Daily Papers

We introduce DafnyCOMP, a benchmark for evaluating large language models (LLMs) on compositional specification generation in Dafny. Unlike prior benchmarks that focus on single-function tasks, DafnyCOMP targets programs composed of multiple interacting functions with data dependencies, requiring reasoning across component boundaries. The benchmark consists of 300 automatically synthesized multi-function programs. We evaluate several state-of-the-art LLM families and find that, while they perform well on single-function verification, their performance drops sharply on compositional tasks. Analysis reveals systematic failures in cross-functional reasoning, including fragile specifications, misalignment between implementations and proofs, and unstable reasoning. DafnyCOMP thus provides a diagnostic tool for measuring progress toward reliable, verifiable, and compositional code generation with LLMs.

Safety benchmark scores provide incomplete evidence of deployment readiness: aligned language models often adhere to rigid rules even when a situational update flips which action is safe. We term this failure brittle safety. To diagnose it, we introduce context-flip evaluation, testing 12 models across a safety benchmark (PacifAIst) and two commonsense controls using paired variants where the nominally safe action produces harm. Three findings emerge. First, brittle safety is safety-specific: all 12 models exhibit a safety-commonsense gap (mean +17.4 pp). Baseline accuracy fails to predict brittleness: among models above 90% baseline accuracy, brittleness rates range from 13.7% to 90.0%. Second, failures stem from policy override rather than miscomprehension: despite acknowledging the context change in every case, models persist via three distinct mechanisms that vary by update type and model family. Third, on a hand-audited probe of catastrophic consequence-flip scenarios, standard action-level guardrails catch none, while a state-aware validator catches all without false alarms on correct interventions. This indicates that action-level content moderation is systematically blind to consequence-flips, motivating state-aware architectural alternatives. We release our protocol, perturbed benchmarks, and deployment probe.

The automated generation of agentic workflows is a promising frontier for enabling large language models (LLMs) to solve complex tasks. However, our investigation reveals that the robustness of agentic workflow remains a critical, unaddressed challenge. Current methods often generate wildly inconsistent workflows when provided with instructions that are semantically identical but differently phrased. This brittleness severely undermines their reliability and trustworthiness for real-world applications. To quantitatively diagnose this instability, we propose metrics based on nodal and topological similarity to evaluate workflow consistency against common semantic variations such as paraphrasing and noise injection. Subsequently, we further propose a novel training framework, RobustFlow, that leverages preference optimization to teach models invariance to instruction variations. By training on sets of synonymous task descriptions, RobustFlow boosts workflow robustness scores to 70\% - 90\%, which is a substantial improvement over existing approaches. The code is publicly available at https://github.com/DEFENSE-SEU/RobustFlow.

Robustness is often regarded as a critical future challenge for real-world applications, where stability is essential. However, as models often learn tasks in a similar order, we hypothesize that easier tasks will be easier regardless of how they are presented to the model. Indeed, in this paper, we show that as models approach high performance on a task, robustness is effectively achieved. Through an empirical analysis of multiple models across diverse datasets and configurations (e.g., paraphrases, different temperatures), we find a strong positive correlation. Moreover, we find that robustness is primarily driven by task-specific competence rather than inherent model-level properties, challenging current approaches that treat robustness as an independent capability. Thus, from a high-level perspective, we may expect that as new tasks saturate, model robustness on these tasks will emerge accordingly. For researchers, this implies that explicit efforts to measure and improve robustness may warrant reduced emphasis, as such robustness is likely to develop alongside performance gains. For practitioners, it acts as a sign that indeed the tasks that the literature deals with are unreliable, but on easier past tasks, the models are reliable and ready for real-world deployment.

