ALT Coding agents are trained to complete tasks, and they keep trying even when the environment makes completion impossible. The evidence that only outside help can restore progress usually appears within a few steps, yet agents rarely act on it: they over-persist, attempt undesired workarounds, and claim success the record does not support – a phenomenon we call evidence-action gap. To measure it, we introduce ImpasseBench, which injects twelve realistic environment blockers into otherwise solvable repair tasks and marks, in each trajectory, the step at which the collected evidence becomes sufficient. Scoring actions relative to that step separates appropriate effort from over-persistence and premature handoff. Across eight frontier models and 19,371 trajectories, we find that nearly every run that needs outside help collects sufficient evidence, yet a third still exhaust their budget, and every unsafe request we detect comes after that point. Fortunately, an escalation tool, or an extern

ALT Greenfield software development in freelance settings requires coding agents to turn incomplete client requests into working software. This makes requirement clarification essential, yet clients may be unable to provide continuous feedback over long development cycles, and receiving their answers does not guarantee correct understanding of complex requirements. These challenges motivate two benchmark design choices: clarification precedes code implementation, and its effectiveness is assessed through explicit tests of requirement understanding. Guided by these choices, we introduce SWE-Clar, a benchmark grounded in real, high-value client commissions to evaluate requirement clarification and code implementation in this setting. It comprises 100 tasks based on real software development jobs on Upwork, each with at least US$4,000 in total payments. Each task begins with multi-round interaction between a coding agent and a client agent, followed by separate runs for code implementation wi

ALT Coding agents can be guided with instruction files in a repository. We examine this emerging practice through a census of popular, active GitHub repositories in thirteen languages, treating each repository's root AGENTS.md and CLAUDE.md as one instruction set. Agent instructions appear in of repositories and of the most-starred; where both files exist, CLAUDE.md usually points to AGENTS.md. We analyse statements using model-assisted annotation and human review. The annotations reveal a practical mix of project knowledge and rules about code, building and workflow. Collaboration rules name concrete requirements, from test plans to commit formats, yet of directives give no reason. Projects disagree on AI attribution: commit-message rules more often prohibit it than require it, while pull-request rules more often require disclosure. A third of instruction sets have a generator-associated signature, a tool-inserted block, shared text or an AI-marked creation commit; four in five are edited

ALT Mobile GUI agents frequently perform repetitive tasks with similar interaction procedures. Reusing previous executions can reduce redundant LLM inference and execution overhead, but variations in user instructions and execution environments may invalidate previously successful actions. We systematically characterize these variations into six representative categories and observe that such changes do not necessarily invalidate entire procedures: individual transitions can remain reusable when validated against the current task context and interface state. Based on this insight, we propose graph-text templates for selective execution-trace reuse. The graph captures UI states and action transitions, while the text encodes task intent, procedural structure, and typed slots for variable content. A record-template-replay framework constructs templates from verified executions and leverages the current instruction and live UI state to reuse, adapt, or discard individual transitions. Given an

ALT Spreadsheets are the lingua franca of modern finance, driving valuation, forecast, audit, and many other core workflows of the industry. As LLM agents advance to automate knowledge work, spreadsheet construction is a natural and pertinent testbed. However, most existing spreadsheet benchmarks evaluate agents on fill-in-the-blank style tasks, where an agent performs minor edits in otherwise complete spreadsheets. This protocol fails to capture the most central and time-consuming part of the spreadsheet workflow: the modeling decisions, format design, and sheet layout regular knowledge workers need to toil through to build a workbook from scratch. We introduce MBABench-2.0, a benchmark of 101 original spreadsheet construction tasks, the hardest of which is estimated to take 33 hours for a modeler with 3+ years of experience. Unlike coding or math, where a unit test or a final answer can verify an agent's output, the quality of a financial spreadsheet that concerns readability, maintainab

