Papers

Botnets represent the backbone of most modern cybersecurity attacks through which botmasters deploy distributed denial of service and advanced persistent threats against legitimate computer networks. In this paper we introduce the Host Attack Graph model and propose two botnet propagation strategies which we study across network topologies, target selection, and attack strategies together with their effectiveness in time. While strategy and botnet size are important for propagation, our study and simulations show that network topology and target selection should not be easily discarded. Implementation and benchmarks are available at https://codeberg.org/AndreiN/HAGP.

Evaluating user experience (UX) with automated computational methods has gained increasing attention, supported by empirical evidence from UXBench. However, binary preference prediction provides limited insight, while relying on a single user-agnostic reward model overlooks the inherent heterogeneity of users, whose expectations can differ substantially. In this paper, we present UXBench Pro, comprising 1{,}000 test instances derived from real user interactions across 12 task scenarios and 82 domains. Each instance is paired with a FACTORS user profile that characterizes the user through seven interpretable behavioral facets, differentiating user groups. To provide richer evaluation insights, we introduce a dual-perspective paradigm that combines a personalized User Reward Model (URM) for third-person judgment with Sim4Eval, a user simulator that enables multi-turn interactions and provides first-person evaluation across four cognitive state dimensions. To assess the reliability of these based evaluators, we further introduce two meta-benchmarks, URMBench and USimBench, that evaluate how faithfully they reproduce real human preferences and behaviors. Extensive experiments reveal seven key findings that highlight the importance of user modeling and multi-perspective evaluation, offering a fresh perspective on user-centric benchmarking and motivating personalized model optimization.

We propose a symmetric Nitsche method for the biharmonic Dirichlet problem on a smooth domain whose boundary may cut arbitrarily through the computational mesh. Bulk least-squares stabilization in a boundary strip and tangential boundary penalties control the consistency terms through an explicit lifting of the two Dirichlet traces. This gives coercivity on $H^4(\Omega)$ without inverse inequalities and permits a fixed penalty independent of the cut configuration for sufficiently thin strips. Under suitable regularity assumptions, splines of degree $p\geq4$ give energy and $L^2$ error bounds of orders $h^{p-1}$ and $h^{p+1}$. We also analyze a face-stabilized extension to $C^1$ splines of degree $p=2$ and $C^2$ splines of degree $p=3$. Exact-ellipse experiments examine convergence, cut stability, and parameter sensitivity.

Large language models (LLMs) perform remarkably well on complex tasks, yet remain highly vulnerable to prompt injection attacks, where malicious instructions embedded in external data can override user intent. Existing defenses remain limited by model fine-tuning requirements, vulnerability to adaptive attacks, or reliance on brittle handcrafted prompts. We argue that a fundamental source of this vulnerability is the lack of an explicit representation of trust provenance. To address this, we introduce Learnable Trust-Boundary Delimiters (LTBD), a lightweight defense that explicitly encodes trust boundaries in the input while keeping the LLM parameters unchanged. LTBD uses a small number of learnable delimiters to distinguish trusted user instructions from untrusted external data, enabling the model to better respect the intended trust hierarchy. Experimental results show that LTBD substantially outperforms inference-time defenses and performs competitively with training-based approaches, while preserving benign-task utility and introducing negligible inference overhead. In particular, LTBD achieves 0.00% ASR on AlpacaFarm and only 0.11-0.19% ASR on TaskTracker. LTBD also remains effective under adaptive attacks, where adversaries have full knowledge of the defense and explicitly attempt to bypass it.

As electric vehicle volume increase, the interest for reusing their retired batteries grow. Giving a second life to batteries reduce their environmental impact and provide access to more affordable energy storage systems. This lifespan extension is of interest in a wide range of fields as the reuse offer a solution for end-of-life batteries management and the development of renewable energies. Although several review articles have described opportunities and barriers related to reuse, to our knowledge none have synthesized insights from studies that conducted experiments on retired batteries. This article aims to address this gap by providing a detailed analysis of more than 150 articles. This article's main findings are the proposition of a new vocabulary for batteries end-of-life, an evaluation of state of health and dispersion in retired batteries as well as the synthesis of aging and safety studies on these batteries. In a nutshell, this review show that the performance of retired batteries can be high, their dispersion should be managed and their degradation can be slow and safe. Limitations of current battery research ideas for future experiments and ideas for future studies are also presented.

