Daily Papers

Leaderboards rank long-horizon agents by their final outputs. Yet a higher score alone does not establish whether two systems are comparable or which stage accounts for the difference. Unequal evidence, inputs, or budgets can affect scores, and statistical corrections do not remove this mismatch. We introduce compositional controllability to address these questions. A comparison window covers one stage, several stages, or the whole agent. Our central result bounds the gap between observed and controlled score differences using only nuisance outside the window. This yields an admissibility test applied before scores are inspected. Inadmissible comparisons are refused. For admissible pairs, an ordering is certified only when the score gap exceeds the combined sampling and nuisance radii; otherwise, it remains undecided. These decisions give each system a rank interval. We introduce BioLitBench, a benchmark of 2,042 biomedical articles represented as structured claim graphs. Among seven published pipelines, a conventional statistical analysis declares a winner in 14 of 21 pairwise comparisons. Yet the top-ranked system alone received the target review's bibliography. To isolate pipeline performance, our test requires matched inputs and a fixed backbone model. It refuses 11 of the 21 comparisons, including every comparison involving the top-ranked system. Seven of the 14 conventional conclusions fall within these refused pairs. The same comparison windows support stage-level training. We train SCRIBE on Qwen3.8-27B using rewards measured at each stage's exit. Under matched evidence, SCRIBE achieves a certified rank interval of [1,2], with certified advantages over all evaluated published pipelines and the evaluated Claude and OpenAI agents. Under same pool, SCRIBE matches the strongest published retriever and is certified above three published pipelines.

A coding agent combines a model with a harness, which decides what the model sees, which tools it can use, and how the work continues. We ask whether changing the harness changes the result when the model and task stay fixed. We compare two configurations of the same harness on three coding benchmarks. The control supplies the full conversation in time order, while the treatment keeps the same record but mechanically shortens older tool results as the context fills and responds to repeated or stalled work. Under tight context, the treatment raises mean per-task fail-to-pass fraction (F2PF) in all three pressure comparisons and increases complete solutions on SWE-bench Verified and SWE-bench Pro. The tight-window Verified comparison uses 169 tasks, a 20,480-token window, and a fixed 480-second attempt endpoint; on this cohort, treatment raises mean per-task F2PF from 28 percent to 49 percent and complete solutions from 43 to 72. Without model-specific retuning, the same frozen treatment also raises both endpoints on the same cohort for three additional models with different designs. In the wide-window Qwen3.6 comparisons, observed arm outcomes are close on Verified and Pro, while FeatureBench retains a higher mean per-task F2PF under treatment. On the wide-window Verified cohort, treatment also serves fewer prompt tokens per turn. Because changing the harness changed what unchanged model weights could accomplish, coding-agent evaluations should treat the model and harness together as the tested solver.

Evaluating object removal in images and videos remains challenging because the task is inherently one-to-many, yet existing metrics frequently disagree with human perception. Full-reference metrics reward copy-paste behaviors over genuine erasure; no-reference metrics suffer from systematic biases such as favoring blurry results; and global temporal metrics are insensitive to localized artifacts within edited regions. To address these limitations, we propose RC (Removal Coherence), a pair of perception-aligned metrics: RC-S, which measures spatial coherence via sliding-window feature comparison between masked and background regions, and RC-T, which measures temporal consistency via distribution tracking within shared restored regions across adjacent frames. To validate RC and support community benchmarking, we further introduce PROVE-Bench, a two-tier real-world benchmark comprising PROVE-M, an 80-video paired dataset with motion augmentation, and PROVE-H, a 100-video challenging subset without ground truth. Together, RC metrics and PROVE-Bench form the PROVE (Perceptual RemOVal cohErence) evaluation framework for visual media. Experiments across diverse image and video benchmarks demonstrate that RC achieves substantially stronger alignment with human judgments than existing evaluation protocols. The code for RC metrics and PROVE-Bench are publicly available at: https://github.com/xiaomi-research/prove/.

Transformers have astounding representational power but typically consume considerable computation which is quadratic with image resolution. The prevailing Swin transformer reduces computational costs through a local window strategy. However, this strategy inevitably causes two drawbacks: (1) the local window-based self-attention hinders global dependency modeling capability; (2) recent studies point out that local windows impair robustness. To overcome these challenges, we pursue a preferable trade-off between computational cost and performance. Accordingly, we propose a novel factorization self-attention mechanism (FaSA) that enjoys both the advantages of local window cost and long-range dependency modeling capability. By factorizing the conventional attention matrix into sparse sub-attention matrices, FaSA captures long-range dependencies while aggregating mixed-grained information at a computational cost equivalent to the local window-based self-attention. Leveraging FaSA, we present the factorization vision transformer (FaViT) with a hierarchical structure. FaViT achieves high performance and robustness, with linear computational complexity concerning input image spatial resolution. Extensive experiments have shown FaViT's advanced performance in classification and downstream tasks. Furthermore, it also exhibits strong model robustness to corrupted and biased data and hence demonstrates benefits in favor of practical applications. In comparison to the baseline model Swin-T, our FaViT-B2 significantly improves classification accuracy by 1% and robustness by 7%, while reducing model parameters by 14%. Our code will soon be publicly available at https://github.com/q2479036243/FaViT.

Recent successful applications of convolutional neural networks (CNNs) to audio classification and speech recognition have motivated the search for better input representations for more efficient training. Visual displays of an audio signal, through various time-frequency representations such as spectrograms offer a rich representation of the temporal and spectral structure of the original signal. In this letter, we compare various popular signal processing methods to obtain this representation, such as short-time Fourier transform (STFT) with linear and Mel scales, constant-Q transform (CQT) and continuous Wavelet transform (CWT), and assess their impact on the classification performance of two environmental sound datasets using CNNs. This study supports the hypothesis that time-frequency representations are valuable in learning useful features for sound classification. Moreover, the actual transformation used is shown to impact the classification accuracy, with Mel-scaled STFT outperforming the other discussed methods slightly and baseline MFCC features to a large degree. Additionally, we observe that the optimal window size during transformation is dependent on the characteristics of the audio signal and architecturally, 2D convolution yielded better results in most cases compared to 1D.

The paper proposes a framework that combines behavioral and computational experiments employing fictional prompts as a novel tool for investigating cultural artifacts and social biases in storytelling both by humans and generative AI. The study analyzes 250 stories authored by crowdworkers in June 2019 and 80 stories generated by GPT-3.5 and GPT-4 in March 2023 by merging methods from narratology and inferential statistics. Both crowdworkers and large language models responded to identical prompts about creating and falling in love with an artificial human. The proposed experimental paradigm allows a direct comparison between human and LLM-generated storytelling. Responses to the Pygmalionesque prompts confirm the pervasive presence of the Pygmalion myth in the collective imaginary of both humans and large language models. All solicited narratives present a scientific or technological pursuit. The analysis reveals that narratives from GPT-3.5 and particularly GPT-4 are more more progressive in terms of gender roles and sexuality than those written by humans. While AI narratives can occasionally provide innovative plot twists, they offer less imaginative scenarios and rhetoric than human-authored texts. The proposed framework argues that fiction can be used as a window into human and AI-based collective imaginary and social dimensions.

In recent years, the potential applications of machine learning to Minimally Invasive Surgery (MIS) have spurred interest in data sets that can be used to develop data-driven tools. This paper introduces a novel dataset recorded during ex vivo pseudo-cholecystectomy procedures on pig livers, utilizing the da Vinci Research Kit (dVRK). Unlike current datasets, ours bridges a critical gap by offering not only full kinematic data but also capturing all pedal inputs used during the procedure and providing a time-stamped record of the endoscope's movements. Contributed by seven surgeons, this data set introduces a new dimension to surgical robotics research, allowing the creation of advanced models for automating console functionalities. Our work addresses the existing limitation of incomplete recordings and imprecise kinematic data, common in other datasets. By introducing two models, dedicated to predicting clutch usage and camera activation, we highlight the dataset's potential for advancing automation in surgical robotics. The comparison of methodologies and time windows provides insights into the models' boundaries and limitations.

