Papers

Recent large language models can emit task-progress signals that agent frameworks use to decide whether a task should continue or stop, yet whether a model can reliably report its task progress at every stage of a task, and where and how its reports fail, has not been studied systematically. We evaluate this ability on the public benchmark $\tau^2$-bench and on StageIF, a controlled testbed in which reporting checkpoints are placed across the task's lifecycle. Both settings require reports at multiple task stages. We find that reporting reliability depends on the stage a task has reached, and that almost every deployed model we test is reliable at some stages and unreliable at others. Where reporting breaks down is not the same everywhere. Most deployed models lose accuracy once work is under way and recover once the task is done. The newest generation closes that mid-task drop and instead grows conservative at the finish line. Our study exposes a capability gap in task-progress reporting and provides an evaluation protocol that spans the whole course of task execution for this ability on which agent operation depends. The findings indicate that agent frameworks should not control task flow on the strength of the model's state reports alone.

PLC developers reuse existing components and third-party libraries to reduce the cost of developing new applications, but this reuse can also introduce security risks. When components are distributed only in binary form, provenance tracing, vulnerability assessment, and security auditing become more difficult. To support these analyses, binary2source matching can retrieve the corresponding Structured Text (ST) source file for a PLC binary from a candidate source repository. However, due to the properties of PLC software, this task faces three challenges: cross-platform compilation heterogeneity, a binary-source representation gap, and inadequate representations of PLC semantics. Therefore, we present PLC-Bin2Src, a cross-platform binary2source matching framework that retrieves corresponding ST source files for binaries produced by CODESYS, GEB, OpenPLC v2, and OpenPLC v3. First, PLC-Bin2Src uses platform-aware binary frontends to recover user control logic across toolchains. Then, ST-to-C conversion and shared normalization are used to reduce syntactic differences between source- and binary-side representations. Next, control-data flow graphs (CDFGs) and function call graphs (FCGs) are constructed to capture program semantics, while recovered symbols provide complementary identity evidence. Finally, PLC-Bin2Src compares these representations and combines their similarity scores to rank source candidates. We evaluate PLC-Bin2Src on PLC-BEAD. The results show that PLC-Bin2Src achieves 95.89% Recall@1, 99.66% Recall@5, and an MRR of 0.9769 across four PLC platforms.

Stateful agents reuse artifacts after producing executions and permissions change. We formalize authority-sufficient observations and durable effects bound to execution and material identities. WTB implements this interface through runtime adapters, shared evidence, and transactional publication/recovery. Six study families separate the mechanism from its integration. Raw and typed evidence both solve 32/32 authority cases, with model-dependent planning effects. Fixed-intent enforcement blocks six unsafe proposals and executes 12 eligible authorized intents. Complete controls match WTB's capability. Paid integration yields 176/210 accepted benchmark-source stages, including 19/30 publication stages, recovery on 8/8 primary SWE repositories, and the most complete continuous trajectories on each of three source tasks. The findings connect authority information, effect admission, and infrastructure reuse in stateful agents.

In persistent interactions, long contexts may encode an evolving process rather than a fixed record: later events can revise or revoke earlier information, changing what remains valid and what conclusions follow. We call this setting information evolution (IE). Solving IE requires identifying valid records, applying updates in order, and reconstructing the query-relevant state from the event history. Existing text-first synthesis pipelines make such data difficult to verify because state transitions and answer logic remain implicit. We introduce EvolveScaler, a code-driven framework that defines information evolution before rendering it as natural language. Human-authored operational specifications define state transitions, record validity, difficulty controls, and executable answer logic; a strong LLM then synthesizes a self-contained simulator from each specification. Executing validated simulators produces natural-language multi-turn event histories, while deterministic replay computes reference answers and atomic checklists. We instantiate EvolveScaler with 117 task prototypes and 159 final-question operators across five difficulty levels spanning approximately 7 to 1,200 events per instance, yielding about 35,100 training examples and 585 validated evaluation instances. On the very_long tier, the strongest model reaches 59.3% avg@5, while six models score below 10%. Training an internal A3B model on 6,000 EvolveScaler examples improves performance over its base checkpoint on all eight independently constructed out-of-distribution benchmarks, with a 5.25-point average gain. These results show that code-driven IE synthesis provides both challenging evaluation and transferable training supervision.