Deploying intelligent robotic systems that interact with humans through gestures requires neural networks capable of recognizing diverse temporal patterns. We present a systematic benchmark of ten abstract sequential tasks–five permutation-invariant (set) and five order-dependent (sequence) problems–evaluated across eighteen neural network architectures spanning recurrent, convolutional, attention-based, and set-function families. Beyond the core architecture-task grid, we explore numerous preprocessing and target-variable transformations, yielding more than 250 distinct experimental configurations. All variants are trained and tested under strictly identical conditions (fixed random seeds, shared hyperparameters, shared data splits) to ensure fair and reproducible comparison. Ranking across all ten tasks reveals four consistently top-performing architectures–BiGRU, TCN, Conv1D, and GRUReLU–all compact enough for real-time deployment (under 2,000 parameters in the benchmark setting). Based on this ranking, we apply three architecturally diverse top models (BiGRU, TCN, and GRUReLU) to a practical robotics problem: estimating the execution speed of dynamic arm gestures from skeletal keypoint sequences. Three speed interpretations (peak count, period time, and mean spike spacing) are evaluated on a custom dataset of eight traffic-related gesture classes comprising 256,710 frames recorded via OpenPose. The best configuration achieves a mean absolute error of 0.198 on the peak-count interpretation, corresponding to roughly 5% relative error, while the period-time interpretation reaches approximately 4% relative error, and the mean spike spacing interpretation approximately 8% relative error. These results demonstrate that neural networks can reliably estimate gesture speed from skeletal data, opening a path toward speed-aware gesture-controlled robotic systems.

Machine unlearning updates a trained model after records are deleted, aiming to match exact retraining without repeating the full training procedure. We develop Gaussian mechanisms for Newton updates under sequential deletion requests. Using Gaussian differential privacy (GDP) and its adaptive composition rule, we show that the full sequence of released models is statistically difficult to distinguish from matched exact retraining. To calibrate these mechanisms for empirical risk minimization, we derive upper bounds on the error of the Newton approximation relative to exact retraining and on how this error changes after each deletion batch. Independent Gaussian noise is calibrated using bounds on the full residual at each release, whereas Gaussian random walk noise uses smaller bounds on residual increments. These bounds yield allocations minimizing the worst-case maximum noise variance across releases under the resulting GDP certification constraints. With count-based bounds, the random walk asymptotically matches the worst-case variance of a single release at deletion cap $M$, while independent noise incurs an additional factor of order $M$. Set-based bounds can reduce the noise variances by using gradients and Hessians of the deleted records. For singleton deletion, we further show that count-based independent noise, count-based random walk noise, and set-based independent noise are minimax among fixed Gaussian covariances under their respective residual or increment bounds. With set-based bounds, allowing variances to adapt to deleted records can improve on every fixed covariance by a factor of order $(\log M)^2$ on some data sequences. The residual and noise bounds also yield parameter and predictive consistency relative to exact retraining, uniformly over deletion policies. Simulations and a credit default data analysis evaluate bounds, noise variances, and estimation errors.

Repairing scientific models from functional observations differs fundamentally from supervised prediction: feedback may certify a solution without revealing which structural correction is responsible. We study this setting for genome-scale metabolic model (GEM) repair, where multiple reaction edits can explain the same phenotypes and many apparently distinct edits correspond to the same biological mechanism. This many-to-one structure creates a hidden failure mode for conventional exploration: diversity in the output space need not translate into diversity of scientific hypotheses. We introduce QuotientPO, which collapses equivalent repairs into canonical mechanisms and optimizes exploration directly over the resulting quotient space. To make quotient exploration informative under finite rollouts, we derive a kernelized Rényi estimator that resolves graded crowding among distinct repair cores beyond coarse exact-match counts. On 2,212 held-out GEMs, QuotientPO improves Success@32 from 17.93% to 20.10% (+12.1% relative) while consistently increasing distinct successful-core discovery under the same sampling budget. These results establish quotient-space exploration as a principled approach to mechanism-level discovery under verifier-induced equivalence.