ALT Context compaction lets long-horizon coding agents continue beyond their context windows, but can erase the state needed to finish a task. Prior evaluations measure efficiency, retained information, or end-to-end success, leaving the effect of a specific history replacement difficult to isolate. Compact-Bench pairs full-history and summary-only continuations from a shared repository state, and evaluates recurring details and successive production compactions. It covers 35 SWE-bench repairs, 146 agentic sessions, and 106 production chains. Across 14 summarizer backbones, stable damage ranges from 5-64% of 22 full-history successes: Claude Opus 4.8 preserves the most repairs, while DeepSeek-Flash damages the most. With Kimi-K3 as summarizer, the Kimi Code prompt preserves the most task continuations (19/22), whereas Claude Code retains the most recurring details (15.0%). LLM summaries retain at most 16.0% of recurring details, compared with 79.1% for mechanical extraction; production sum

ALT Designing large language model (LLM) multi-agent systems (MAS) still relies on trial and error and informal "folk wisdom." Manual studies test only a few communication structures or topologies (e.g., sequential, parallel, shared-memory, or debate), while automated optimizers discard search trajectories after selecting a task-specific workflow. We present a two-phase pipeline for mining reproducible design principles from workflow code and execution traces. We repurpose AFlow's MCTS optimizer across six composable operators and 26 deterministically verified Enigmata tasks, retaining all intermediate rounds to build a corpus of 28,568 executable workflows. A sandboxed AutoResearch loop then mines orchestration code and prompt templates under an L₀-penalized validation objective and tests candidate principles on held-out searches. Across 300 feature-mining trials, we identify effects that persist on held-out searches across three levels of workflow design: workflows beginning with indepen

ALT Evaluating language agents on open-ended, artifact-producing tasks is difficult: model-based graders can be inconsistent, while exhaustive programmatic checks are often impractical. Textual rubrics make evaluation criteria explicit, but writing them requires domain expertise. Rubrics generated from task descriptions alone can miss requirements and failure modes that become apparent in attempted solutions. We introduce RubricCraft, which treats rubric construction as the generation of natural-language specifications guided by candidate solutions. Given a task description and independently sampled solver trajectories, RubricCraft compares how each attempt satisfies or violates the task requirements and uses these differences to construct rubric criteria. It applies the criteria to the collected solutions and revises checks that overlook errors or penalize valid alternatives. The resulting rubrics capture partial correctness without requiring any single solution to serve as a complete ref

ALT Most questions that reach an HPC help desk have already been answered in the center's user guides or in a ticket someone else filed last semester; users still file new tickets because the guides are hard to navigate and the ticket history is not theirs to search. We present an assistant that answers from both sources: an orchestrator calls two tools over the Model Context Protocol, retrieval-augmented generation (RAG) over the live documentation and a Llama-3-8B model fine-tuned with QLoRA on 11,244 query-resolution pairs mined from historical tickets, and merges their answers. Every model runs on-premises or on the university's hosted LLM service because ticket data may not leave the institution. On 400 held-out tickets from Purdue's Rosen Center for Advanced Computing, disjoint from training and free of near-duplicates, and evaluated by two judges from model families that generated none of the answers, fine-tuning on resolutions rewritten into self-service guidance is the clear winne

ALT Large language model (LLM) agents increasingly complete tasks through live graphical user interfaces (GUIs). Because the model cannot directly operate the GUI, these systems often rely on tools to capture screenshots or UI trees, translate model outputs into GUI actions, and report whether the interface changed. We study failures where this tool-mediated interaction makes the agent's view of the task diverge from the live GUI. We construct Malva, a defect library with 335 confirmed real-world failures from 40 open-source applications. These failures fall into 11 defect patterns rooted in state representation, state transition, and synchronization problems. They are widespread: 90% of the studied applications contain more than one defect type. They are also often silent: incorrectness appears in 86.6% of failures, including 119 cases that produce wrong behavior without a fail-stop signal. We operationalize this taxonomy with MalvaGuard, a pre-deployment static contract checker that reac