Coding agents use system-level tools to read files, execute commands, and modify source code. Within the agent's sandbox, these tools often carry ambient authority: naming a resource is sufficient to act on it. Indirect prompt injection exploits this authority by placing instructions in repository files or tool output that cause the agent to perform actions the user did not request. We propose CapScope, a harness-level authorization mechanism that restricts tool use without requiring the model to identify malicious text. Before repository contents or tool output are read, CapScope derives a task-wide authority ceiling from trusted input. It then assigns each agent a separate set of typed capabilities, stored outside the model's context. Every tool call is checked against the capabilities of the agent that issued it. Permissions assigned to one sub-agent are therefore not automatically available to another. An injection may cause an agent to request an action, but the request is blocked unless that agent already has the required capability. We implement CapScope on the Pi coding agent and evaluate it in a repair workflow where an orchestrator delegates subtasks to separate sub-agents. The evaluation covers five Python tasks, five injection surfaces, four authorization conditions, and three trials per cell (300 runs). The injected effect executes in 33-47/75 runs under the ambient-authority and global-policy baselines, compared with 3/75 under CapScope. CapScope completes 68/75 repairs, while the baselines complete 68-72/75.

Solving repository-level code tasks requires LLM-based agents to use code search tools to navigate large codebases and identify a small set of relevant files and functions. However, current retrieval tools typically return flat lists of isolated code snippets: such lists can surface relevant files, but provide insufficient structure for agents to distinguish the target function from semantically similar alternatives in the same file. We introduce RepoNav, a lightweight post-retrieval interface that reorganizes retrieved snippets into a file-centered navigation scaffold. By presenting compact structural cues and candidate targets, this scaffold guides on-demand file-structure browsing, helping agents compare sibling symbols before selecting a target function. Across diverse models on LocBench, RepoNav improves function-level localization and narrows the file-to-function gap. Controlled ablations demonstrate that these gains come from structured evidence organization rather than simply exposing additional file structure, and the approach also improves performance on a repository-level question-answering benchmark.

In open-world scenarios with massive and evolving tool repositories, tool-augmented large language models rely on a retriever to surface relevant tools for a given query. Because such repositories often contain many tools that implement the same functionality, a single query can often be resolved by several distinct but functionally equivalent tool combinations, making the natural query-to-tool mapping inherently one-to-many. However, existing tool retrieval benchmarks annotate each query with a single relevant tool combination, collapsing this one-to-many mapping into a rigid one-to-one annotation and causing valid retrieved tools to be misjudged as failures. To address this, we propose ToolEX (Tool Equivalent eXpansion), a framework that automatically discovers and annotates the tool combinations functionally equivalent to the labeled ones. Applied to the 7,360-query Tool-DE benchmark, ToolEX finds that 67.9% of sub-queries admit equivalent alternatives, expanding the singular ground truth to an average of 5.3 valid combinations per query. Using the expanded benchmark ToolEQ, we re-evaluate eight base retrievers and two fine-tuned variants; metrics on ToolEQ rise substantially over Tool-DE, showing that one-to-one annotation systematically underestimates retrievers and that 30–47% of the reported fine-tuning gain is an evaluation artifact rather than genuine improvement. Applying the same pipeline to skill retrieval on SkillRet further confirms that the one-to-one problem extends beyond tool retrieval.