Traversability is essential for visual navigation but varies with robot capabilities and user preferences. Conventional pipelines often rely on explicit costmaps or segmentation masks with predefined criteria, requiring hand-crafted rules and careful tuning. Moreover, viewpoint-dependent segmentation masks complicate asynchronous planning under perception latency. We present LaTraNav, a framework that learns language-conditioned traversability representations for adaptive visual navigation. Its asynchronous architecture combines a slow vision-language model that produces latent representations of traversability and navigation goals, with a fast flow-matching planner conditioned on these representations. To train the system, we develop a simulation-based data generation pipeline with controllable trajectories, producing observations paired with language instructions, traversability maps, goal locations, and diverse trajectories. Photorealistic image translation further enhances visual realism. Evaluations on datasets from multiple sources demonstrate effective language-guided traversability segmentation and goal localization by the slow VLM, alongside adaptive pixel-space path planning by the fast planner. Latent conditioning improves planning performance over explicit segmentation masks, while asynchronous scheduling increases the path-update rate by $6.05\times$ at the same semantic-update rate.

Consensus can make pseudo-label learning more reliable, but only when its predictors contribute genuinely different evidence. Multiple models that repeat the same boundary provide additional votes without additional information. We address this problem by con structing decision sources through controlled changes to within-class structure. Starting from a shared graph representation, we vary center granularity and neighborhood mixing, reproduce each resulting source to test its stability, and select a complementary subset using node pair coassignment. Unanimous predictions from the selected sources are then ranked for student training. On the public fixed splits of Cora, CiteSeer, and PubMed, evaluated with five random seeds, the constructed sources improve fixed-budget training pseudo-label precision by 1.19 to 4.39 percentage points over three conventionally initialized GCN sources. Under matched structural filters, three-source consensus is more precise than each constituent source in all 45 dataset slot eed comparisons. The gains are strongest in pseudo-label quality: downstream accuracy remains competitive but does not lead on every dataset. These results identify source construction rather than model count alone as an important design problem for consensus-based pseudo-label learning.

Parameter-efficient fine-tuning (PEFT) enables large language models (LLMs) to adapt to specialized tasks, but often at the cost of degrading general capabilities acquired during pretraining. Existing approaches primarily mitigate this trade-off through data replay or regularization, relying on additional data or explicit optimization constraints. We instead focus on a different question: where should adaptation be applied? We find that fine-tuning different Transformer layers produces different target-task gains and degrees of capability degradation, suggesting that not all layers are equally suitable for adaptation. To characterize this difference, we use layer-wise empirical Fisher information to measure target-task sensitivity. However, computing Fisher scores requires backward computation and becomes increasingly expensive for large models. We therefore introduce input–output cosine similarity as a lightweight, forward-only proxy for ranking layer sensitivity. Across models and tasks, layers with lower input–output similarity consistently exhibit higher empirical Fisher scores. Building on this observation, we propose Layer-Selective LoRA (LS-LoRA), which places trainable LoRA adapters only in layers with low input–output similarity. Experiments on mathematical reasoning and code generation show that LS-LoRA improves average target-task performance while retaining substantially more commonsense reasoning capability than standard all-layer LoRA, demonstrating that carefully choosing where to adapt can provide a simple and effective way to balance target-task adaptation and general capability retention.