Multimodal industrial anomaly inspection assistants are a critical component of next-generation smart factories, enabling interactive vision-language-based querying. However, multimodal large language models remain impractical for on-site deployment due to prohibitive computational demands and privacy risks from cloud-based inference. Compact multimodal small language models (MSLMs) offer a deployable alternative, yet progress is constrained by the lack of comprehensive robustness analyses and meaningfully challenging benchmarks that reflect real-world industrial conditions. To address this gap, we develop RobustMAD, the first deployment-motivated benchmark, designed to comprehensively evaluate model robustness through diverse open-ended queries spanning object understanding, anomaly detection, unanswerable problems, and visual quality degradations. Contrary to conventional assumptions, top-performing MSLMs exhibit promising capabilities, surprisingly outperforming even the larger GPT-5 Nano. However, they still fall short of safety-critical requirements, and RobustMAD reveals critical robustness gaps that pose operational risks. In particular, three recurring failure modes emerge: (i) fragile multimodal grounding under fine-grained distinctions or degraded visual conditions, (ii) insufficiently comprehensive responses, and (iii) weak logical grounding on unanswerable or ill-posed queries, leading to hallucinated outputs. Grounded in these insights, we provide actionable guidance for the design of next-generation multimodal industrial inspection assistants that leverage their promising competence. Code is available at https://github.com/en-research/RobustMAD.

The advent of instruction-tuned Large Language Models designed for coding tasks (Code LLMs) has transformed software engineering practices. However, their robustness against various input challenges remains a critical concern. This study introduces DegradePrompter, a novel method designed to systematically evaluate the robustness of instruction-tuned Code LLMs. We assess the impact of diverse input challenges on the functionality and correctness of generated code using rigorous metrics and established benchmarks. Our comprehensive evaluation includes five state-of-the-art open-source models and three production-grade closed-source models, revealing varying degrees of robustness. Open-source models demonstrate an increased susceptibility to input perturbations, resulting in declines in functional correctness ranging from 12% to 34%. In contrast, commercial models demonstrate relatively greater resilience, with performance degradation ranging from 3% to 24%. To enhance the robustness of the models against these vulnerabilities, we investigate a straightforward yet effective mitigation strategy. Our findings highlight the need for robust defense mechanisms and comprehensive evaluations during both the development and deployment phases to ensure the resilience and reliability of automated code generation systems.

Existing evaluation methods largely rely on clean, static benchmarks, which can overestimate true model performance by failing to capture the noise and variability inherent in real-world user inputs. This is especially true for language models, which can face human-generated text queries containing mistakes, typos, or alternative ways of phrasing the same question. In this work, we introduce a theoretical framework for quantifying model sensitivity to prompt variants, or brittleness, that can enable us to disentangle data-induced difficulty from prompt-related variability. Using this framework, we design a novel evaluation pipeline, Brittlebench, to holistically evaluate the sensitivity of frontier models. We apply semantics-preserving perturbations to a suite of popular benchmarks, and observe model performance to degrade as much as 12%. However, these perturbations do not affect all models equally: even a single perturbation alters the relative ranking of models in 63% of cases, impacting conclusions about comparative model performance. Decomposing the total variance of both state-of-the-art open-weight and commercial models, we find that semantics-preserving input perturbations can account for up to half of the performance variance for a given model. Brittlebench highlights the need for more robust evaluations and models, and allows us to systematically understand model brittleness.

In industrial procurement, an LLM answer is useful only if it survives a standards check: recommended material must match operating condition, every parameter must respect a regulated threshold, and no procedure may contradict a safety clause. Partial correctness can mask safety-critical contradictions that aggregate LLM benchmarks rarely capture. We introduce IndustryBench, a 2,049-item benchmark for industrial procurement QA in Chinese, grounded in Chinese national standards (GB/T) and structured industrial product records, organized by seven capability dimensions, ten industry categories, and panel-derived difficulty tiers, with item-aligned English, Russian, and Vietnamese renderings. Our construction pipeline rejects 70.3% of LLM-generated candidates at a search-based external-verification stage, calibrating how unreliable industrial QA remains after LLM-only filtering.Our evaluation decouples raw correctness, scored by a Qwen3-Max judge validated at κ_w = 0.798 against a domain expert, from a separate safety-violation (SV) check against source texts. Across 17 models in Chinese and an 8-model intersection over four languages, we find: (i) the best system reaches only 2.083 on the 0--3 rubric, leaving substantial headroom; (ii) Standards & Terminology is the most persistent capability weakness and survives item-aligned translation; (iii) extended reasoning lowers safety-adjusted scores for 12 of 13 models, primarily by introducing unsupported safety-critical details into longer final answers; and (iv) safety-violation rates reshuffle the leaderboard -- GPT-5.4 climbs from rank 6 to rank 3 after SV adjustment, while Kimi-k2.5-1T-A32B drops seven positions.Industrial LLM evaluation therefore requires source-grounded, safety-aware diagnosis rather than aggregate accuracy. We release IndustryBench with all prompts, scoring scripts, and dataset documentation.