The transition from human-centric assistance to Autonomous Software Engineering (ASE) agents has enabled the resolution of complex real-world SE tasks. However, the trial-and-error nature of these agents generates lengthy interaction trajectories, creating severe bottlenecks in terms of context window limits and cost. While context compression offers a potential remedy, prior approaches suffer from static pruning strategies and granularity mismatches, often failing to preserve the semantic dependencies and syntactic details crucial for SE tasks. To strictly preserve critical task evidence while reducing context length, we introduce AttnCompress, a dynamic attention-guided trajectory compression framework. Unlike existing approaches, AttnCompress bridges the gap between semantic integrity and dynamic adaptability through three key mechanisms: (1) structure-aware segmentation via perplexity (PPL) spikes to preserve the syntactic structure of code and logs; (2) relevance estimation using proxy attention weights to quantify the precise relevance of historical blocks to the agent's current reasoning; and (3) a dynamic rolling window to re-evaluate and recall historical context as the task evolves. Extensive evaluation on SWE-Bench-Verified and Multi-SWE-Bench demonstrates that AttnCompress achieves a pass rate of 53.17%, outperforming prior state-of-the-art baselines while reducing token consumption by 21.6% and total costs by 33.6%. The framework proves to be model-agnostic and generalizes effectively across diverse programming languages.

AI coding agents are becoming part of developers' workflows, but their behavior is difficult to understand from final code changes alone. During a task, agents interact with software repositories through sequences of actions such as searching for files, reading code, editing programs, and running tests or build commands. These interactions, together with token usage, are often recorded in console logs, but raw logs are difficult for developers to inspect. In this paper, we propose Agent ATO (Agentic Trajectory Observer), a tool for visualizing AI coding agent interaction timelines from console logs. Agent ATO extracts agent interactions, classifies them by command or tool type, and visualizes them as timelines. In addition to an all-interaction timeline, Agent ATO provides filtered timelines that emphasize file discovery, file reading, file editing, and execution while preserving surrounding context. We illustrate how Agent ATO may help developers inspect and compare agent actions using selected runs from two repair tasks. Future work will apply Agent ATO to more agents, tasks, and development environments, and will evaluate whether it reduces the effort needed to compare trajectories.

This report analyzes Qiushi Engine v0.8 across all 40 test tasks in AstaBench E2E-Bench-Hard, a benchmark that requires autonomous agents to carry a research question through experimental design, code implementation, actual execution, result analysis, and report delivery. Qiushi Engine is model-configurable; this evaluation selected DeepSeek deepseek-v4pro-preview as the model backend. The official AstaBench leaderboard records a score of 0.816 and an average benchmark cost of USD 15.209 per task, while the full-precision local recomputation is $81.59 \pm 1.87$. Four tasks satisfied every rubric item, yielding a full-task completion rate of 4/40 = 10% – 7 percentage points above, and about 3.3 times, the approximately 3% best rate reported for AstaBench's official agents. Across 507 required rubric items, 416 were satisfied (82.1%). Official scoring archives and 40 Meta-Trace records show sustained production and verification of reports, code, and experimental artifacts; the principal gaps lie in repeated runs, external dependencies, specified metrics, and ablation studies. The report explains the benchmark, system workflow, aggregate results, representative cases, and limits of interpretation.

SWE-Bench Pro has emerged as a standard benchmark for evaluating software engineering agents on challenging repository-level tasks. However, our analysis work show that its evaluation is undermined by two sources of unreliability: reward hacking, enabled by leakage of gold solutions or hidden evaluation information, and task quality issues, including misleading problem statements and improperly scoped tests. These issues can inflate benchmark performance and obscure agents' true coding ability. We present SWE-Bench Pro Verified, a verified version of SWE-Bench Pro that addresses both problems. Our approach combines anti-hacking safeguards that eliminate major leakage channels without disrupting normal agent functionality, with task refinement that minimally corrects inconsistencies within flawed instances. Evaluations on SWE-Bench Pro Verified reveal that some models perform substantially worse than previously evaluated, suggesting that existing results on SWE-Bench Pro may overestimate real software engineering capability. SWE-Bench Pro Verified offers a more trustworthy benchmark for assessing software engineering agents.