Claude Code is an agentic coding tool that can run shell commands, edit files, and call external services on behalf of the user. This study describes its comprehensive architecture by analyzing the publicly available TypeScript source code and further comparing it with OpenClaw, an independent open-source AI agent system that answers many of the same design questions from a different deployment context. Our analysis identifies five human values, philosophies, and needs that motivate the architecture (human decision authority, safety and security, reliable execution, capability amplification, and contextual adaptability) and traces them through thirteen design principles to specific implementation choices. The core of the system is a simple while-loop that calls the model, runs tools, and repeats. Most of the code, however, lives in the systems around this loop: a permission system with seven modes and an ML-based classifier, a five-layer compaction pipeline for context management, four extensibility mechanisms (MCP, plugins, skills, and hooks), a subagent delegation mechanism with worktree isolation, and append-oriented session storage. A comparison with OpenClaw, a multi-channel personal assistant gateway, shows that the same recurring design questions produce different architectural answers when the deployment context changes: from per-action safety classification to perimeter-level access control, from a single CLI loop to an embedded runtime within a gateway control plane, and from context-window extensions to gateway-wide capability registration. We finally identify six open design directions for future agent systems, grounded in recent empirical, architectural, and policy literature.

Embedding text sequences is a widespread requirement in modern language understanding. Existing approaches focus largely on constant-size representations. This is problematic, as the amount of information contained in text often varies with the length of the input. We propose a solution called Nugget, which encodes language into a representation based on a dynamically selected subset of input tokens. These nuggets are learned through tasks like autoencoding and machine translation, and intuitively segment language into meaningful units. We demonstrate Nugget outperforms related approaches in tasks involving semantic comparison. Finally, we illustrate these compact units allow for expanding the contextual window of a language model (LM), suggesting new future LMs that can condition on significantly larger amounts of content.

Objective: BCI (Brain-Computer Interface) technology operates in three modes: online, offline, and pseudo-online. In the online mode, real-time EEG data is constantly analyzed. In offline mode, the signal is acquired and processed afterwards. The pseudo-online mode processes collected data as if they were received in real-time. The main difference is that the offline mode often analyzes the whole data, while the online and pseudo-online modes only analyze data in short time windows. Offline analysis is usually done with asynchronous BCIs, which restricts analysis to predefined time windows. Asynchronous BCI, compatible with online and pseudo-online modes, allows flexible mental activity duration. Offline processing tends to be more accurate, while online analysis is better for therapeutic applications. Pseudo-online implementation approximates online processing without real-time constraints. Many BCI studies being offline introduce biases compared to real-life scenarios, impacting classification algorithm performance. Approach: The objective of this research paper is therefore to extend the current MOABB framework, operating in offline mode, so as to allow a comparison of different algorithms in a pseudo-online setting with the use of a technology based on overlapping sliding windows. To do this will require the introduction of a idle state event in the dataset that takes into account all different possibilities that are not task thinking. To validate the performance of the algorithms we will use the normalized Matthews Correlation Coefficient (nMCC) and the Information Transfer Rate (ITR). Main results: We analyzed the state-of-the-art algorithms of the last 15 years over several Motor Imagery (MI) datasets composed by several subjects, showing the differences between the two approaches from a statistical point of view. Significance: The ability to analyze the performance of different algorithms in offline and pseudo-online modes will allow the BCI community to obtain more accurate and comprehensive reports regarding the performance of classification algorithms.

We study a governed approach to enterprise analytics: a language model interprets the question, while deterministic policy selects and runs a pre-approved analytical program that returns both results and evidence. We show that this restriction can remain expressive within a defined analytical class, using relational operations plus aggregation, comparison, windows, ranking, and similarity. Fixed meaning, policy, data, and execution rules also make results replayable. Across 440 runs, three 8B models generated SQL and selected tools at runtime, while Qwen3-8B interpreted intent only and policy executed the approved program. None of 330 runtime-planning episodes matched the full answer-and-evidence contract across all test datasets; the policy-executed analyzer matched 110 of 110. This is a configuration-specific result, not evidence that runtime agents cannot succeed under other designs.

Data-driven modeling of fluid dynamics has advanced rapidly with neural PDE solvers, yet a fair and strong benchmark remains fragmented due to the absence of unified PDE datasets and standardized evaluation protocols. Although architectural innovations are abundant, fair assessment is further impeded by the lack of clear disentanglement between spatial, temporal and loss modules. In this paper, we introduce FD-Bench, the first fair, modular, comprehensive and reproducible benchmark for data-driven fluid simulation. FD-Bench systematically evaluates 85 baseline models across 10 representative flow scenarios under a unified experimental setup. It provides four key contributions: (1) a modular design enabling fair comparisons across spatial, temporal, and loss function modules; (2) the first systematic framework for direct comparison with traditional numerical solvers; (3) fine-grained generalization analysis across resolutions, initial conditions, and temporal windows; and (4) a user-friendly, extensible codebase to support future research. Through rigorous empirical studies, FD-Bench establishes the most comprehensive leaderboard to date, resolving long-standing issues in reproducibility and comparability, and laying a foundation for robust evaluation of future data-driven fluid models. The code is open-sourced at https://anonymous.4open.science/r/FD-Bench-15BC.

We introduce CompareBench, a benchmark for evaluating visual comparison reasoning in vision-language models (VLMs), a fundamental yet understudied skill. CompareBench consists of 1000 QA pairs across four tasks: quantity (600), temporal (100), geometric (200), and spatial (100). It is derived from two auxiliary datasets that we constructed: TallyBench (2000 counting images with QA) and HistCaps (515 historical images with bilingual captions). We evaluate both closed-source APIs (OpenAI, Gemini, Claude) and open-source models (Qwen2.5-VL and Qwen3-VL series). Results show clear scaling trends but also reveal critical limitations: even the strongest models consistently fail at temporal ordering and spatial relations, and they often make mistakes in basic counting and geometric comparisons that are trivial for humans. These findings demonstrate that visual comparison remains a systematic blind spot for current VLMs. By providing controlled, diverse, and diagnostic evaluation, CompareBench establishes a foundation for advancing more reliable multimodal reasoning.

Reference listening is a common strategy in music production, but current comparison tools often obscure a key human judgment: deciding what should be compared. We present Diptych, an AI-assisted system that lets users define comparison scope across whole tracks or independently selected segments, while inspecting structured audio features and scope-specific AI interpretations. We evaluated Diptych in a within-participants study with 12 musicians, complemented by source-blinded ratings from four expert listeners. Participants used the system to surface additional differences, nine of ten of which received at least partial expert support, and reported good usability and greater clarity about possible next steps. These findings suggest that AI support for creative comparison should prioritize user-defined scope, inspectable evidence, and actionable guidance, while avoiding authoritative judgments that exceed what the evidence can support.

Comparative settings (e.g. pairwise choice, listwise ranking) have been adopted by a wide range of subjective studies for image quality assessment (IQA), as it inherently standardizes the evaluation criteria across different observers and offer more clear-cut responses. In this work, we extend the edge of emerging large multi-modality models (LMMs) to further advance visual quality comparison into open-ended settings, that 1) can respond to open-range questions on quality comparison; 2) can provide detailed reasonings beyond direct answers. To this end, we propose the Co-Instruct. To train this first-of-its-kind open-source open-ended visual quality comparer, we collect the Co-Instruct-562K dataset, from two sources: (a) LMM-merged single image quality description, (b) GPT-4V "teacher" responses on unlabeled data. Furthermore, to better evaluate this setting, we propose the MICBench, the first benchmark on multi-image comparison for LMMs. We demonstrate that Co-Instruct not only achieves 30% higher superior accuracy than state-of-the-art open-source LMMs, but also outperforms GPT-4V (its teacher), on both existing related benchmarks and the proposed MICBench. Our model is published at https://huggingface.co/q-future/co-instruct.