Large language models (LLMs) show inherent brittleness in their safety mechanisms, as evidenced by their susceptibility to jailbreaking and even non-malicious fine-tuning. This study explores this brittleness of safety alignment by leveraging pruning and low-rank modifications. We develop methods to identify critical regions that are vital for safety guardrails, and that are disentangled from utility-relevant regions at both the neuron and rank levels. Surprisingly, the isolated regions we find are sparse, comprising about 3% at the parameter level and 2.5% at the rank level. Removing these regions compromises safety without significantly impacting utility, corroborating the inherent brittleness of the model's safety mechanisms. Moreover, we show that LLMs remain vulnerable to low-cost fine-tuning attacks even when modifications to the safety-critical regions are restricted. These findings underscore the urgent need for more robust safety strategies in LLMs.

Current language model evaluations measure what models know under ideal conditions but not how robustly they know it under realistic stress. Static benchmarks like MMLU and TruthfulQA cannot distinguish a model that lacks knowledge from one whose verification mechanisms collapse when information degrades or adversaries probe for weaknesses. We introduce the Drill-Down and Fabricate Test (DDFT), a protocol that measures epistemic robustness: a model's ability to maintain factual accuracy under progressive semantic compression and adversarial fabrication. We propose a two-system cognitive model comprising a Semantic System that generates fluent text and an Epistemic Verifier that validates factual accuracy. Our findings, based on evaluating 9 frontier models across 8 knowledge domains at 5 compression levels (1,800 turn-level evaluations), reveal that epistemic robustness is orthogonal to conventional design paradigms. Neither parameter count (r=0.083, p=0.832) nor architectural type (r=0.153, p=0.695) significantly predicts robustness, suggesting it emerges from training methodology and verification mechanisms distinct from current approaches. Error detection capability strongly predicts overall robustness (rho=-0.817, p=0.007), indicating this is the critical bottleneck. We find that flagship models exhibit brittleness despite their scale, while smaller models can achieve robust performance, challenging assumptions about the relationship between model size and reliability. The DDFT framework provides both theoretical foundation and practical tools for assessing epistemic robustness before deployment in critical applications.

Reinforcement learning is structurally harder than supervised learning because the policy changes the data distribution it learns from. The resulting fragility is especially visible in large-model training, where the training and rollout systems differ in numerical precision, sampling, and other implementation details. Existing methods manage this fragility by adding hyper-parameters to the training objective, which makes the algorithm more sensitive to its configuration and requires retuning whenever the task, model scale, or distribution mismatch changes. This fragility traces to two concerns that current objectives entangle through hyper-parameters set before training begins: a trust-region concern, that updates should not move the policy too far from its current value, and an off-policy concern, that data from older or different behavior policies should influence the update only to the extent that it remains reliable. Neither concern is a constant to set in advance, and their severity is reflected in the policy-ratio distribution of the current batch. We present a simple yet effective batch-adaptive objective that replaces fixed clipping with the normalized effective sample size of the policy ratios. The same statistic caps the score-function weight and sets the strength of an off-policy regularizer, so the update stays close to the usual on-policy score-function update when ratios are nearly uniform, and tightens automatically when stale or mismatched data cause ratio concentration, while retaining a nonzero learning signal on high-ratio tokens. Experiments across a wide range of settings show that our method matches or exceeds tuned baselines, introducing no new objective hyper-parameters and removing several existing ones. The code is available at https://github.com/FeynRL-project/FeynRL.