NumPy is a widely used Python library for numerical scientific computing, known for its declarative APIs and its optimized implementations. However, writing efficient NumPy programs, which often entails using vectorized array operations instead of explicit Python loops, may not be straightforward. This can be difficult for programmers who are accustomed to imperative array traversal, especially when vectorized API invocations require careful reasoning about shapes, broadcasting, and advanced indexing. This paper presents a rewrite-based approach for vectorizing Numpy programs with explicit loops over array data. Our approach vectorizes loops from the inside out, using array shapes and dataflow analysis to guide a source-to-source transformation that replaces loop bodies with vectorized statements. Following a set of rewrite rules that are correct by construction, our approach is consistently fast. We have implemented the approach as a tool called Vectorizer and evaluated it on 150 benchmarks collected from prior work and Stack Overflow. The evaluation shows that Vectorizer vectorizes 142 of the 150 benchmarks directly and 2 more after minor changes to the original benchmarks, with only 0.53 seconds on average to rewrite each one. The resulting programs are, on average, 74.83x faster than the original loop-based implementations.

Contract-clause extraction benchmarks measure reference recovery, but interpreting a system for review assistance also requires measuring unnecessary output and the evidence available within categories. This paper presents a retrospective, reproducible evaluation of a fixed public RoBERTa checkpoint on CUAD's published 102-contract test split. Candidate generation is preserved from an earlier frozen run; matching errors are corrected and category thresholds are reselected on 62 training-split contracts using the original 90% recall target. The corrected operating point recovers 82.2% of reference spans at 8.2% CUAD precision. Of 30,464 returned candidate strings, 19,562 occur on questions with no annotated answer. The system answers 1,335 of 2,938 such questions, a 45.4% false-positive rate (95% contract-bootstrap interval: 43.3-47.9%). Matching candidates constitute 20.3% of returned strings, illustrating why reference-based precision and candidate-level review burden require different denominators. Only nine of 41 categories have at least 30 positive and 30 negative contracts; this count changes to 18 and two under support minima of 20 and 40. Two categories have no negative contracts, making their no-answer false-positive rates undefined. These findings describe one checkpoint, decoder, and threshold policy. Earlier test access and uncertain checkpoint training overlap limit confirmatory interpretation. The paper supplies the original and corrected analyses, predictions, and software checks as ancillary artifacts; it establishes neither a new release criterion nor production readiness.

The adoption of generative AI in software-intensive systems is proceeding rapidly, but current analytical instruments - principally unidimensional maturity models - compress important configurational variation into a single progressive axis. Drawing on an inductive interview study of eighteen senior practitioners across telecommunications, automotive, defence, aviation, banking, energy, government, and enterprise software services, this paper presents the Trustworthy Autonomy Health Check Model: a structured, multidimensional instrument for characterizing how organizations establish trust in GenAI-assisted software engineering. The model organizes eight empirically grounded dimensions into a system layer (Scope of Agent Authority, Assurance Mechanisms, Data Trustworthiness, Architectural Containment, Traceability & Comprehensibility) and an organizational layer (Governance, Human Oversight Posture, Workforce Capability Sustainability), each on a five-level ordinal scale. A cross-cutting overlay of four trust paradigms - operational, engineering, statistical, and containment-based - captures how trust is established, complementing the dimensions capturing what must be trustworthy. The model is diagnostic rather than prescriptive: it supports cross-organizational comparison, surfaces configurational trade-offs, and locates an organization in a shared space without imposing a single progression path. Higher levels are not inherently better; the goal is alignment across dimensions appropriate to the organization's domain and chosen trust paradigm. This is formalized as the alignment hypothesis: effective trustworthiness is constrained by the fit between the scope of agent authority and the dimensions enabling it, with misalignment producing pathological risk or unnecessary friction. We discuss how practitioners can apply the model and outline directions for empirical validation.

Choosing a deferral policy for a frozen classifier requires more than ranking uncertain cases: confidence may be miscalibrated, errors have unequal costs, reviewers can err, and deployment data can leave calibration support. We study these interactions through EcoTrust, a post-hoc framework that compares automatic action with review using a six-group error-risk estimator, class-asymmetric costs, reviewer accuracy, and an optional support gate. On a Columbia River thermal-stress testbed, the learned estimator improves error-ranking area under the receiver operating characteristic curve from 0.869 to 0.889, but Chow's confidence rule has lower in-distribution cost (0.416 versus 0.567 per day). Across 12 off-the-shelf backends, learned risk and a calibration-matched, class-aware confidence estimator each beat raw Chow on six; a paired year-block bootstrap does not resolve their mean cost difference. In transfer to ten river stations, the gate flags every case and becomes an always-review fallback, attaining the lowest cost on eight stations only when review is perfect and unconstrained. These results characterize decision boundaries on one controlled task: richer risk signals do not reliably improve on calibrated confidence, and detected extrapolation does not imply transferable case-level ranking.