Large language model (LLM) providers boast big numbers for maximum context window sizes. To test the real world use of context windows, we 1) define a concept of maximum effective context window, 2) formulate a testing method of a context window's effectiveness over various sizes and problem types, and 3) create a standardized way to compare model efficacy for increasingly larger context window sizes to find the point of failure. We collected hundreds of thousands of data points across several models and found significant differences between reported Maximum Context Window (MCW) size and Maximum Effective Context Window (MECW) size. Our findings show that the MECW is, not only, drastically different from the MCW but also shifts based on the problem type. A few top of the line models in our test group failed with as little as 100 tokens in context; most had severe degradation in accuracy by 1000 tokens in context. All models fell far short of their Maximum Context Window by as much as 99 percent. Our data reveals the Maximum Effective Context Window shifts based on the type of problem provided, offering clear and actionable insights into how to improve model accuracy and decrease model hallucination rates.

Null Hypothesis Significance Testing is the de facto tool for assessing effectiveness differences between Information Retrieval systems. Researchers use statistical tests to check whether those differences will generalise to online settings or are just due to the samples observed in the laboratory. Much work has been devoted to studying which test is the most reliable when comparing a pair of systems, but most of the IR real-world experiments involve more than two. In the multiple comparisons scenario, testing several systems simultaneously may inflate the errors committed by the tests. In this paper, we use a new approach to assess the reliability of multiple comparison procedures using simulated and real TREC data. Experiments show that Wilcoxon plus the Benjamini-Hochberg correction yields Type I error rates according to the significance level for typical sample sizes while being the best test in terms of statistical power.

Long-video language models cannot look at every frame: an hour sampled once per second is 3,600 images, and a system keeps only a small fixed slice of that pool. Which frames survive that slice is usually treated as a preprocessing detail; we test whether it should be. Published selectors make the comparison hard because they change the frame scorer, the prompt boundary, the resolution policy, and the answering model all at once. We hold each fixed and vary one decision at a time: selection, spatial compression, and reinvestment of the savings, across six training-free selection rules, three long-video benchmarks, and two answering models. Selection is the largest single lever: on LongVideoBench's hour-long bin, eight query-selected frames beat sixteen uniformly spaced ones by 6.9 points, and Orthogonal Matching Pursuit, an unmodified decades-old sparse-approximation algorithm, matches or comes within a point of every purpose-built selector we compare it against, across all three benchmarks. Compression is close to free: halving each frame's spatial budget at fixed timestamps costs at most 0.44 points. Reinvestment is where that budget turns back into accuracy: spending the freed tokens on twice as many compressed frames, at a measured cost no higher than the original eight, returns a further two to three points; compression only pays off once its savings are spent this way. Along the way, an implementation bug in our own AKS baseline and a 0.07 to 3.74 point gap between two harnesses running the same published rules at the same budget show why these comparisons need to happen inside one controlled harness rather than across papers.

We present BrowseComp, a simple yet challenging benchmark for measuring the ability for agents to browse the web. BrowseComp comprises 1,266 questions that require persistently navigating the internet in search of hard-to-find, entangled information. Despite the difficulty of the questions, BrowseComp is simple and easy-to-use, as predicted answers are short and easily verifiable against reference answers. BrowseComp for browsing agents can be seen as analogous to how programming competitions are an incomplete but useful benchmark for coding agents. While BrowseComp sidesteps challenges of a true user query distribution, like generating long answers or resolving ambiguity, it measures the important core capability of exercising persistence and creativity in finding information. BrowseComp can be found at https://github.com/openai/simple-evals.

Finding relevant literature underpins the practice of evidence-based medicine. From 2014 to 2016, TREC conducted a clinical decision support track, wherein participants were tasked with finding articles relevant to clinical questions posed by physicians. In total, 87 teams have participated over the past three years, generating 395 runs. During this period, each team has trialled a variety of methods. While there was significant overlap in the methods employed by different teams, the results were varied. Due to the diversity of the platforms used, the results arising from the different techniques are not directly comparable, reducing the ability to build on previous work. By using a stable platform, we have been able to compare different document and query processing techniques, allowing us to experiment with different search parameters. We have used our system to reproduce leading teams runs, and compare the results obtained. By benchmarking our indexing and search techniques, we can statistically test a variety of hypotheses, paving the way for further research.

This paper presents an eight-week observational comparison of 68 single-file HTML generations collected across 17 public experiments in the "HTML AI Battle" project between December 10, 2025 and February 4, 2026. Four reasoning model families, GPT, Gemini, Grok, and Claude, were compared under a fixed public-interface protocol with no custom instructions, no personality tuning, and no repair prompts. Each output was evaluated from a rendered browser video using human scores and a Gemini LLM-as-a-judge layer for prompt adherence, functional correctness, and UI quality, then packaged into a standardized social-media protocol spanning X (Twitter), TikTok, and YouTube. The tracker was also used for two supervised predictive analyses: an experiment-level model for 24-hour X impressions and a generation-level model for HTML verbosity. Under this protocol, Claude was the strongest and most consistent family, leading mean performance and winning 9/17 prompts under the primary human weighted score. Longer measured reasoning time was not associated with higher quality overall. Gemini as a judge was significantly more lenient than the human evaluator on functional correctness and overall performance, while stable self-favoring bias remained unresolved. The exploratory X-impressions model remained weak under post-screen cross-validation (MAE = 46,874, R^2 = -0.377), whereas the HTML-lines model performed better, with a model-family-only baseline outperforming prompt-aware alternatives (MAE = 135.2, R^2 = 0.576). Overall, selected pre-publication technical/audio variables were not sufficient to predict 24-hour X reach, while code verbosity was driven much more by model family than by prompt wording. The comparisons remain observational and are limited by public-interface drift, access-path differences, and one primary human scorer.

Language models hold latent quantities in a form they can report on, and more of a quantity is present in that form when the task requires reusing it flexibly. What causes a representation to enter that form is open, and the word workspace invites an admission story: a gate that decides what gets in. Testing it on open-weight models with Jacobian lenses, over a benchmark whose five arms share an identical context, we find no gate where it predicts one. Demand raises a concept's lens visibility beyond what applying an operator to a supplied value produces: +0.050 [+0.045, +0.057] in percentile rank on our primary checkpoint, positive on all four we measure, though that arm answers at ceiling and the accuracymatched contrast is stronger under that readout. At the same time one shared linear map decodes the variable from every arm, the control included, at 6.4-9.0x its selection-corrected floor. What produces the later readable form at the queried position is attention-mediated gathering inside a mid-depth window: separating patch depth from readout depth puts transport there at least 17x above anywhere shallower under non-saturating readouts, with no tested MLP output contributing positively inside it. Under the saturating percentile rank the same grid does not localise the window, which is a fact about that measure. An arm that needs the variable for nothing concentrates sevenfold less, so the window is demand-specific. That window has two measured edges, a survival failure below and destruction above, and it falls at the same fractional depth in a 64-layer hybrid and a 62-layer dense model from another family. We localise where the variable is installed and read, not the route from the passage, which transports nothing. But the readout is not a calibrated measure of use: three components move it to within 12% of one another and differ 7.4x in what they do to the answer.

Foundation-model features are increasingly used to ask what information neural activity represents, often by comparing prediction gains between nested encoding models. We show that such multimodal contrasts can change sign when only the conditioning predictor is reconstructed. Using fMRI from the Natural Scenes Dataset, DINOv2 visual features, and MPNet embeddings of MS COCO captions and Localized Narratives, a caption-narrative contrast in the additional predictive contribution of vision favors narratives when one short caption is compared with a long narrative (+0.012/+0.015 in Places), but favors captions after approximate word-count matching (-0.031/-0.023). The shift occurs across every measured ROI in both subjects and is driven primarily by differences in language-only prediction. Comparable contrasts also survive removal of image-specific content-word identity in several ROIs. These results show that nested neural contrasts do not identify represented content by themselves: predictor construction is part of the experimental design, and matched controls are required for representational claims.

Medical systematic reviews typically require assessing all the documents retrieved by a search. The reason is two-fold: the task aims for ``total recall''; and documents retrieved using Boolean search are an unordered set, and thus it is unclear how an assessor could examine only a subset. Screening prioritisation is the process of ranking the (unordered) set of retrieved documents, allowing assessors to begin the downstream processes of the systematic review creation earlier, leading to earlier completion of the review, or even avoiding screening documents ranked least relevant. Screening prioritisation requires highly effective ranking methods. Pre-trained language models are state-of-the-art on many IR tasks but have yet to be applied to systematic review screening prioritisation. In this paper, we apply several pre-trained language models to the systematic review document ranking task, both directly and fine-tuned. An empirical analysis compares how effective neural methods compare to traditional methods for this task. We also investigate different types of document representations for neural methods and their impact on ranking performance. Our results show that BERT-based rankers outperform the current state-of-the-art screening prioritisation methods. However, BERT rankers and existing methods can actually be complementary, and thus, further improvements may be achieved if used in conjunction.