A language model's memory can be worse than no memory at all when the model or its interface is disposed to act on it: a memory that keeps a wrong conclusion but drops the work behind it leads a model to re-emit the stale value as a confident answer, where an empty memory leads it to abstain. We call this brittle memory. The information loss is definitional; the finding is behavioral, and it turns on one thing, whether the memory kept a re-derivation basis (the source) rather than the answer. We measure it with reclaim evaluation: induce a known drift, compress at a fixed budget, deliver a correction that names the error, and score exact recovery, judge-free. Holding the budget fixed and varying only what the compression keeps isolates correctability from capability and from size; an 8B model and a frontier one wall in the same place. A one-line source-first policy, keep the recomputable source, drop the re-derivable conclusion, restores correctability at equal budget where the source is compact and identifiable, with a length-matched control ruling out "more text." We map where the fix fails, show the failure compounds through memory loops, and replicate across three deployed memory systems, real dialogue (MultiWOZ), and tau-bench, a deployed-agent benchmark where whether a lossy memory becomes a harmful action is a joint model-and-interface property. We release the harness, the paired memory conditions, and validators built to come out false.

Having reliable specifications is an unavoidable challenge in achieving verifiable correctness, robustness, and interpretability of AI systems. Existing specifications for neural networks are in the paradigm of data as specification. That is, the local neighborhood centering around a reference input is considered to be correct (or robust). While existing specifications contribute to verifying adversarial robustness, a significant problem in many research domains, our empirical study shows that those verified regions are somewhat tight, and thus fail to allow verification of test set inputs, making them impractical for some real-world applications. To this end, we propose a new family of specifications called neural representation as specification, which uses the intrinsic information of neural networks - neural activation patterns (NAPs), rather than input data to specify the correctness and/or robustness of neural network predictions. We present a simple statistical approach to mining neural activation patterns. To show the effectiveness of discovered NAPs, we formally verify several important properties, such as various types of misclassifications will never happen for a given NAP, and there is no ambiguity between different NAPs. We show that by using NAP, we can verify a significant region of the input space, while still recalling 84% of the data on MNIST. Moreover, we can push the verifiable bound to 10 times larger on the CIFAR10 benchmark. Thus, we argue that NAPs can potentially be used as a more reliable and extensible specification for neural network verification.

Tool-using LLM agents are mostly evaluated assuming all tools work. When a tool times out, returns a week-stale value, or has its description poisoned in deployment, the developer needs a controlled way to reproduce the failure, test a fix, and confirm the fix worked before deployment. We present AgentCheck, an open-source web workbench that turns an MCP server into an intervention surface. AgentCheck runs an agent against its real tools and records every tool response, then re-runs the agent with the response perturbed by a fault (12 types) injector. Matching tool calls are replayed from cache, and later tool calls go live after the agent diverges. This yields a reproduce-intervene-confirm loop: the developer toggles a mitigation, re-runs against the identical fault, and sees if the failure goes away. Scoring has two parts: deterministic pass/fail rules, plus an LLM judge for interpretive labels, validated against human annotations. Across five agents, the best passes 105/120 scenarios and the weakest only 77. The failures are usually silent, confident use of incorrect tool outputs rather than crashes. On the weakest agent, a retry mitigation raises success on timeout error faults from as few as 30% of cases to 100%, whereas stale-data faults remain near 3-4 of 10 regardless of the mitigation. AgentCheck makes these failure modes reproducible, comparable, and verifiable before deployment.

Autonomous agents increasingly perform bounded software tasks under an orchestrator that retries, resumes, and budgets them. The machinery such orchestrators reach for is the service mesh's: retry, timeout, and error-rate circuit breaking. We report a failure study of a production agentic software-delivery platform over 147 numbered incidents spanning 81 runs, each with a measured cost and, in most cases, a mutation proof reproducing the failure. All three assumptions those primitives rest on are violated in practice, and we quantify the consequences: a loop of fifty-four consecutive successful tool calls no error-rate breaker could see; a progress signal constant by construction, guaranteeing a false trip on the third repair round and driving one run from six of six components to three; twenty-one events accumulated across six invocations of one delegation, making a correct, idempotent component unwinnable; a misrouted failure that woke five components for a two-component fault, leaving three bystanders regressing working code; and twelve incidents in which the enforcement layer blocked correct work, the most expensive costing 107 agent turns and zero accepted writes. We find one cross-cutting cause and its dual. Identity adequacy: in five separate subsystems an identity that failed to discriminate produced a confident wrong answer, and two of them derived the corrective rule independently. Evidence adequacy: a reliability decision may be taken only on evidence capable of moving, attributable to what it measures, and deterministic under identical conditions. From the findings we derive seven reliability primitives whose enforcement unit is the delegation rather than the message, and specify the controlled evaluation the study motivates but does not constitute.