We develop a model-free policy gradient method for discrete-time mean-field control (MFC). In MFC, the policy affects the objective both through the controlled dynamics and through the population distribution. Standard REINFORCE estimators capture the first effect but not the second. We introduce Transport REINFORCE, a transport map-based approach that perturbs a suitable transformation of the population distribution to estimate this missing mean-field contribution. The method applies to both finite and continuous state spaces. In finite state spaces, we perturb the population distribution directly on the probability simplex through a convex combination of the current population weights and random weights. In continuous state spaces, we project the population distribution onto the manifold of Gaussian mixtures, and then randomize it via a transport map that ensures the perturbed law remains within this manifold. We prove consistency of the perturbed objective and gradient as the perturbation vanishes, and derive bias and mean-square error bounds for the resulting sample-based gradient estimator. Numerical experiments on several MFC benchmarks show that Transport REINFORCE improves over standard REINFORCE.

As large language models increasingly move toward repository-level software engineering, existing code-generation benchmarks remain fragmented across language coverage, task granularity, and evaluation protocols, impeding systematic comparison. To address this gap, we present PolyCodeEval, a unified multilingual and multi-granularity benchmark for code generation. It comprises 2,590 code generation tasks spanning functions to repositories, derived from 58 real, executable open-source repositories in five programming languages. All tasks are evaluated under a unified execution-based protocol with integration procedures tailored to their generation targets. Building on this benchmark, we evaluate frontier large language models, state-of-the-art specialized methods, and general coding agents. Our results show that existing approaches still struggle to correctly generate complete code fragments across granularities and languages. Specifically, the studied methods generate at most 71.7%, 76.7%, and 31.0% correct functions, files, and repositories, respectively, with performance varying widely across languages. Paired experiments further show that implementation context from related functions in the same file improves the executable correctness of function generation. Method rankings also vary across task granularities and programming languages, highlighting the importance of multilingual, multi-granularity evaluation for comprehensively assessing code generation capabilities.

Knowledge distillation enables efficient spatiotemporal prediction by transferring knowledge from an accurate teacher to a compact student. However, matching outputs or features independently for each sample leaves cross-sample predictive structure underused. Exploiting this structure requires representations and historical references that reflect the dynamics of each task. We propose TAM, a Task-Aware Memory Distillation framework that organizes a frozen teacher's knowledge into a bounded, retrievable history. Memory entries encode latent features, forecast changes, or flow residuals, while task-specific selection rules identify relevant historical references. The student either matches the teacher's similarity distribution over shared references or regresses observation-conditioned residual prototypes. These objectives complement supervised prediction and conventional distillation. The teacher, memory, and auxiliary adapters are used only during training, leaving student inference unchanged. We evaluate TAM on video prediction, weather forecasting, and traffic flow prediction across multiple teacher-student configurations. Averaged over four paired runs, adding TAM improves SSIM on all six video datasets and reduces MSE on five relative to the corresponding KD baselines. Mean paired MSE reductions reach 1.86% on KittiCaltech, 1.93% on WeatherBench with a gSTA teacher, and 1.01% on TaxiBJ. These results demonstrate the utility of historical teacher supervision across distinct forecasting tasks without additional student inference cost.

We give a direct information-theoretic proof of the Plünnecke–Ruzsa inequalities for finite subsets of abelian groups. The argument rests on an elementary coupling inequality proved by maximizing joint entropy, without tensor powers or asymptotic constructions. It also yields Ruzsa's sumset triangle inequality and an extension to non-abelian groups.

An agent can complete a task without improving how it works. Turning task experience into reusable capability requires connecting the changed component to its evaluation and subsequent use. We present AgentEvolver, a system for developing capabilities during task execution while keeping the foundation model fixed. Eight entity families expose reusable operations, methods, agents, control flow, interfaces, and supporting state to revision through a common versioned lifecycle. A shared Runtime coordinates ongoing work, while persistent planning and recoverable context preserve task direction and supporting evidence. We evaluate task outcomes on SWE-bench Pro Public and examine capability changes in six application cases. The team reports an 82.08% resolution rate with evolution, exceeding its reported baseline without evolution. The cases show retained capabilities entering later website, game, and research work, while also documenting incomplete objectives and an unsuccessful strategy. These findings distinguish improvement in a reusable component from success on the final task. AgentEvolver provides a concrete basis for studying capability accumulation through execution; independent-task transfer and total development cost remain open questions.