Non-stationarity of an underlying data generating process that leads to distributional changes over time is a key characteristic of Data Streams. This phenomenon, commonly referred to as Concept Drift, has been intensively studied, and Concept Drift Detectors have been established as a class of methods for detecting such changes (drifts). For the most part, Drift Detectors compare regions (windows) of the data stream and detect drift if those windows are sufficiently dissimilar. In this work, we introduce the Window Dilemma, an observation that perceived drift is a product of windowing and not necessarily the underlying data generating process. Additionally, we highlight that drift detection is ill-posed, primarily because verification of drift events are implausible in practice. We demonstrate these contributions first by an illustrative example, followed by empirical comparisons of drift detectors against a variety of alternative adaptation strategies. Our main finding is that traditional batch learning techniques often perform better than their drift-aware counterparts further bringing into question the purpose of detectors in Stream Classification.

Automated research systems support literature synthesis, ideation, experiments, writing, and peer review, but their evaluation is dispersed across tasks, benchmarks, and studies that are difficult to compare directly. We review this literature from the perspective of evaluation design and evidence, covering six targets: literature synthesis, research ideation, executable workflows, scholarly writing and communication, automatic peer review, and end-to-end research. We compare task construction, evidence sources, evaluators, and scoring procedures to explain the capabilities assessed by different designs. Our synthesis highlights three recurring lessons: output checks, process checks, and human studies provide complementary information; evaluator calibration is specific to the property being assessed; and resource budgets and attempt selection are integral to interpreting performance comparisons. We identify diagnostic evaluation designs and documented gaps in supporting evidence, and translate these comparisons into reporting and audit recommendations for specific evaluation settings. The survey helps readers navigate existing evaluations, select appropriate benchmarks, and design subsequent studies.

Different types of user interfaces differ significantly in the number of elements and how they are displayed. To examine how such differences affect the way users look at UIs, we collected and analyzed a large eye-tracking-based dataset, UEyes (62 participants, 1,980 UI screenshots, near 20K eye movement sequences), covering four major UI types: webpage, desktop UI, mobile UI, and poster. Furthermore, we analyze and discuss the differences in important factors, such as color, location, and gaze direction across UI types, individual viewing strategies and potential future directions. This position paper is a derivative of our recent paper with a particular focus on the UEyes dataset.

Large language models (LLMs) are currently applied to scientific paper evaluation by assigning an absolute score to each paper independently. However, since score scales vary across conferences, time periods, and evaluation criteria, models trained on absolute scores are prone to fitting narrow, context-specific rules rather than developing robust scholarly judgment. To overcome this limitation, we propose shifting paper evaluation from isolated scoring to collaborative ranking. In particular, we design Comparison-Native framework for Paper Evaluation (CNPE), integrating comparison into both data construction and model learning. We first propose a graph-based similarity ranking algorithm to facilitate the sampling of more informative and discriminative paper pairs from a collection. We then enhance relative quality judgment through supervised fine-tuning and reinforcement learning with comparison-based rewards. At inference, the model performs pairwise comparisons over sampled paper pairs and aggregates these preference signals into a global relative quality ranking. Experimental results demonstrate that our framework achieves an average relative improvement of 21.8\% over the strong baseline DeepReview-14B, while exhibiting robust generalization to five previously unseen datasets. https://github.com/ECNU-Text-Computing/ComparisonReview{Code}.

Large language models (LLMs) show remarkable potential to act as computer agents, enhancing human productivity and software accessibility in multi-modal tasks that require planning and reasoning. However, measuring agent performance in realistic environments remains a challenge since: (i) most benchmarks are limited to specific modalities or domains (e.g. text-only, web navigation, Q&A, coding) and (ii) full benchmark evaluations are slow (on order of magnitude of days) given the multi-step sequential nature of tasks. To address these challenges, we introduce the Windows Agent Arena: a reproducible, general environment focusing exclusively on the Windows operating system (OS) where agents can operate freely within a real Windows OS and use the same wide range of applications, tools, and web browsers available to human users when solving tasks. We adapt the OSWorld framework (Xie et al., 2024) to create 150+ diverse Windows tasks across representative domains that require agent abilities in planning, screen understanding, and tool usage. Our benchmark is scalable and can be seamlessly parallelized in Azure for a full benchmark evaluation in as little as 20 minutes. To demonstrate Windows Agent Arena's capabilities, we also introduce a new multi-modal agent, Navi. Our agent achieves a success rate of 19.5% in the Windows domain, compared to 74.5% performance of an unassisted human. Navi also demonstrates strong performance on another popular web-based benchmark, Mind2Web. We offer extensive quantitative and qualitative analysis of Navi's performance, and provide insights into the opportunities for future research in agent development and data generation using Windows Agent Arena. Webpage: https://microsoft.github.io/WindowsAgentArena Code: https://github.com/microsoft/WindowsAgentArena

Humans' internal states play a key role in human-machine interaction, leading to the rise of human state estimation as a prominent field. Compared to swift state changes such as surprise and irritation, modeling gradual states like trust and satisfaction are further challenged by label sparsity: long time-series signals are usually associated with a single label, making it difficult to identify the critical span of state shifts. Windowing has been one widely-used technique to enable localized analysis of long time-series data. However, the performance of downstream models can be sensitive to the window size, and determining the optimal window size demands domain expertise and extensive search. To address this challenge, we propose a Selective Windowing Attention Network (SWAN), which employs window prompts and masked attention transformation to enable the selection of attended intervals with flexible lengths. We evaluate SWAN on the task of trust prediction on a new multimodal driving simulation dataset. Experiments show that SWAN significantly outperforms an existing empirical window selection baseline and neural network baselines including CNN-LSTM and Transformer. Furthermore, it shows robustness across a wide span of windowing ranges, compared to the traditional windowing approach.

Dataset summarisation is a fruitful approach to dataset inspection. However, when applied to a single dataset the discovery of visual concepts is restricted to those most prominent. We argue that a comparative approach can expand upon this paradigm to enable richer forms of dataset inspection that go beyond the most prominent concepts. To enable dataset comparison we present a module that learns concept-level prototypes across datasets. We leverage self-supervised learning to discover these prototypes without supervision, and we demonstrate the benefits of our approach in two case-studies. Our findings show that dataset comparison extends dataset inspection and we hope to encourage more works in this direction. Code and usage instructions available at https://github.com/Nanne/ProtoSim

We have compared three common visualisations for hierarchical quantitative data, treemaps, icicle plots and sunburst charts as well as a semicircular variant of sunburst charts we call the sundown chart. In a pilot study, we found that the sunburst chart was least preferred. In a controlled study with 12 participants, we compared treemaps, icicle plots and sundown charts. Treemap was the least preferred and had a slower performance on a basic navigation task and slower performance and accuracy in hierarchy understanding tasks. The icicle plot and sundown chart had similar performance with slight user preference for the icicle plot.

Prompt optimization methods either analyze individual failures in isolation or compare prompt variants across examples, operating on single execution traces with no access to the reasoning process distinguishing success from failure on the same input. We introduce ContraPrompt, built on the observation that when a model fails but succeeds on a retry with feedback, the difference between its two chain-of-thought traces constitutes an optimization signal not captured by prior methods. Unlike prior contrastive methods, we compare complete intermediate reasoning processes: the two traces share model, input, and base prompt, so remaining differences reflect reasoning strategy and appended error feedback -- we call this dyadic reasoning trace analysis. The multi-attempt solving phase is an instrumented agentic retry loop that generates contrastive data automatically without human annotation. Extracted rules are organized into an input-aware decision tree routing instructions by observable input characteristics. On four reasoning and compliance benchmarks, ContraPrompt outperforms GEPA (Agrawal et al., 2026) on all four, with absolute gains of +8.29 pp on HotPotQA (+20.8% rel.), +2.21 pp on GDPR-Bench (+18.2% rel.), +7.14 pp on GPQA Diamond (+10.6% rel.), and +0.74 pp on BBH (+0.85% rel.). Ablations confirm dyadic trace contrastivity is the critical component, with a -16% relative average drop upon its removal. On 53 EvalSet black-box optimization problems, ContraPrompt beats GEPA on 11, ties on 41, and loses on 1 at equal budget. On FiNER-139 financial named entity recognition (Loukas et al., 2022), ContraPrompt achieves +7.77 pp over the unoptimized baseline (+11.6% rel.) and +1.94 pp over GEPA (+2.66% rel.), with branch conditions aligning with standard US GAAP financial-instrument categories.