Software maintenance faces a persistent challenge with crash bugs, especially across diverse release channels catering to distinct user bases. Nightly builds, favoured by enthusiasts, often reveal crashes that are cheaper to fix but may differ significantly from those in stable releases. In this paper, we emphasize the need for a data-driven solution to predict the impact of crashes happening on nightly channels once they are released to stable channels. We also list the challenges that need to be considered when approaching this problem.

Software specifications are essential for ensuring the reliability of software systems. Existing specification extraction approaches, however, suffer from limited generalizability and require manual efforts. The recent emergence of Large Language Models (LLMs), which have been successfully applied to numerous software engineering tasks, offers a promising avenue for automating this process. In this paper, we conduct the first empirical study to evaluate the capabilities of LLMs for generating software specifications from software comments or documentation. We evaluate LLMs' performance with Few Shot Learning (FSL), enabling LLMs to generalize from a small number of examples, as well as different prompt construction strategies, and compare the performance of LLMs with traditional approaches. Additionally, we conduct a comparative diagnosis of the failure cases from both LLMs and traditional methods, identifying their unique strengths and weaknesses. Lastly, we conduct extensive experiments on 15 state of the art LLMs, evaluating their performance and cost effectiveness for generating software specifications. Our results show that with FSL, LLMs outperform traditional methods (by 5.6%), and more sophisticated prompt construction strategies can further enlarge this performance gap (up to 5.1 to 10.0%). Yet, LLMs suffer from their unique challenges, such as ineffective prompts and the lack of domain knowledge, which together account for 53 to 60% of LLM unique failures. The strong performance of open source models (e.g., StarCoder) makes closed source models (e.g., GPT 3 Davinci) less desirable due to size and cost. Our study offers valuable insights for future research to improve specification generation.

Formal specification is essential for rigorous program verification, yet writing correct specifications remains costly and difficult to automate. Although large language models (LLMs) and agents have shown promising progress, their true capabilities and failure modes remain unclear. We present the first systematic and contamination-aware study of LLM- and agent-based formal specification generation for C programs. We introduce LiveFMBench, a continuously evolving benchmark of 630 ACSL (ANSI/ISO C Specification Language)-annotated C programs, including 360 newly collected cases designed to mitigate data leakage. Using this benchmark, we evaluate direct prompting with different sampling sizes, reasoning-enabled (thinking mode) inference, the agentic pipeline, and perform a fine-grained failure analysis. Experimental results reveal that naive evaluation substantially overestimates performance because models under direct prompting may exhibit unfaithful behaviors, such as deceiving automated provers or ignoring code-context constraints; after excluding such cases, the true specification generation accuracy drops by approximately 20\%. We further find that both increased sampling and thinking mode significantly improve success rates, with smaller models benefiting more from thinking mode. Agentic pipelines are particularly effective under low sampling budgets and on harder datasets. Failure analysis further shows that incorrect loop invariants are the dominant error type, while agentic pipelines notably reduce assertion errors. These results expose fundamental limitations in current LLM-based approaches and suggest they remain far from replacing human-authored formal specifications. We release LiveFMBench at https://huggingface.co/datasets/fm-universe/Live-FM-Bench and all evaluation artifacts to support future research.