This paper addresses multiview RGB-D point cloud registration, aiming to estimate global rigid poses for unordered RGB-D scans and align them in a metrically consistent coordinate frame. The conventional pairwise-then-global paradigm suffers from locally optimized pairwise registration, severe error propagation and high computational burden. In particular, existing methods typically treat RGB data as a mere auxiliary matching cue and overlook the holistic geometric priors (e.g., camera poses and 3D models) encoded across image sequences. This paper introduces PointVGGT, a zero-shot framework built upon a novel foundation-then-refinement paradigm that systematically leverages visual geometry foundation models (e.g., VGGT) as the computational backbone for robust, training-free multiview RGB-D registration. In the foundation stage, we directly recover metrically consistent global poses (without any pairwise estimation) by grounding the scale-ambiguous pose predictions of the foundation model against metric depth observations. In the refinement stage, we introduce an efficient voxelized spatial hashing mechanism that exploits the globally coherent 3D reconstruction (induced by the foundation model) as a shared spatial anchor, enabling dense multiview correspondences in near-linear time. On top of this, an IRLS-based robust motion-only bundle adjustment is performed using a conjugate gradient solver to jointly minimize the correspondence and reprojection residuals for multiview pose refinement. Extensive experiments on indoor/object-centric/outdoor datasets verify the outstanding zero-shot registration accuracy and computational efficiency of our proposed method.

Generating ultrasound reports from multiple images requires aggregating clinical evidence across views, yet archived key frames capture only part of the dynamic examination. Raw-report imitation is therefore misaligned with visual supervision: content that is clinically valid for the full examination may be unverifiable from the images available to a model. This gap creates a clinical behavior alignment problem. A model must preserve visible findings, avoid diagnostic reversals and unsupported completion, and not collapse into conservative templates. We propose CAMEO, a Clinically Aware Multi-image Evidence-grounded Orchestration framework for ultrasound report generation. Stage I learns ultrasound visual-language primitives; Stage II performs Cross-View Evidence Grounding by distilling trusted visible report points into multi-image QA and report-style supervision; and Stage III performs Clinically Aware Preference Alignment using clinical-error-oriented preference pairs. From USReport, we construct USReport-Distilled with 17,670 evidence-grounded paired-image training instances and USReport-Pref with 21,869 preference pairs; we additionally use 25,631 PubMedVision-US ultrasound instruction samples for domain adaptation and multi-image instruction tuning. On the primary USReport-Distilled benchmark, CAMEO improves over EchoVLM from 0.25 to 0.40 BLEU-1, 0.28 to 0.45 ROUGE-1, and 0.27 to 0.43 METEOR, while raising ClinicalScore from 55.02 to 74.20. These results underscore the value of evidence-grounded supervision, clinically aware alignment, and clinically structured evaluation for reliable ultrasound report generation.

Error-correcting codes are a foundational technology for representing information robustly against noise in communication and data storage. The binary code packing problem, which seeks to maximize the number of codewords at a fixed code length and minimum distance, is a fundamental problem in coding theory that remains open for many parameter choices. We give explicit binary codes with parameters $(n,M,d)=(22,84,9)$, $(24,196,9)$, and $(25,65,11)$, where $n$, $M$, and $d$ denote the code length, number of codewords, and minimum distance, respectively. These establish the lower bounds $A_2(22,9)\ge84$, $A_2(24,9)\ge196$, and $A_2(25,11)\ge65$, where $A_2(n,d)$ denotes the maximum possible number of codewords, improving the respective lower bounds 80, 192, and 64 in the public table of general binary codes. Most notably, the third result improves the lower bound supplied by a lexicographic construction for the first time in 66 years, while the first two improve bounds that have stood for 21 years. The new codes represent more messages without changing the code length or error-correction guarantees, with gains compounding multiplicatively across blocks. We release all codewords and an exhaustive verifier to enable independent verification.