Reinforcement learning from verifiable rewards (e.g. GRPO) is the engine behind today's reasoning models, yet it grades only the final answer. On hard problems this trains models to write more rather than to think better, since the trace itself is never graded and no label for good thinking exists. We introduce Agon, which makes two competing models each other's graders. Both attempt the same problem; in alternating roles, one drafts a solution and the other reads it while solving, and each is rewarded for out-solving the other. To win, a model must out-reason a rival that has seen its work, so reasoning is judged implicitly during training, with no process labels and no reward model. Because both models are optimized, each faces a progressively stronger rival, which single-model RL cannot provide. The two need only be comparably strong and behaviorally different. At inference the pair deploys as it trains, a two-stage cascade in which one model drafts and the other answers after reading the draft. On the hard split of DeepMath with Qwen3, this doubles GRPO's pass@1, roughly eight times the gain of an untrained Mixture-of-Agents pass over the same base. The ordering replicates on competitive-programming code and across model families (Qwen3.5, Gemma 4). For now the models talk in text; the next step is to let them reason together in latent space.

In this paper, we propose a multi-modal search engine for interior design that combines visual and textual queries. The goal of our engine is to retrieve interior objects, e.g. furniture or wall clocks, that share visual and aesthetic similarities with the query. Our search engine allows the user to take a photo of a room and retrieve with a high recall a list of items identical or visually similar to those present in the photo. Additionally, it allows to return other items that aesthetically and stylistically fit well together. To achieve this goal, our system blends the results obtained using textual and visual modalities. Thanks to this blending strategy, we increase the average style similarity score of the retrieved items by 11%. Our work is implemented as a Web-based application and it is planned to be opened to the public.

Agent skills are often injected in full on every request, increasing token cost. We compare four content-preserving loading methods: Full, Skill Block, Reference, and Hybrid. Across SearchQA, SpreadsheetBench, ALFWorld, ScienceWorld, and SynthProc, we measure token usage using raw input for single-turn tasks and cache-correct effective input for multi-turn tasks. Results show no universal winner. Hybrid reduces input by 27.4% on SearchQA and 39.8% on SpreadsheetBench. On large multi-turn skills, Skill Block and Hybrid achieve substantial reductions, reaching 62.5% and 52.8% on ScienceWorld and 73.0% and 66.6% on SynthProc. ALFWorld shows smaller gains because procedures are short and repeatedly needed. Paired outcome tests detect no quality differences, though they do not establish equivalence. Overall, conditional loading is most beneficial when large portions of a skill are not needed on every turn.

Algorithmic fairness has conventionally adopted the mathematically convenient perspective of racial color-blindness (i.e., difference unaware treatment). However, we contend that in a range of important settings, group difference awareness matters. For example, differentiating between groups may be necessary in legal contexts (e.g., the U.S. compulsory draft applies to men but not women) and harm assessments (e.g., referring to girls as ``terrorists'' may be less harmful than referring to Muslim people as such). Thus, in contrast to most fairness work, we study fairness through the perspective of treating people differently -- when it is contextually appropriate to. We first introduce an important distinction between descriptive (fact-based), normative (value-based), and correlation (association-based) benchmarks. This distinction is significant because each category requires separate interpretation and mitigation tailored to its specific characteristics. Then, we present a benchmark suite composed of eight different scenarios for a total of 16k questions that enables us to assess difference awareness. Finally, we show results across ten models that demonstrate difference awareness is a distinct dimension to fairness where existing bias mitigation strategies may backfire.

An agent whose tool keeps returning nothing useful should stop relying on it. In a retrieval environment with controlled source failures, we separate how agents judge results from what they do. We compare stopping at the same step after longer and shorter runs of results the agent judged useless; this contrast is zero for clock- or deadline-driven stopping. Where we record their judgments, the seven agents we test call a failing source's results useless 97-100% of the time, yet most of them rarely stop on that judgment. Prompt cues change when they stop but not what they stop on. Permission to answer from memory and a reasoning mode can bring early stops regardless of evidence, a stated budget moves the 7-8B models' stops to the deadline, and a stopping rule or call cost in the prompt is followed at most partly. Stopping follows the evidence only when the harness enforces an integration step that makes the agent answer after five consecutive results it judged useless. This step raises failing-source success for every model, keeps the stopping point fixed when the budget doubles, and needs no extra judgment call when the agent states its judgments. A pre-registered replication on 300 fresh questions confirms the dissociation and the rule's effect.

Radiological similarity depends on disease relationships and on fine details such as laterality, lobe, severity, size, and certainty. Broad biomedical similarity can overlook these qualifiers, particularly when several attributes vary together. We introduce QureRadEmbed, a 4B radiology-aware encoder trained with two complementary signals: RadSim supplies deterministic, attribute-decomposed ranking targets, while RadThought aligns reports with hierarchical evidence and reasoning descriptions. A three-stage curriculum combines these signals with report triplets, finding perturbations, and single- and cross-attribute contrasts. The final model achieves 0.996 mean ordering accuracy across ten controlled synthetic attributes and raises Spearman correlation with the designed joint-attribute targets from 0.501 to 0.976. On external findings-to-impression retrieval, Recall@1 reaches 10.5% on Open-I, 12.4% on testing XR, and 42.9% on testing CT, compared with 6.6%, 5.7%, and 31.4% for its backbone. Frozen embeddings support finding extraction with only 100 labeled testing-XR reports (macro-F1 0.481 versus 0.412 for the backbone). Whole-report comparison costs 8.8 seconds per 1,000 pairs in our benchmark, versus 2,755.1 seconds for the generative evaluator GREEN. Sentence-level comparison improves sensitivity to local discrepancies, although generative evaluation remains stronger on several expert-rated and subtle-error tasks. The results support reusable radiology-aware representations for search, structured report indexing, and efficient report comparison.

A benchmark score compares a system output against a reference, and methodological attention falls almost entirely on the first term. We measure the second. The retained annotation record of a six-language benchmark for personally identifiable information contains two independent annotator labellings, the aggregate shipped as gold, and a reviewer gold from independent expert re-annotation of a sample. Using it, we hold the scored output fixed and exchange the reference. The score moves by 4.95 F1 points for one output and 2.00 for the other (95% CIs [3.23, 6.27] and [0.26, 3.37]), and by 7.55 in the worst language. The comparison between two outputs moves as well: the paired interaction between reference and system is +2.95 points (CI [+1.97, +3.87]), survives correction for multiple testing, and changes one language's margin outright. The cause is an undocumented aggregation default that usually kept one annotator when adjudication did not fire, making the shipped reference a partial copy of an output being scored. We report the resulting reference-sensitivity band, show how to compute one from any retained annotation record, and argue that the quantity belongs beside the score.

Logical reading comprehension is a challenging task that entails grasping the underlying semantics of text and applying reasoning to deduce the correct answer. Prior researches have primarily focused on enhancing logical reasoning capabilities through Chain-of-Thought (CoT) or data augmentation. However, previous work constructing chain-of-thought rationales concentrates solely on analyzing correct options, neglecting the incorrect alternatives. Addtionally, earlier efforts on data augmentation by altering contexts rely on rule-based methods, which result in generated contexts that lack diversity and coherence. To address these issues, we propose a Premise-Oriented Data Augmentation (PODA) framework. This framework can generate CoT rationales including analyses for both correct and incorrect options, while constructing diverse and high-quality counterfactual contexts from incorrect candidate options. We integrate summarizing premises and identifying premises for each option into rationales. Subsequently, we employ multi-step prompts with identified premises to construct counterfactual context. To facilitate the model's capabilities to better differentiate the reasoning process associated with each option, we introduce a novel thought-path contrastive learning method that compares reasoning paths between the original and counterfactual samples. Experimental results on three representative LLMs demonstrate that our method can improve the baselines substantially across two challenging logical reasoning benchmarks (ReClor and LogiQA 2.0). The data and code are released at https://github.com/lalalamdbf/TPReasoner.