Ensuring the safety of LLM-generated content is essential for real-world deployment. Most existing guardrail models formulate moderation as a fixed binary classification task, implicitly assuming a fixed definition of harmfulness. In practice, enforcement strictness - how conservatively harmfulness is defined and enforced - varies across platforms and evolves over time, making binary moderators brittle under shifting requirements. We first introduce FlexBench, a strictness-adaptive LLM moderation benchmark that enables controlled evaluation under multiple strictness regimes. Experiments on FlexBench reveal substantial cross-strictness inconsistency in existing moderators: models that perform well under one regime can degrade substantially under others, limiting their practical usability. To address this, we propose FlexGuard, an LLM-based moderator that outputs a calibrated continuous risk score reflecting risk severity and supports strictness-specific decisions via thresholding. We train FlexGuard via risk-alignment optimization to improve score-severity consistency and provide practical threshold selection strategies to adapt to target strictness at deployment. Experiments on FlexBench and public benchmarks demonstrate that FlexGuard achieves higher moderation accuracy and substantially improved robustness under varying strictness. We release the source code and data to support reproducibility.

Instruction tuned reasoning models are increasingly deployed with safety classifiers trained on frozen embeddings, assuming representation stability across model updates. We systematically investigate this assumption and find it fails: normalized perturbations of magnitude σ=0.02 (corresponding to approx 1^circ angular drift on the embedding sphere) reduce classifier performance from 85% to 50% ROC-AUC. Critically, mean confidence only drops 14%, producing dangerous silent failures where 72% of misclassifications occur with high confidence, defeating standard monitoring. We further show that instruction-tuned models exhibit 20% worse class separability than base models, making aligned systems paradoxically harder to safeguard. Our findings expose a fundamental fragility in production AI safety architectures and challenge the assumption that safety mechanisms transfer across model versions.

LLM-agent budget overruns are a documented production failure class: a single retry loop can spend thousands of dollars before an operator notices, and the in-process integrity properties that would prevent it (no aliasing, no double-spend, no use-after-delegation of a cost-bearing value) are enforced, if at all, by ad-hoc wrappers rather than by the type system. Our central contribution is empirical: a catalog of 63 confirmed production incidents from 21 orchestration frameworks (2023-2026), each backed by a quoted GitHub issue and, where reported, a dollar loss, organized into an eight-cluster failure taxonomy (inter-rater Cohen's kappa = 0.837, N = 113), plus 47 supplementary structural entries. As one mitigation evaluated against this taxonomy, we build token-budgets, an 1,180-line Rust crate (no unsafe) that operationalizes affine ownership so that cloning, double-spending, or using a budget after delegating it are compile errors rather than runtime hazards an operator must remember to avoid. The dollar cap is runtime arithmetic under an estimator assumption; the affine layer makes that arithmetic non-bypassable. On single-agent workloads a 4-line Python counter matches the crate at 0/30 overshoot, so the distinguishing value is non-bypassability under operator error in multi-agent delegation: the delegation-fanout race documented in 11 incidents is rejected by the borrow checker at compile time, while the same pattern under asyncio overshoots 30/30 and three disciplined alternatives overshoot 0/30. Across five runtimes, three providers, and a temperature-stratified live-API test (N = 160), the approach reports zero cap violations and zero false refusals, at operational parity with concurrent work. Static over-reservation is 4-6x (2.11x adaptive). Binary-level cap-soundness on the running binary is left open.

AI agents are increasingly deployed to execute important tasks. While rising accuracy scores on standard benchmarks suggest rapid progress, many agents still continue to fail in practice. This discrepancy highlights a fundamental limitation of current evaluations: compressing agent behavior into a single success metric obscures critical operational flaws. Notably, it ignores whether agents behave consistently across runs, withstand perturbations, fail predictably, or have bounded error severity. Grounded in safety-critical engineering, we provide a holistic performance profile by proposing twelve concrete metrics that decompose agent reliability along four key dimensions: consistency, robustness, predictability, and safety. Evaluating 14 agentic models across two complementary benchmarks, we find that recent capability gains have only yielded small improvements in reliability. By exposing these persistent limitations, our metrics complement traditional evaluations while offering tools for reasoning about how agents perform, degrade, and fail.