Cross-view geo-localization (CVGL) aims to estimate geographic locations by matching images captured from different viewpoints, such as drone and satellite views. Existing methods mainly rely on visual representations, but often fail to jointly model fine-grained structural correspondences and semantic priors, making them prone to confusion between visually similar but semantically different regions, and thus limiting robustness under large viewpoint variations. To address these challenges, we propose \textbf{S$^3$Geo}, a structure-semantic synergistic learning framework for cross-view matching. Specifically, we first introduce a Decoupled Query Pooling (DQP) module to extract a compact set of region-aware features from dense tokens, enabling explicit modeling of local structural patterns. We then design a query-level contrastive learning scheme with an optimal transport (OT)-based formulation to establish soft correspondences under cross-view spatial misalignment. Furthermore, we incorporate a Semantic Knowledge Distillation (SKD) strategy from a frozen CLIP teacher to transfer semantic priors and relational structures, thereby improving discrimination on hard negatives. By operating synergistically, the semantic priors provide robust contextual filtering, which guides the structural module to establish precise spatial alignments. Experiments on the University-1652 and SUES-200 datasets demonstrate that \textbf{S$^3$Geo} consistently outperforms state-of-the-art approaches without increasing inference complexity, validating the effectiveness of jointly modeling structural and semantic information for CVGL.

We introduce NanoProof, to our knowledge the first factorized execution-guided theorem prover in Lean 4 whose training data, extraction tooling, training pipeline, and weights are all released, making it end-to-end reproducible using open-source resources. To this end, we build and release a dataset of structured proof trees, as well as a tool for programmatic interaction and data extraction within the Lean 4 formal verifier. To support sustainable research, we focus on compute efficiency to facilitate accessible training and evaluation. NanoProof achieves 50.8% pass@16 on MiniF2F-Test, exceeding the two closest systems of its class, HyperTree Proof Search and ABEL, at roughly 90x and 7x less compute, and using more than four orders of magnitude less compute than AlphaProof. Stronger open-weight provers exist, but they are fine-tuned from large pretrained language models and release neither training data nor pipeline; NanoProof shows that the factorized execution-guided class of provers can be rebuilt from scratch with modest resources.

LLM agents can spend millions of tokens during vulnerability discovery without producing a working proof of concept (PoC). What consumes that budget, and why does it fail to produce results? We diagnose these costs and failures through a multi-axis open-coding study of 200 CyberGym traces, spanning four agents (i.e., Codex, OpenCode, Cybench, and EnIGMA) under an unaided baseline and four existing efficiency methods. The study reveals three key findings. First, different agents vary substantially in success and cost, and higher spending does not consistently yield better outcomes. Second, code localization and understanding, together with vulnerability reasoning and trigger design, account for 60.4% of tokens and represent the two leading bottlenecks in failed runs. Third, only 24.4% of matched comparisons preserve success at lower total cost; unsuitable signals and auxiliary overhead limit the benefits of existing methods. Motivated by these findings, we present AVRI, an Agent-centric Vulnerability Reasoning Interface built around a persistent Bidirectional Evidence Trace (BET). BET connects how the harness consumes input with the conditions required to make a selected operation unsafe, retaining source-supported correspondences alongside the agent's hypotheses and open questions. Reading, analysis, and persistence commands help agents build and reuse this evidence rather than repeatedly retrieve and reconstruct it. On 20 evaluation tasks, AVRI reduces total cost by 18.0% for Codex and 23.7% for OpenCode while preserving success rates and improving or maintaining recall.