Understanding visual differences between dynamic scenes requires the comparative perception of compositional, spatial, and temporal changes--a capability that remains underexplored in existing vision-language systems. While prior work on Image Difference Captioning (IDC) has enabled models to describe semantic changes between static images, these approaches fail to capture motion continuity, event evolution, or editing consistency over time. We introduce the ViDiC (Video Difference Captioning) task and its corresponding ViDiC-1K dataset, designed to evaluate the ability of Multimodal Large Language Models (MLLMs) to provide fine-grained descriptions of similarities and differences between video pairs. ViDiC-1K comprises 1,000 curated video pairs annotated with over 4,000 comparative checklist items, covering seven categories: subject, style, background, cinematography, motion, location, and playback techniques. To ensure reliable evaluation, we propose a dual-checklist framework that measures the accuracy of similarity and difference separately, based on the LLM-as-a-Judge protocol. Experiments on nineteen representative multimodal models reveal a significant performance gap in their comparative description and difference perception abilities. We hope ViDiC-1K can be a challenging benchmark that lays a solid foundation for advancing video understanding, edit awareness, and comparative reasoning in multimodal intelligence.

Opinion summarization focuses on generating summaries that reflect popular subjective information expressed in multiple online reviews. While generated summaries offer general and concise information about a particular hotel or product, the information may be insufficient to help the user compare multiple different choices. Thus, the user may still struggle with the question "Which one should I pick?" In this paper, we propose the comparative opinion summarization task, which aims at generating two contrastive summaries and one common summary from two different candidate sets of reviews. We develop a comparative summarization framework CoCoSum, which consists of two base summarization models that jointly generate contrastive and common summaries. Experimental results on a newly created benchmark CoCoTrip show that CoCoSum can produce higher-quality contrastive and common summaries than state-of-the-art opinion summarization models. The dataset and code are available at https://github.com/megagonlabs/cocosum

Using a large language model to play the user is now standard in scalable evaluation. It has a repeatedly diagnosed failure: the simulated user is excessively cooperative, so a system under test can score by the sheer number of questions it asks rather than by making the user willing to speak. We answer with a disclosure gate conditioning information release on the companion agent's behaviour: its state is a ladder of five ordered gates, merged onto three observable depth layers. We specify, ablate, and audit it, and train a user simulator against that specification. Gating behaviour is learned from the training corpus's synthetic branch, while the real branch supplies how people speak and react; after training, the simulator need not be told at runtime which gate each item sits behind. The gate is a load-bearing component of the environment: on the English corpus of a published companion-agent benchmark (CompanionBench), once training no longer states per example which gate each item sits behind, the largest rank displacement across 12 systems under test exceeds the noise band set by re-running that environment under a new seed, while per-system scores show no detectable change. We state two acceptance criteria: a ranking must be order-preserving, and absolute scores must be scale-stable. Of the candidates we examine, only one passes both -- the simulator we release -- and its leaderboard correlates at 0.993 with the benchmark's original simulator. By contrast, prompting a frontier model as the simulator barely moves the ranking while shifting every score upward -- a shift invisible to anyone checking the ranking alone. The environment we specify is the one that benchmark already used. That publication describes the mechanism in about four hundred words, and we supply what it lacked: specification, ablations, human studies, negative controls, and downstream sensitivity analysis.

We are born with the ability to learn concepts by comparing diverse observations. This helps us to understand the new world in a compositional manner and facilitates extrapolation, as objects naturally consist of multiple concepts. In this work, we argue that the cognitive mechanism of comparison, fundamental to human learning, is also vital for machines to recover true concepts underlying the data. This offers correctness guarantees for the field of concept learning, which, despite its impressive empirical successes, still lacks general theoretical support. Specifically, we aim to develop a theoretical framework for the identifiability of concepts with multiple classes of observations. We show that with sufficient diversity across classes, hidden concepts can be identified without assuming specific concept types, functional relations, or parametric generative models. Interestingly, even when conditions are not globally satisfied, we can still provide alternative guarantees for as many concepts as possible based on local comparisons, thereby extending the applicability of our theory to more flexible scenarios. Moreover, the hidden structure between classes and concepts can also be identified nonparametrically. We validate our theoretical results in both synthetic and real-world settings.

RED-2400 is a public benchmark of algorithmically-rejected trading events from a live Solana decentralized-exchange filter stack. I logged the data continuously between 2026-04-10 and 2026-05-02. The benchmark contains 6,659 rejection events linked to 169,122 post-rejection price and liquidity observations and 1,836 graveyard-tracker snapshots. Outcome labels follow the five-tier classification of Kamat (2026c): saved (windowed), saved (early-death), missed, flat, and unclassifiable. Thresholds use the trough-to-reference and peak-to-reference price ratios within a 24-hour window. Most filter-design datasets cover the accept side only. That gap leaves reject-side outcomes unmeasured and biases filter validation. RED-2400 lets researchers replicate filter-precision claims directly. RED-2400 is the first window in a planned dataset series; subsequent windows will extend the time horizon and enable regime-stratified analysis.

Computer-using agents drive real software through the screen -- clicking and typing -- but they solve every task from scratch: asked to repeat a task, an agent re-reads the screen, re-reasons every tap, and pays the full cost again. We present PreAct, which lets such an agent get faster on tasks it has done before. The first time it succeeds, PreAct compiles the run into a small state-machine program-states that check the screen, transitions that act-and on later runs replays it directly instead of invoking the agent 8.5-13x faster, with no per-step language-model calls. Replay is not blind: at each step PreAct checks that the screen matches what the program expects before acting, and hands control back to the agent the moment something is off. PreAct applies the same discipline when deciding what to keep: a freshly compiled program enters the store only if, re-run from a clean state, an independent evaluator confirms it solved the task-catching programs that replay to their last step yet leave the task undone. Across a mobile, a desktop, and a web benchmark, this store-time check separates repeated runs that improve from ones that degrade as faulty programs accumulate, worth 1.75-2.6 tasks per benchmark, the same direction on all three; a fallback that explores afresh when no program fits brings PreAct level with a strong record-and-replay baseline. We also report what did not matter: prompt wording, runtime guardrails, and whether a language model or a plain embedding retriever selects which program to reuse.

This paper measures hour-of-day effects, filter precision, fragility, and realised yield in a 15-day paper-traded deployment of an autonomous memecoin trading system on Solana decentralised exchanges. The 190-trade sample (March 29 to April 12, 2026) shows a 40.5 percent win rate, mean per-trade return of +0.62 percent, cumulative +117.7 percent (net SOL +0.039), skewness -1.21, excess kurtosis 6.61. A Mann-Whitney U test of three poorest-performing UTC hours (2, 13, 23) against the others yields U = 1,274, p = 0.22; directional but not significant at n = 190. The three hours were selected in-sample, so the comparison is exploratory, not confirmatory. A parallel counterfactual rejection-tracking system collected 4,874 forward-sample observations across 184 distinct rejection events. Of those events, 17.9 percent reached a 50 percent drawdown from reference within 24 hours; 26.0 percent of forward samples recorded the rejected token below half-reference. The filter stack avoided these realised drawdowns: evidence that the rejection criteria are net-positive against forward-market outcomes. Fragility is the principal caveat. Removing the top three trades (1.6 percent of sample) flips cumulative return unprofitable. Profitability rests on a small number of large winners and is structurally fragile. The dataset and audit script are deposited under CC-BY-4.0 (Zenodo DOI 10.5281/zenodo.20043302).