AI research agents combine public information and experimental feedback to produce measurable results. The Discovery Certification Protocol (DCP) turns an outcome claim into an executable audit under a registered model, information boundary, and budget. Gate 1 validates useful improvement. Gate 2 tests recovery by matched agents given the starting information and observed Web content, with run history and new measurements withheld. Core requires adequate registered controls, zero recoveries, and a finite-sample recovery bound. Optional Gate 3 compares truthful and neutral feedback from a shared checkpoint; Evidence adds a supported effect and a null-policy equivalence check. Controlled SQLite and virtual catalyst audits pass both decision kernels. On real-data response surfaces, Yacht and Ionosphere pass the Core kernel after zero recoveries in 96 attempts, with an upper bound of 0.0468. Each target combines ten observed utilities and six predictions into a 16-entry data product. Yacht scores 0.7677 on reconstruction of all 32 switch effects, with utility-prediction MAE 0.0315 on its six unmeasured configurations. Fresh truthful continuations recover the target level in 9/30 and 16/30 trials, respectively, separating achieved utility from process repeatability. A deterministic verifier reproduces these local decisions from frozen records.

The software supply chain has become an increasingly exposed attack surface because of its reliance on intricate yet fragile dependencies. Existing defenses such as GitHub Dependabot often raise many false alerts because their coarse-grained matching cannot determine whether a vulnerable dependency is actually exploitable. Security analysts typically spend substantial time assessing vulnerability exploitability case by case. Recent LLM agents have emerged as promising candidates for this task given their advanced capabilities in coding and cybersecurity, yet no existing benchmark evaluates them on it. Prior benchmarks target zero-day settings, where agents detect and exploit previously unknown vulnerabilities. In contrast, software supply chain security focuses on how known vulnerabilities in upstream dependencies affect downstream projects. This requires agents to reason across repositories and determine whether an upstream vulnerability is exploitable in the downstream project. To address this gap, we introduce VEX-Bench, the first benchmark for evaluating LLM agents' ability to assess the exploitability of software supply chain vulnerabilities. It contains 75 real-world cases mined from GitHub and labeled by security experts, covering Python, Java, and Go. We evaluate nine models across three agent harnesses. While GPT-5.5 and Claude Opus 4.6 reach approximately 80% F1 on binary vulnerability-status classification, only GPT-5.5 surpasses 70% macro-F1 on fine-grained justification classification. This gap highlights the challenge of moving beyond binary exploitability assessment to identifying fine-grained exploitability reasons. Code and data: https://github.com/steven1518/vex-bench

Distributed systems support many critical business workflows, but service health is often judged through component dashboards rather than through end-to-end user outcomes. This article presents service health engineering as a practical reliability discipline that connects telemetry, workflow completion, dependency behavior, operational readiness, and recovery validation. Using a document approval workflow as a running example, it describes how service promises, service-level indicators and objectives, watchdogs, incident measures, resiliency testing, and weekly service-health reviews can reveal silent failures and stranded asynchronous work. It also presents a human-reviewed, AI-assisted reporting architecture for assembling service-health evidence without making AI an autonomous decision-maker. The approach brings established reliability practices together around whether user journeys complete as promised.

Artificial intelligence is reshaping open source software (OSS) contribution by lowering the cost of producing code, documentation, issue reports, and review interactions. This creates opportunities for broader participation, but also disrupts how maintainers assess contributor effort, competence, and accountability. In response, OSS projects are beginning to regulate AI-mediated contribution through contribution guidelines and other project documentation. This paper presents an empirical study of these emerging policies. We analyze project policies on AI-mediated contributions by evaluating their underlying rationales, rules, and expectations. Our analysis shows that these policies seek to protect scarce maintainer attention, preserve accountability, sustain meaningful review interactions, address legal and quality concerns, and maintain pathways for newcomer learning. Based on these findings, we introduce the AI Contribution Governance Framework, which organizes recurring concerns and governance mechanisms across projects. The framework helps OSS communities develop AI contribution policies and provides researchers with a vocabulary for studying how AI is changing collaborative software production.