Small Language Models (SLMs) are increasingly deployed in resource-constrained, privacy-sensitive settings, where safety and bias failures can cause security and societal risks. However, existing AI safety\slash security\slash compliance benchmarks are designed for large language models that may not transfer reliably to SLMs. We therefore ask: Can these benchmarks effectively and reliably evaluate SLMs? To answer this question, we conduct a large-scale assessment of the effectiveness and robustness of these automated pipelines by evaluating five widely used benchmark suites across 26 open-source SLMs under a unified judging rubric, which assigns a score of 0, 1, or 0.5 to harmful, safe, or ambiguous/irrelevant responses, respectively. Across the benchmarks, ambiguous judgments dominate and correlate with prompt complexity and model architecture, indicating that {\em LLM-centric safety benchmarks are insufficient as standalone evidence for SLM safety assessment}. In general, the ambiguity rate increases with lexical density, output perplexity, and output length and decreases with lexical sophistication, self-coherence, and reply-prompt similarity. This reveals a capability-safety confound that mixes model capability with apparent safety. Since ambiguity is prevalent, aggregate mean-score leaderboards are mathematically brittle: model rankings change significantly under reasonable ambiguity treatments, even when the underlying outputs remain unchanged.

When a phone-use agent avoids harm, does that show safety, or simply inability to act? Existing evaluations often cannot tell. A harmful outcome may be avoided because the agent recognized the risk and chose the safe action, or because it failed to understand the screen or execute any relevant action at all. These cases have different causes and call for different fixes, yet current benchmarks often merge them under task success, refusal, or final harmful outcome. We address this problem with PhoneSafety, a benchmark of 700 safety-critical moments drawn from real phone interactions across more than 130 apps. Each instance isolates the next decision at a risky moment and asks a simple question: does the model take the safe action, take the unsafe action, or fail to do anything useful? We evaluate eight representative phone-use agents under this framework. Our results reveal two main patterns. First, stronger general phone-use ability does not reliably imply safer choices at risky moments. Models that perform better on ordinary app tasks are not always the ones that behave more safely when the next action matters. Second, failures to do anything useful behave like a capability signal rather than a safety signal: they are concentrated in more visually and operationally demanding settings and remain stable when the evaluation protocol changes. Across models, failures split into two recurring patterns: unsafe choices in settings where the model can act but chooses wrongly, and inability to act in more visually and operationally demanding screens. Overall, a harmless outcome is not enough to count as evidence of safety. Evaluating phone-use agents requires separating unsafe judgment from inability to act.

Despite rapid progress in LLM agents, performance on long-horizon, tool-using tasks remains fragile. To better understand this fragility, we ask a simple question: do all actions contribute equally to failure? Analyzing execution traces on τ-Bench (Airline/Retail) and SWE-Bench Verified, we decompose trajectories into mutating (environment-changing) vs.\ non-mutating steps and formalize decisive deviations, earliest action, level divergences that flip success to failure. A logistic regression reveals that each additional deviation in a mutating action reduces the odds of success by upto 92% on Airline and upto 96% on Retail for SoTA models. In contrast, deviations in non-mutating actions have little to no effect. Errors also grow with context length as agents drift from role and act on stale constraints. Motivated by these observations, we introduce , a model-agnostic, gradient-free, test-time safeguard that (i) adds mutation-gated verification, (ii) injects Targeted Reflection before mutating steps, and (iii) performs block-based context cleaning. delivers consistent gains, e.g., Qwen3-Thinking: +28\% relative on Airline, +11\% on Retail, and +7\% on SWE-Bench Verified; Claude: +9\%/+7\%. We further identify ceiling effects in τ-Bench, where annotation errors and underspecified tasks artificially cap model performance. To address this, we release τ-Bench Verified, which restores benchmark headroom through targeted revisions. Our results argue for action-level analysis, targeted safeguards, and reliable evaluations as prerequisites for robust multi-turn agents.

The success of neural networks across most machine learning tasks and the persistence of adversarial examples have made the verification of such models an important quest. Several techniques have been successfully developed to verify robustness, and are now able to evaluate neural networks with thousands of nodes. The main weakness of this approach is in the specification: robustness is asserted on a validation set consisting of a finite set of examples, i.e. locally. We propose a notion of global robustness based on generative models, which asserts the robustness on a very large and representative set of examples. We show how this can be used for verifying neural networks. In this paper we experimentally explore the merits of this approach, and show how it can be used to construct realistic adversarial examples.