A growing body of evidence suggests that political polarization and mental health and wellbeing influence each other. Yet the two directions, how polarization shapes mental wellbeing and how mental wellbeing shapes polarization, remain siloed across disciplines. We review both literatures to evaluate the strength and alignment of evidence for bidirectional effects. We find that the literature varies widely in constructs, measures, and levels of analysis, and that the evidence for the two pathways is asymmetric: links from polarization to mental wellbeing are more direct, grounded in well-developed theoretical frameworks and social-relational mechanisms. In contrast, the reverse pathway is substantially less direct, with studies often examining cognitive and socio-emotional factors, or political outcomes adjacent to polarization rather than polarization itself. We identify clear gaps in the literature highlighting the need for future studies with conceptual clarity, unified frameworks, validated measures, and multilevel designs examining both pathways within the same empirical and theoretical setting.

LLM-based multi-agent systems (MASs) are increasingly used to solve complex tasks through coordinated reasoning, tool use, and interaction with external resources. However, attributing failures in such systems remains challenging because the observed outcome often does not directly reveal the error responsible for the failed execution. In this work, the attribution target is the decisive error, defined as the agent–step pair whose correction would recover the failed execution. Existing approaches largely identify suspicious steps without explicitly modeling how errors propagate across interactions or persist in unresolved loops, making decisive errors difficult to distinguish from downstream failure symptoms. We propose Error-Propagation Modeling for Failure Attribution (EMFA). EMFA constructs a structured representation of the failed trajectory, models both cascading propagation and persistent interaction loops, and uses propagation-aware candidate screening followed by counterfactual verification to identify the decisive agent–step pair. On the Who&When benchmark, EMFA achieves state-of-the-art step-level attribution accuracy and remains competitive at the agent level. It improves the previous best step-level results by 3.45 and 4.40 percentage points on the Hand-Crafted and Algorithm-Generated subsets, respectively.

Journals and conferences have begun to screen submitted manuscripts for text written using large language models (LLMs). The reliability of this screening rests on benchmark evaluations against a fixed set of LLM versions, while the versions in actual use keep changing. Here we quantify how this LLM turnover affects the screening of scientific manuscripts. We paired 4,000 pre-ChatGPT abstracts from the Proceedings of the National Academy of Sciences with their rewrites by 23 LLM versions from three vendors, released between June 2023 and August 2026. We then trained detectors under maintenance scenarios ranging from a detector retrained on every new version to one trained once and never updated. Detectors trained only on a vendor's past versions can collapse at the boundaries between model generations: calibrated to falsely flag 1% of human-written abstracts, they catch above 99% of rewrites just before the sharpest boundary and 3.8% just after it. Detectors trained on later versions can also miss rewrites of earlier ones. Vocabulary differences between versions largely track where detection transfers and where it fails. In the two screening scenarios we simulated, screens covering all 23 versions either flagged one in eight human-written abstracts or missed one in three rewrites of the newest version. Indeed, a commercial detector missed most rewrites of the version just after the sharpest boundary while flagging almost no human-written abstracts. Research-integrity policy should therefore treat the benchmark accuracy of a detector as provisional, to be re-verified with every LLM release, including earlier versions.

In this paper, we provide an overview of the NTCIR-19 Automatic Evaluation of LLMs 2 (AEOLLM-2) task. Building on the success of the NTCIR-18 core task AEOLLM, we proposed AEOLLM-2 for NTCIR-19 to further investigate automatic evaluation methods for Large Language Models (LLMs), particularly in long-form text generation scenarios. In AEOLLM-2, we introduced a new subtask, Deep Research Evaluation, which focuses on the automatic evaluation of long-form deep research reports generated by LLMs. Participants developed evaluation methods to automatically assess the quality of these reports, and the performance of each method was measured by comparing its scores against human-annotated ground-truth labels. This year, we received 91 runs from 10 teams in total. This paper describes the background of the task, the dataset construction, the evaluation measures, the participants' methods, and the final evaluation results.