In recent years, smart contracts have become the backbone of decentralized applications (DApps), and off-chain systems such as bridges, wallets, and indexers rely heavily on event logs to track contract execution and state changes. However, the Ethereum Virtual Machine (EVM) does not validate or enforce event semantics, so logs can diverge from on-chain state, misleading off-chain systems into accepting incorrect state transitions. Existing smart contract vulnerability detection tools focus on logic bugs, with limited support for detecting event-semantic defects. To address this gap, we collect audit reports and incident cases and apply open card sorting to define five classes of event-semantic defects: event collision, state-event mismatch, unauthorized event emission, event emission mismatch, and event parameter mismatch. We propose EventSpec, which infers event specifications from a contract corpus via behavior inference and semantic-constraint extraction and applies differential checking to identify event-semantic defects in target contracts. We run EventSpec on 6,617 real-world contracts and evaluate detection effectiveness based on manually labeled results; EventSpec achieves an overall comprehensive precision of 90.17%. We further provide an off-chain evaluation harness that reproduces two off-chain attack vectors on any EVM-compatible chain: event origin confusion caused by unintended emitters and event-state desynchronization where events lack matching state updates. Using this harness, we demonstrate the feasibility of these attacks on bridge relayers, blockchain explorers, and NFT marketplaces, and report six wallet issues, four of which were confirmed (including a $600 bounty), with two remaining pending.

As AI-code assistant tools become widespread, automatic assessment of the correctness of generated code becomes a significant challenge. Code LLMs are prone to hallucinations, which may lead to code that does not solve the required problem, or even to code with severe security vulnerabilities. In this paper, we introduce CodeTD – the first approach to pre-execution assessment of code correctness based on topological data analysis (TDA) of Code LLMs' attention maps. Our method quantifies prompt-generation mismatch using topological patterns of attention maps. We carry out experiments with common benchmarks (HumanEval, MBPP, BigCodeBench, MultiPL-E), 5 programming languages and 10 Code LLMs of size up to 34B parameters. The experimental results show that the proposed method outperforms recent baselines. Moreover, CodeTD is transferable between coding benchmarks.

AI coding assistants now select, install, and configure software, and attackers have exploited that position through invented package names, compromised maintainer accounts, and manipulated repository text. In response, the supply-chain community publishes machine-checkable trust signals: software bills of materials, signed releases, build provenance attestations, and declared official channels. Whether coding assistants read or act on those signals has not been measured for any of these classes on research software. We pre-registered and ran a controlled study on six open-source research software projects (three HPC, three quantum computing) drawn from an 87-project corpus, with protocol, seed, panel, and analysis plan deposited with a DOI before any trial. W created nine modified copies for each project: no signal, one per signal class, two with a signature or attestation from the wrong issuer, one with all four signals, and one reproducing documented conflicts in the project's own metadata. Three models under two ways of operating an assistant, with and without an approval step, gave 1,920 registered trials, plus a supplement on three frontier models. We scored behavior from container logs rather than from what the assistant said, and recorded the cost of every trial. Verification was rare under every condition: in 9 of 1,920 registered trials (0.5%), the assistant opened any provenance signal before installing in 0 of 384 control trials, and no trial ran a verification command, so signal presence had no measurable effect. We drew three conclusions: publishing signals is necessary but not sufficient; price did not buy verification (the model that verified most often costs $0.10 per trial; the most capable, at $1.00, verified nothing); verification must be built into the program that runs the assistant. We release the per-trial cost ledger, the protocol, and every log.