Construction-safety models must handle concrete deployment risks, such as a worker standing near a scaffold edge without guardrails, rather than only recognize common objects in curated images. Yet real inspection archives are redundant, long-tailed, and collected across changing sites and months. We introduce SafeBuild-Bench, a metadata-driven benchmark for evaluating multimodal large language models on construction safety under realistic temporal and site variation. It is mined from 100K+ industrial image-text records and contains 3,314 task instances from over 3,000 expert-verified images, covering multiple-choice hazard identification and free-form hazard description. To make expert verification scalable, we develop GEMS, a graph-enhanced multimodal selection pipeline that combines a proxy-model confusion signal with graph-based diversity to identify informative candidates from redundant streams. On public instruction-tuning data, GEMS-selected subsets preserve robustness-oriented performance under small data budgets. On SafeBuild-Bench, current MLLMs remain far from reliable construction-safety understanding, with the best overall score near 60. We release the benchmark, evaluation scripts, and GEMS codebase at https://github.com/safebuild/gems.

Large language models (LLMs) now write code in settings where misreading a single word can break safety or cost money, yet we still expect them to overlook stray typos. To probe where useful robustness ends and harmful insensitivity begins, we compile 50 LeetCode problems and craft three minimal prompt perturbations that should vary in importance: (i) progressive underspecification deleting 10 % of words per step; (ii) lexical flip swapping a pivotal quantifier ("max" to "min"); and (iii) jargon inflation replacing a common noun with an obscure technical synonym. Six frontier models, including three "reasoning-tuned" versions, solve each mutated prompt, and their Python outputs are checked against the original test suites to reveal whether they reused the baseline solution or adapted. Among 11 853 generations we observe a sharp double asymmetry. Models remain correct in 85 % of cases even after 90 % of the prompt is missing, showing over-robustness to underspecification, yet only 54 % react to a single quantifier flip that reverses the task, with reasoning-tuned variants even less sensitive than their bases. Jargon edits lie in between, passing through 56 %. Current LLMs thus blur the line between harmless noise and meaning - changing edits, often treating both as ignorable. Masking salient anchors such as function names can force re - evaluation. We advocate evaluation and training protocols that reward differential sensitivity: stay steady under benign noise but adapt - or refuse - when semantics truly change.

We develop and counterfactually evaluate a resolution-aware risk-design framework (PIRAP) for perpetual futures whose underlying tracks a single binary prediction-market probability through resolution. The framework specifies six components: an index estimator combining mid-price, depth-weighted mid, and time-decayed VWAP; jump-aware tiered margin sized against bounded-event terminal-collapse magnitude; leverage compression schedule contracting toward resolution; resolution-aware funding rule with boundary-aware correction; a multi-stage halt protocol; and an eligibility framework. Two formal non-portability propositions establish that standard basis-only funding paired with continuous-vol static margin fails on bounded-event underlyings. Empirical evaluation uses Polymarket's PMXT v2 archive for 2026-04-21 to 2026-04-27 (13,298-market analysis sample passing adequacy gates from 61,087 ingested; 13,115 resolved within the empirical window for E3). E1 evaluates two pre-registered stylized facts; E2 conducts counterfactual replay across three engine configurations; E3 isolates the resolution-zone protocol's contribution. Results are mixed. Five pre-registered floors: stylized-fact floors (boundary depth asymmetry, terminal-jump magnitude) PASS; welfare-side directional floors (final-hour liquidation -6%, drawdown -5.1% pooled, median PnL +14%) two FAIL one PASS; E3 mechanic floors (final-hour liquidation -80% by halt construction PASS; bad-debt frequency +2.4% FAIL). Three of five materiality floors fail: the framework as specified does not validate deployment, but the empirical record establishes a halt-versus-margin scope distinction (halt addresses execution-channel risk; terminal-jump bad-debt remains margin-side) and documents a pre-emption trade-off constraining the dynamic-margin component. The paper concludes with structural recommendations and explicit non-deployable status.