ALT Institutions that deploy large language models in regulated settings often need technical evidence of responsible AI practices before approving a deployment. COMPL-AI provides a technical interpretation of the EU AI Act that organises this evidence under six principle groups and eighteen technical requirements, twelve of which current benchmarks can measure. The benchmark suites that produce this evidence are typically operated from a command line, while the staff who approve deployments are non-engineers. We present VERA, an open-source self-hosted dashboard deployed to facilitate responsible AI processes within a large European bank. A reviewer selects a model and runs public benchmarks against it. VERA scores the twelve requirements that current benchmarks can measure and instruments the energy consumed by each evaluation, adding run-level evidence for environmental impact. We run four served open-weight models through the requirement pipeline, and the dashboard displays a score for

ALT Commit messages help developers understand code changes and support software maintenance. Recent approaches use repository context to improve commit message generation (CMG) with large language models (LLMs). However, existing CMG methods provide limited support for understanding how local edits affect functionality jointly implemented by multiple code entities. This functional understanding is essential for generating commit messages that explain the main change and its impact. To address this problem, we propose CAMGen, a core change-aware multi-view commit message generation framework that incorporates functional context into generation. CAMGen identifies core entities that represent the primary change intent. It then forms candidate functional units through repository-wide semantic clustering and uses those containing the core entities to construct a Functional Semantic View. This view supplies semantic context for interpreting the affected functionality. CAMGen also uses context p

ALT Procrustes-Bering-Sheaft automates lightweight model discovery and virtual crash tests for microservices. Each test estimates operation availability by Monte Carlo sampling of service and communication failures. Procrustes checks deployment and tracing evidence; Bering discovers dependencies and incorporates replica declarations; Sheaft evaluates declared operation-success conditions. Independent command-line interfaces exchange reusable, versioned artifacts. The toolchain extends an earlier graph-based approach with mandatory-call contracts, failure-tolerance sweeps, baseline comparison, component-importance analysis, and CI/CD gates. We demonstrate the workflow on one HTTP operation. Six controlled execution states exposed two mismatches between reachability and observed success; an explicit required-call predicate matched all six. Two modelled one-replica additions produced different decisions: recommendation retained an availability-target violation, whereas catalog restored the ba

ALT Feature flags are runtime configuration mechanisms used for gradual feature rollouts, experimentation, and kill switches. Once a feature is fully rolled out, the flag and its gated code become technical debt and can introduce operational risk through inadvertently enabling dormant code paths. At DoorDash, over 56,000 feature flags span 623 repositories, with 1,659 currently stale as of May 2026, with internal estimates of one to two hours per manual cleanup. Existing rule-based cleanup tools proved insufficient in DoorDash's codebases. Our contribution is an end-to-end automated LLM-based feature flag cleanup system that integrates querying live feature flag rollout data using MCP, Jira ticket processing, and end-to-end pull request creation. Our system successfully produced engineer-approved flag removal PRs for 45 (90%) of the 50 stale flags it was evaluated on, proving the system's operational viability at scale with each cleanup averaging only 4.79 and 13.8 minutes. We evaluated th

ALT Fuzzing software with complex inputs has been a longstanding challenge. Traditionally, fuzzers either programmatically encode language constraints, requiring significant engineering effort, or rely on users to declare grammars and constraints. Recent LLM-based fuzzers address these drawbacks but introduce new issues. Some use LLMs for test generation, sacrificing throughput and producing invalid inputs when the LLM makes mistakes. Others rely on language-specific parsers, static analysis, and AST manipulation libraries. We introduce Typed Template Fuzzing (TTF), a lightweight LLM-based fuzzing methodology. The key idea is to use LLMs in a preprocessing step to transform seeds into typed templates. The typed templates then enable semantically aware, mutation-based fuzzing without language-specific parsers, type checkers, or further LLM queries during fuzzing. By exploiting the correspondence between seeds and templates, TTF can moreover repair LLM mistakes. We have implemented TTF in ou

