of 100 contexts is also human-verified and forms the benchmark test set. We evaluate three language models on two tasks. In diagram repair, the strongest model repairs 64.3% of semantic errors . In cross-diagram update the best propagation F1 is 80.7% when a model applies one change across related diagrams. The results show that syntax repair is nearly solved, but semantic repair and consistency across diagrams are still challenging tasks for models. SEMAADB therefore provides both a large diagram resource and a set of benchmarks for measuring coherent multi-diagram SysML generation.

Manual repair of program failures is time-consuming and disruptive for software developers, particularly during the pre-submit phase where test failures occur within continuous integration systems. While Automated Program Repair has seen significant advancement through Large Language Models, existing state-of-the-art techniques primarily focus on post-submit workflows, operating offline without the low-latency requirements necessary to assist developers in real-time within their flow before they switch context. In this paper, we introduce FlowAgent, an AI agent deployed at Google to automatically repair test failures in the pre-submit outer-loop workflow inside continuous integration systems. Integrated into Google's internal developer tools, Critique and Cider,FlowAgent utilizes a ReAct-style generate-and-validate loop, as well as rigorous pre-execution and post-execution abstention filters to ensure high-quality suggestions under strict latency constraints. Based on our case studies, FlowAgent is highly effective. First, a manual evaluation conducted on 195 real-world test failures demonstrated 67.18% accuracy in suggesting correct fixes. Following its Google-wide deployment, FlowAgent suggested fixes on 295,508changes, of which developers previewed 65,069 and applied 28,554. Developer feedback from interviews indicate that the agent is useful in suggesting correct fixes, integration of autonomous repair agents into industrial software engineering workflows is received well, while interesting challenges and opportunities still remain.

Deployment-time safety of language models is commonly implemented through runtime guardrails such as input moderation, routing, retrieval verification, and output filtering. Existing deployment frameworks provide increasingly capable mechanisms for these functions, but offer limited guidance on how the safety decisions they produce should be explicitly organized, coordinated, and audited. We formulate deployment-time safety as a decision-organization problem with two elements: responsibility-oriented decomposition of safety decisions and explicit coordination among them. We instantiate this formulation in SAFESHIELD, a deployment-time safety system for small language models that organizes four recurring decision responsibilities (admission, routing, evidence, and release) and records committed decisions in auditable Decision Traces. We evaluate SAFESHIELD through mechanism-level experiments, aggregate stage ablations, controlled coordination ablations, and a deployment-oriented stress suite. Mechanism-level results show that the instantiated safeguards provide the capabilities required by the decision process, while aggregate ablations show substantial degradation in end-to-end safety as the surrounding safety organization is removed. More importantly, dedicated coordination ablations preserve the participating safeguard mechanisms while selectively severing their dependencies: removing admission gating substantially increases false release, and withholding upstream evidence from the release decision reduces release accuracy from 96.0% to 69.5%. These results provide system-level evidence that deployment-time safety depends not only on the capability of individual guardrails, but also on how their decisions are organized and coordinated.

Despite the promise and potential of quantum computing, most of the current day developments of quantum computing have several limitations for relevant practical use. As a result, hybrid classical-quantum computing has emerged as a viable solution. This paper discusses the software aspects of hybrid classical-quantum computing solutions to understand and examine how hybrid computing solutions can be expected to work in practice. This paper examines existing software solutions (cloud applications, middleware frameworks, and API gateways) that can enable classical and quantum computing to work together. For practitioners the paper provides a curated list of algorithms, full stack libraries, simulators, and cloud service providers that are likely to be central to the development of any hybrid computing solutions. We conclude by identifying an agenda for future research on classical-quantum hybrid software engineering, and some near-term priorities for development of functional, robust hybrid software systems. The paper argues that due to the deep dependency of quantum execution on classical pre- and post-processing, hybrid computing may represent a near-permanent outcome of classical-quantum computing rather than a transitional workaround.

Around 30% of global energy expenditure can be attributed to the building sector, where a large portion of energy-consumption could be avoided by repairing existing faults. Fault detection and diagnosis (FDD) software addresses this issue; however, its creation and operation also have an environmental impact. The magnitude of this impact is influenced by the diagnosis architecture, as different architectures and methods have different energy demands. Yet, simply considering the energy consumed by the software itself is not sufficient to assess its overall environmental impact, since the diagnostic performance, e.g., number of detected faults or number of faults missed, also contributes to its ecological footprint. In this paper, we propose an energy-consumption model that considers FDD performance and energy spend directly by the diagnosis software. In an initial experiment, we compare several FDD architecture families, i.e., rule-based, model-based, classical machine learning, and large-language-model-based, in simulation using performance and energy-consumption values collected from prior literature. The results show that considering the computational energy and accuracy of FDD can change the relative benefit of the different approaches. Computationally efficient machine learning methods, such as random forest, provide the largest net savings on smaller buildings, whereas more resource-intensive approaches, such as fine-tuned large language models, become advantageous as building size increases. Our findings suggest that overall energy efficiency depends not only on the computational demand of the FDD software, but also on its diagnostic performance and the scale of the building.