In this paper, we establish a quantitative finite-time approximation of scattering fields for nonlinear Alfvén waves in three-dimensional ideal incompressible magnetohydrodynamics near a strong constant magnetic background. Using the global weighted estimates, we prove that truncating the scattering profiles at time $T$ introduces an error in both the $L^\infty$ norm and the $H^{N_*+1}$ norm of order $$ O\bigl(\varepsilon^2(R+T)^{-\delta}\bigr), $$ where $\varepsilon\in (0,1)$ measures the size of the initial perturbation, $R\ge100$ is the scale parameter in the weighted energy, $\delta\in(0,2/3)$ is the exponent related to weights, and $N_*+1$ is the Sobolev regularity order assumed for the initial data. The pointwise estimate follows from the decay of the nonlocal pressure along nonlinear characteristics, while the Sobolev estimate combines higher-order weighted pressure bounds with estimates for derivatives of the characteristic flows. Numerical experiments measure pointwise and Sobolev pressure-integral tails to verify the quadratic dependence of the initial perturbation amplitude.

Coding agents produce large, tangled patches that mix multiple development purposes, making the code hard to review and maintain. Commit untangling offers the promise of organizing such large patches into untangled, manageable commits. This paper emphasizes two important limitations in existing commit untangling studies. First, they do not consider that untangled commits are ordered and should leave the code runnable. In practice, maintainers are unlikely to accept commits that prevent the code from running. Second, existing studies claim that commit untangling helps software maintenance. However, they conduct syntactic comparisons between the untangled commits and developers' original commits without directly showing the claimed maintenance benefits. To address these gaps, this paper makes two novel contributions: (1) RucTangle, the first agentic method that untangles commits while keeping the code runnable after each commit; and (2) TangleEval, the first evaluation framework that quantifies how untangled, manageable commit histories help coding agents repair bugs. We compare RucTangle against four untangling methods on 131 agent-generated patches. All histories produced by RucTangle are runnable, while baselines produce 20.6%-37.4% unrunnable commit histories. We further collect 453 agent-generated patches that introduce regressions (i.e., causing previously passing tests to fail) and ask two other coding agents to repair regressions. Augmenting agent context with RucTangle-produced histories yields 5.2% absolute improvement in pass@1. We also analyze agent trajectories to learn how they use untangled commits to navigate and fix bugs. Our findings demonstrate the value of adopting established software engineering practices in the era of coding agents, which broaden the future research agenda: how can agents actively use software history to make better development decisions?

Current frontier LLMs can theoretically process long contexts with 1M tokens or more. But to what extent can they go beyond simple retrieval and perform deeper reasoning over such long contexts? We empirically investigate long-horizon reasoning capabilities of LLMs, focusing on deductive logic expressed in Prolog. We construct ProloNg, a synthetic testbed to probe Prolog Long Reasoning, which systematically varies the complexity (reasoning depth) of problems, where the hardest case has a reasoning depth of 22 and 62k context length. We study 8 reasoning models across 5 families of frontier LLMs, and find that performance degrades substantially as reasoning depth grows, with the majority of models approaching chance beyond depth 10.

Robot navigation commonly uses wide-coverage, high-frequency sensing to reduce partial observability; this reliance becomes restrictive when another task temporarily redirects a shared sensor from navigation, interrupting navigation-relevant observations. We study navigation under intermittent perception: acting from an internal spatial belief and looking again only when execution needs a new observation, potentially freeing the shared sensor for other tasks between navigation observations. ALONE, a Bayesian spatial world model, propagates a structured spatial belief using executed actions and corrects it with selectively acquired observations; learned priors over common geometric structures infer unobserved structure from available observation history. It decodes the belief into a spatial estimate for the motion-planning module and predicts a reliability map expressing confidence in the estimate's accuracy. ALONE requests an observation only if insufficient reliability hinders navigation and new evidence should make relevant-region spatial information more reliable; otherwise, it continues acting from the propagated belief. We instantiate ALONE for drone navigation with intermittent single-camera depth images. Across two simulated scene families, it achieves 98% and 97% closed-loop success at a 10 Hz decision rate. Among successful trials, median fractions of decision steps requiring a new depth observation are only 0.9% and 1.3%, respectively, demonstrating high navigation success with substantially reduced observation demand. Real-world indoor flight experiments further validate navigation under intermittent depth observations, with all 10 trials successful.