ALT Software agents are being trained to exceed human engineers; we argue that capability alone does not produce better software engineering. We define superintelligent software engineering as the discipline of building and evolving software with agents whose capability exceeds that of human engineers, in which governance (gates, contracts, decisions and decay control) scales with capability. The argument rests on three claims. First, correctness in a project rests on decisions and contracts that the code does not carry. Second, knowledge decays. Third, once an agent outpaces its reviewers, reading catches a shrinking share of the changes built on stale knowledge. A simple model shows that, past a fixed review capacity, escaping changes grow linearly with throughput while the share that reading catches falls toward zero; governance can lower the slope, capability alone cannot. An exploratory snapshot of 452 of the most-starred public GitHub repositories finds a root-level or.github agent c

ALT Multi-agent LLM pipelines are often credited with gains in software engineering tasks, but it is rarely clear whether a gain stems from the typed contract between agents or from the specialized prompts that decomposition enables. We study this attribution problem in Requirements Engineering, comparing three architectures for classifying requirements as functional or non-functional and then prioritizing them with MoSCoW: a single-call baseline; a two-call variant that reuses the pipeline's specialized prompts but passes an unvalidated intermediate; and a pipeline with a Pydantic-validated typed state. The 18 conditions cover PROMISE NFR+ (625 requirements), three locally hosted small language models, and two languages. The F1 gain over the baseline is associated with the two-call, specialized-prompt variant (up to +0.075), whereas the typed state adds a small difference (-0.003 to +0.013) that is significant in one of six comparisons. Beyond accuracy, the typed pipeline contains out-of-

ALT Frontend coding agents are usually graded on one question: did the requested target get built. Real engineering changes carry a second obligation, because the rest of the site has to keep working. We call that second obligation website continuity, and introduce ProductWebBench, a benchmark that scores both on living frontend repositories: 320 Change tasks over existing code and 80 long-horizon Build tasks. Every task freezes a repository snapshot, staged requirements, browser evidence and deterministic checks before evaluation, and enters only once a reference passes every check and plausible-wrong ones fail. A simulated user reveals the requirements one stage at a time, and every check cleared earlier stays armed for the rest of the run. Across 8,737 runs from 13 models the two come apart: of the Change runs passing every requested-work check, 28.2% still fail a continuity check – a blank route, horizontal overflow, console errors – and 10.8% push a browser state they had already pass

ALT Large Language Models (LLMs) can generate UML class diagrams from natural language requirements, but hallucinations may compromise the correctness and completeness of the resulting diagrams. Existing evaluations mostly assess the final diagram, without examining the intermediate traces of reasoning-capable LLMs, which can reveal where these hallucinations arise. We develop an empirical taxonomy of eleven hallucination sub-types organised into three dimensions: Prompt Faithfulness (deviations between requirements and reasoning), Code Faithfulness (discrepancies between reasoning and generated PlantUML code), and Reasoning Quality (problems within the reasoning). The taxonomy was derived from 60 manually annotated DeepSeek-R1 traces, applied to 120 further DeepSeek-R1 traces through a dual-LLM annotation pipeline, and examined on 20 DeepSeek-V4-Pro traces. Code Faithfulness was the most frequent dimension for DeepSeek-R1 in both datasets, whereas Prompt Faithfulness dominated for DeepSee

ALT Enterprise AI-agent evaluation needs evidence about whether test suites expose specified faults and whether their reference rules are trustworthy. We introduce REGATTA (Regulatory Evaluation of Agents via Two-stage Testing and Assurance), a measurement framework with three instruments. A 125-item source-cited checklist spans five industry-by-jurisdiction cells across the United States and Vietnam. A 25-fault corpus covers five categories, and a harness scores suite-level fault detection at the design and execution stages. We examine four measurement diagnostics on 180 generated suites (5,400 scenarios) from three LLM generators. A source audit finds 24 items misstating the rule in force, 46 additional citation defects, 31 items with only non-binding, unidentifiable, or unverifiable sources, and 24 verified clean. Only initially substance-flagged items received author review; all 24 clean rows received AI review only. Results therefore describe the instruments as written, not legal comp