Evaluation budgets in agentic retrieval-augmented generation span questions, search trajectories, and repeated answers. We measure allocation precision, reading efficiency, and cost boundaries using a retrieval-feedback comparison on HotpotQA and MuSiQue. At 34.14--34.39M model tokens, broader question coverage lowers standard error by 33\% versus five reads and 12.6\% versus three trajectories. Archived nested and Q-only forecasts predict these allocations within 4.0\% and 3.5\%, respectively. Depth subsets establish no clear forecasting advantage beyond the two-trajectory audit. One-read variance penalties relative to the fitted optimum at the same token budget are 0--9.9\%, with substantial Pro uncertainty. Under recorded model fees, more questions beat more trajectories at search prices of \$0--1 per 1,000 requests; question-versus-read fee rankings remain unresolved. Temperature zero cuts answer disagreement from 14.3\% to 3.4\% while comparison precision stays similar. \par\medskip\noindentKeywords: Agentic RAG; Evaluation budget; Generalizability theory; Repeated sampling.

Neural Architecture Search (NAS) is an exciting new field which promises to be as much as a game-changer as Convolutional Neural Networks were in 2012. Despite many great works leading to substantial improvements on a variety of tasks, comparison between different methods is still very much an open issue. While most algorithms are tested on the same datasets, there is no shared experimental protocol followed by all. As such, and due to the under-use of ablation studies, there is a lack of clarity regarding why certain methods are more effective than others. Our first contribution is a benchmark of 8 NAS methods on 5 datasets. To overcome the hurdle of comparing methods with different search spaces, we propose using a method's relative improvement over the randomly sampled average architecture, which effectively removes advantages arising from expertly engineered search spaces or training protocols. Surprisingly, we find that many NAS techniques struggle to significantly beat the average architecture baseline. We perform further experiments with the commonly used DARTS search space in order to understand the contribution of each component in the NAS pipeline. These experiments highlight that: (i) the use of tricks in the evaluation protocol has a predominant impact on the reported performance of architectures; (ii) the cell-based search space has a very narrow accuracy range, such that the seed has a considerable impact on architecture rankings; (iii) the hand-designed macro-structure (cells) is more important than the searched micro-structure (operations); and (iv) the depth-gap is a real phenomenon, evidenced by the change in rankings between 8 and 20 cell architectures. To conclude, we suggest best practices, that we hope will prove useful for the community and help mitigate current NAS pitfalls. The code used is available at https://github.com/antoyang/NAS-Benchmark.

In medical imaging, the clinical value of Computed Tomography (CT) lies not only in depicting current disease status, but crucially in enabling longitudinal comparison of serial scans to determine disease evolution, a process that underpins response assessment, recurrence detection, and ongoing patient management. Yet, despite this central role of temporal comparison in clinical decision-making, existing medical foundation models remain largely confined to single-study understanding, leaving temporally grounded cross-examination insufficiently addressed. To address this gap, we study longitudinal imaging difference reporting, a task in which a model takes two temporally separated scans from the same patient and generates a clinically meaningful report describing interval changes between them. We introduce CT-ΔBench, a dedicated benchmark for this task with patient-level splitting to prevent information leakage. To better evaluate this task beyond surface-level text similarity, we further develop change-aware metrics specifically designed to capture clinically meaningful longitudinal changes, and conduct an independent physician validation to assess the reliability of the synthesized references and event extraction pipeline. We also compare direct paired-CT reasoning with an indirect two-stage pipeline that first generates single-timepoint reports and then performs textual differencing. Finally, we propose DeltaMed, a baseline model for direct paired-CT difference reporting, and train it on the benchmark training set. Together, these contributions lay the groundwork for temporally aware medical foundation models that better reflect real-world longitudinal clinical reasoning.

Continuous evaluation of LLM products relies on a strong LLM judge treated as ground truth: a cheap monitor scores every interaction and a team is paged when the score drifts down. But the judge is itself a model behind an API, and a silent version bump or scoring-prompt update changes how it scores -- so every drift alarm is ambiguous between a worse product and a changed judge. We resolve the ambiguity with a fixed, human-labeled anchor set that the current judge re-scores at a steady interleave, a second betting e-process on the judge-versus-human gap, and a guard-window rule returning a verdict in {none, system, judge}. We prove anytime-validity, one-way identification (only the judge can move the anchors), an attribution race whose design law is that the anchors must out-run the main process they guard, and process orthogonality. On two real judge changes, a silent version bump is detected as judge drift in 60/60 runs with zero judge-to-system misattribution, and a contaminating strict-prompt change is correctly attributed on 110 of 120 runs at guard width 300 -- while the industry-default rolling z-test false-alarms on 75% of drift-free streams. Every experiment replicates on a second domain (TL;DR summarization) with nothing re-tuned, and where the domains differ the differences are the ones the race predicts: the strict-prompt change shifts scores harder there, so the anchors fire faster and attribution becomes perfect (240/240). The monitor runs at approximately 0.64 of the cost of strong-judging every item, or 0.21 in a cheaper-but-deafer regime.

A manga reader meets a character on one page and knows them on sight a hundred pages later, without ever being handed a cast list. Re-identifying comic characters demands the same, open-set and sequential: pages arrive as a stream in reading order, new faces appear before anyone names them, and the cast is assembled as the story is read. Re:Cognize evaluates recognition as the story is read, not against a cast handed over in advance: four protocols on one query stream, from closed-set retrieval to a cast the model must build and grow itself. The surprise is where models fail. Recognising is close to solved: one reference image per character already ranks as well as a gallery built in advance. Knowing what to believe is not: a model that adds its own matches makes its cast worse, while the same growth with correct labels would gain over twenty points of top-1 accuracy. The bottleneck is acceptance, not vision, and one comparison decides it: an addition pays exactly when it is right more often than the cast already was on the queries it takes over. The comparison has nothing to fit, and measured on half of a new corpus it calls the other half correctly. ReCast puts it to work with nothing fitted on data: a cast sheet of one running average per character, grown only where the page itself vouches for a crop. It recovers a third to two thirds of what perfect labels would, depending on whether the cast starts from random examples or from first appearances. Re:Cognize measures whether a model can read along; ReCast is a cast that does. Our claims are on identity maintenance, recognising characters already met; the emergence of new ones is measured as a diagnostic under a fixed reference rule, and we propose no method for it.

The paper presents analysis of time evolution within am Internet political forum, characterized by large political differences and high levels of emotions. The study compares samples of discussions gathered at three periods separated by important events. We focus on statistical aspects related to emotional content of communication and changes brought by technologies that increase or decrease the direct one-to-one discussions. We discuss implications of user interface aspects on promoting communication across a political divide.

Prior work on a social web highlighter located individuality in selection -- which documents a person chooses to highlight -- but measured it cross-sectionally. We ask the temporal question: is a reader's selection signature a trait or a state? We freeze each reader's first six months of highlighting as a profile and track its own-vs-other advantage on their later selections at growing gaps (to 24+ months), with negatives drawn from the same calendar era -- so supply drift cannot masquerade as personal drift -- at a coarse global level and at a fine level whose negatives and controls come from the reader's own interest neighborhood; the anchor cell reproduces the prior cross-sectional level (+0.188 vs +0.169), validating the harness. Four results. Within the same users, the fine-layer advantage shows no statistically detectable paired decline at any horizon (6-12 month retention R = 1.00 [0.85, 1.18], n = 212; the farthest bin is compatible with a modest decline; the only contrast whose interval excludes zero is the coarse layer at 12-24 months, about 13%). The signal is not reducible to repeated domains (~90% survives excluding all profile sources). Within-person drift is slow (a recent-half profile beats the old half by +0.042). Prospectively, personal profiles -- even one built from a reader's earliest documents, median 20 months before evaluation -- rank their next reads at roughly 3x the AP of every simple non-personal prior tested. We use "trait" operationally (a stable signature under continued engagement); the scope is heavy, long-tenured readers of one platform, and exposure is not separable from choice.