As software engineering research submission counts surge, peer reviewers face severe time constraints, making systematic verification of citation-supported claims prohibitively expensive. Consequently, unsubstantiated claims and semantic drift can propagate undetected across scientific literature. Existing approaches such as fact-checking and retrieval-augmented generation tools operate on open-domain web data or evaluate claims in isolation without processing complete manuscripts. To address this gap, we present RefVerifier, a semi-automated, citation-bounded reference verification prototype designed to support in academic peer review. RefVerifier extracts citation-bearing sentences from manuscripts, checks bibliography metadata against scholarly databases, resolves references to full-text open-access PDFs, localizes relevant evidence passages, and generates verdicts with natural language explanations. Evaluating RefVerifier on public benchmarks shows claim detection at an F1 score of 0.990, open-access resolution of 57.6% of references, and evidence localization with a hit rate of 98% on abstracts and 68% on complete cited papers. In an end-to-end test with eight manuscripts, RefVerifier achieves a verdict accuracy of 71%. By automating document retrieval and evidence localization while preserving reviewer oversight, RefVerifier provides first indicators for the feasibility of semi-automated integrity checks in scholarly publishing.

Software repositories contain vast amounts of data on code contributions, bug reports, and project activities, yet this information remains challenging for non-technical stakeholders and developers to access due to limited expertise in querying repositories. To address this, we introduce a novel chatbot architecture leveraging OpenAI's GPT-4 model for automated extraction and analysis of repository data. In contrast, our architecture takes a structured path first by parsing the user's query to extract relevant parameters, then selecting the correct tool to employ based on that analysis, and finally invoking the GPT-4 model to create a highly detailed response. In contrast to previous work based on multi-component systems with embedding models and document retrievers, our architecture inverts the process by relying on prompt engineering and tool selection to fit with the query intent. To validate our approach, we conducted experiments on various question types, including Issues, Pull Requests, Commits, Compound Questions, and General Repository Information, evaluating our target prompts' ability to improve the accuracy of responses from the model. Beyond demonstrating the utility of this architecture to a diverse set of users, our findings suggest that this architecture can make repository data more accessible to technical and non-technical audiences through the production of actionable insights.

Open source communities are converging on a new governance artifact: the AI contribution policy. These policies barely existed a few months ago and are now being written and adopted. We analyzed 281 AI contribution policies, and manually classified them along the six dimensions; to study how policies change, we also tracked 92 dedicated AI policy files over time. We answer four research questions on (1) AI usage allowance, (2) AI disclosure practices, (3) AI slop countermeasures, and (4) AI policy evolution. We find that, first, permission is the norm rather than the exception: 83.3% of policies permit or encourage AI in code contributions. But permission comes with conditions, as 67.3% require a high level of human involvement and 43.4% assign accountability. Second, AI disclosure is required by 48.8% of policies, most often in pull request descriptions and commit messages, but what must be disclosed varies widely. Third, we identify ten countermeasures against AI slop, targeting pull requests, users, and autonomous agents. Finally, policies are not static: half of the dedicated AI policy files have already been revised since creation. Our results give maintainers and researchers a baseline and a labeled corpus for studying the impact of AI policies.

Writing error-free floating-point programs is a challenging task, especially for programmers who lack a strong background in numerical analysis and rounding-error propagation. State-of-the-art techniques typically aim to bound such errors using static or dynamic analysis. However, only a few tools explicitly address critical floating-point pitfalls such as absorption and catastrophic cancellation. These anomalies represent situations in which rounding errors are significantly amplified, causing the semantics of the finite-precision computation to deviate substantially from the real-number semantics. In this article, we present FPScan, a novel tool to formally define and detect both catastrophic cancellation and absorption in floating-point programs. Our approach starts with a custom static analyzer based on abstract interpretation to infer the order of magnitude of all program variables. This magnitude information is then used to build a set of first-order constraints that model error propagation and numerical precision within the program. Finally, we employ an off-the-shelf SMT solver to determine whether the program exhibits any of these critical numerical pitfalls. Experiments were conducted on FPBench, a well-known benchmark suite of floating-point programs, to evaluate the effectiveness of our tool. We also present a comparison with state-of-the-art tools regarding soundness and analysis time.

Detecting refactorings in commit history is essential to improve comprehension to code changes on code reviews, and to provide valuable information for empirical studies on software evolution. Techniques have been proposed to accurately detect refactorings on the granularity of a single commit. However, refactorings can be made over multiple commits because of their complexity or other practical development problems, which cause detecting on only the granularity of a single commit not enough. We observe that some refactorings can only be detected in coarser granularity, i.e., changes conducted over multiple commits, or in the granularity of a single commit but not in coarse-grained. We call these types of refactorings as coarse-grained refactorings (CGRs) and ephemeral refactorings (EPRs). We investigated the features and causes of CGRs and EPRs through an empirical study of 32 open-source Java projects and found that both commonly occur during development. In addition, we found that refactoring types related to splitting or merging classes and packages, as well as those involving modifications to the inheritance structure, tend to be CGRs, and types targeting small objects such as variables and attributes, and refactorings with context-sensitive detection criteria tend to be EPRs. The causes of CGRs and EPRs are analyzed and categorized, and the relationships between the commit messages of CGRs and themselves are also assessed. We found that about 20% of commit messages explicitly suggest the existence of CGRs. We suggest that CGRs and EPRs be valued in refactoring research and that detectors be extended to identify CGRs.

Natural-language Computer-Aided Design (CAD) code generation aims to turn design intent into executable and editable parametric programs. Large language models (LLMs) make this goal increasingly practical, but useful systems must preserve the construction process behind the rendered geometry. Existing benchmarks and methods mostly focus on how closely the generated CAD model matches the reference geometry, often using metrics such as Intersection over Union (IoU). Such metrics can miss errors in part decomposition, construction hierarchy, Boolean operations, sketch structure, and geometric relations. This gap calls for a representation that makes design intent explicit and lets a system check generated code against that intent. We propose CIT-CAD, a framework that infers a Constraint Intent Tree (CIT) from the input description to represent the intended entities, hierarchy, operations, and relations. The tree has two roles: it guides CAD code generation and defines expected constraints for verification. The framework extracts actual constraints from the generated program, compares them with the expected constraints, and uses mismatches to localize and repair design violations. Experiments show that the framework improves CAD generation performance, with larger gains on more complex multi-entity designs. By turning design intent into an explicit and checkable object, this work is the first attempt to move text-to-CAD generation beyond rendered-geometry matching toward construction-aware synthesis, verification, and repair.

Software model optimization is a process that generates architecture alternatives aimed at improving quantifiable non-functional properties of software systems, such as performance and reliability. Multi-objective evolutionary algorithms are commonly used to explore the search space and help designers identify trade-offs among competing non-functional properties (e.g., through a Pareto front). However, such algorithms face efficiency challenges in complex software models and large design spaces, since evaluating the fitness (i.e., the quality) of each architecture requires analysis tools that become computationally expensive when repeatedly invoked during the search process. In this paper, we explore the construction of surrogate models based on regression techniques to approximate the outputs of these analysis tools at significantly lower computational cost, while maintaining reasonable output accuracy. Our experimental results suggest that surrogate models provide savings of up to $30\%$ in computational time and maintain the Pareto front quality provided by evolutionary algorithms. Also, we observed some differences in the architectural models produced by our approach. Overall, surrogate models constitute a promising approach for scaling multi-objective architecture optimization to larger spaces and complex architectural models.

Architectural decision records (ADRs) have become a popular lightweight mechanism for documenting architectural knowledge in software projects. However, there is limited empirical evidence on the kinds of architectural concerns captured in ADRs and how well their contents align with established architectural knowledge concepts and documentation practices. In this paper, we propose an automated text-mining and classification approach for analyzing ADRs at scale. We apply this approach to a dataset of ADRs extracted from ~550 open-source repositories, combining topic modeling, LLM-based classification, and template compliance checks. Our analysis examines decision taxonomies and quality attributes, and the degree to which ADRs adhere to the MADR template. Our findings show that ADRs frequently capture existence, technology, and process-related decisions, while alternatives, decisions drivers, and some quality concerns remain under-documented. We also observe recurring mismatches between ADR contents and template sections. These insights into current documentation practices provide architects with valuable information to reflect on how ADRs are and should be used to effectively deal with architectural knowledge. Furthermore, our automated approach is adaptable to other architectural tasks.