Many peer-review venues are using algorithms to assign submissions to reviewers. The crux of such automated approaches is the notion of the "similarity score" -- a numerical estimate of the expertise of a reviewer in reviewing a paper -- and many algorithms have been proposed to compute these scores. However, these algorithms have not been subjected to a principled comparison, making it difficult for stakeholders to choose the algorithm in an evidence-based manner. The key challenge in comparing existing algorithms and developing better algorithms is the lack of publicly available gold-standard data. We address this challenge by collecting a novel dataset of similarity scores that we release to the research community. Our dataset consists of 477 self-reported expertise scores provided by 58 researchers who evaluated their expertise in reviewing papers they have read previously. Using our dataset, we compare several widely used similarity algorithms and offer key insights. First, all algorithms exhibit significant error, with misranking rates between 12%-30% in easier cases and 36%-43% in harder ones. Second, most specialized algorithms are designed to work with titles and abstracts of papers, and in this regime the SPECTER2 algorithm performs best. Interestingly, classical TF-IDF matches SPECTER2 in accuracy when given access to full submission texts. In contrast, off-the-shelf LLMs lag behind specialized approaches.

Natural-language instance navigation becomes challenging when the initial user request does not uniquely specify the target instance. A practical agent should reduce the user's burden by actively asking only the information needed to distinguish the target from similar distractors, rather than requiring a detailed description upfront. Existing approaches often fall short of this goal: they may stop at the first plausible candidate before sufficiently exploring alternatives, or, even after collecting multiple candidates, ask about the target's attributes derived from individual candidates rather than questions selected to distinguish candidates in the pool. As a result, despite the dialogue, the agent may still fail to distinguish the target from distractors, leading to premature decisions and lengthy user responses. We propose Proactive Instance Navigation with Comparative Judgment (ProCompNav), a two-stage framework that first constructs a candidate pool and then identifies the target through comparative judgment. At each round, ProCompNav extracts an attribute-value pair that splits the current pool, asks a binary yes/no question, and prunes all inconsistent candidates at once. This reframes disambiguation from open-ended target description to pool-level discriminative questioning, where each question is chosen to narrow the candidate set. On CoIN-Bench, ProCompNav improves Success Rate over interactive baselines with the same minimal input and non-interactive baselines with detailed descriptions, while substantially reducing Response Length. ProCompNav also achieves state-of-the-art Success Rate on TextNav, suggesting that comparative judgment is broadly useful for instance-level navigation among similar distractors. Code is available at https://github.com/tree-jhk/procompnav.

Conversational memory changes during use, so endpoint question answering alone cannot establish how a persistent state accumulates, ages, or incorporates revisions. We introduce LSREP, a Longitudinal State-Replay Evaluation Protocol combining ordered replay, explicit lifecycle schedules, repeated probes, evolving reference answers, and mechanism-fidelity checks. Its architectural case study is ICE v2, a local-first memory middleware with typed stores, retrieval fusion, and dynamic context budgets. The private, single-user instantiation contains 1,985 turns, 219 distinct probes, and 1,211 probe-checkpoint observations across 52 checkpoints. On three ordinary-density datasets, ICE v2 has a near-zero mean quality difference from vector-RAG while selecting 32% fewer fragments but using 6.6% more estimated prompt tokens. A fourth, dense dataset exposes catastrophic failures of the unbudgeted baseline. The fidelity audit limits attribution: procedural retrieval is defective, several mechanisms are unexercised, and graph utility is not established. In a complementary matched public diagnostic, ICE v2 loses decisively to pure vector-RAG on LongMemEval: 50.8% versus 72.8% in the evidence-only oracle and 43.0% versus 69.5% in full-S. Paired differences are -22.0 points (95% CI [-26.6, -17.4]) and -26.5 ([-31.3, -21.8]). Conservative abstention accompanies severe multi-session and temporal failures. ICE uses less context in this diagnostic, establishing a quality-cost trade-off rather than superior efficiency. Together, replay, fidelity auditing, and public endpoint testing expose distinct failure modes that neither architectural descriptions nor aggregate scores identify alone.

Existing benchmarks for multimodal agentic search evaluate multimodal search and visual browsing, but visual evidence is either confined to the input or treated as an answer endpoint rather than part of an interleaved search trajectory. We introduce InterLV-Search, a benchmark for Interleaved Language-Vision Agentic Search, in which textual and visual evidence is repeatedly used to condition later search. It contains 2,061 examples across three levels: active visual evidence seeking, controlled offline interleaved multimodal search, and open-web interleaved multimodal search. Beyond existing benchmarks, it also includes multimodal multi-branch samples that involve comparison between multiple entities during the evidence search. We construct Level 1 and Level 2 with automated pipelines and Level 3 with a machine-led, human-supervised open-web pipeline. We further provide InterLV-Agent for standardized tool use, trajectory logging, and evaluation. Experiments on proprietary and open-source multimodal agents show that current systems remain far from solving interleaved multimodal search, with the best model below 50% overall accuracy, highlighting challenges in visual evidence seeking, search control, and multimodal evidence integration. We release the benchmark data and evaluation code at https://github.com/hbhalpha/InterLV-Search-Bench

Graphical User Interface (GUI) tasks are vital for automating workflows such as software testing, user interface navigation. For users, the GUI is the most intuitive platform for interacting with a computer. Previous work identified a key challenge in developing visual GUI agents: GUI grounding - the ability to accurately locate screen elements based on instructions. However, most existing GUI agents rely on structured data formats like DOM or HTML files in training or inferencing, which are inaccessible across all applications, particular in a general desktop environments such as Windows OS. To address this, we introduce WinClick, a novel visual GUI agent developed in Windows platform. WinClick leverages screenshots to detect actionable regions. To overcome the challenge of GUI grounding, we enhance WinClick with GUI grounding pre-training and propose an LLM-based method for aligning GUI grounding data. Additionally, we introduce WinSpot, the first comprehensive benchmark for GUI grounding on Windows. Our experiments demonstrate that WinClick, combined with GUI grounding pre-training, significantly outperforms existing baselines, offering a scalable solution for GUI automation in desktop environments. WinSpot is publicly available at https://github.com/zackhuiiiii/WinSpot.

Ask a language model the same question about the same document twenty times, and it sometimes returns two different answers. We built Probity, a benchmark of 60 tasks and 470 items from real venture-financing filings, to measure how often this happens. Then we audited our own corpus and found a defect any excerpt-built benchmark can carry: items whose evidence is missing from the window of text the model is shown. The audit flags 36 items and separates two failures a single flag would conflate: evidence genuinely absent from the window and answers that must be computed from numbers the window does supply. Flagged items change their answers far more often, wobbling at 0.255 against 0.087 on the 427 clean items, and excluding them cuts apparent cross-model agreement by about a fifth. Before testing whether the missing evidence explains the instability, we registered a prediction: re-cut each window to hold its evidence, and instability should fall below a set threshold. It failed: the repair moved wobble by 0.058, with an interval containing zero. We report the association as correlational. Almost all measurements sit where instability cannot show, which bounds what a corpus built for accuracy can say about stability. We release the corpus, all 112,800 raw responses, and the audit as a runnable check for any document benchmark.

We propose several small modifications to Duet---a deep neural ranking model---and evaluate the updated model on the MS MARCO passage ranking task. We report significant improvements from the proposed changes based on an ablation study.

We study the ranking of individuals, teams, or objects, based on pairwise comparisons between them, using the Bradley-Terry model. Estimates of rankings within this model are commonly made using a simple iterative algorithm first introduced by Zermelo almost a century ago. Here we describe an alternative and similarly simple iteration that provably returns identical results but does so much faster -- over a hundred times faster in some cases. We demonstrate this algorithm with applications to a range of example data sets and derive a number of results regarding its convergence.

Today, comprehensive evaluation of large-scale machine learning models is possible thanks to the open datasets produced using crowdsourcing, such as SQuAD, MS COCO, ImageNet, SuperGLUE, etc. These datasets capture objective responses, assuming the single correct answer, which does not allow to capture the subjective human perception. In turn, pairwise comparison tasks, in which one has to choose between only two options, allow taking peoples' preferences into account for very challenging artificial intelligence tasks, such as information retrieval and recommender system evaluation. Unfortunately, the available datasets are either small or proprietary, slowing down progress in gathering better feedback from human users. In this paper, we present IMDB-WIKI-SbS, a new large-scale dataset for evaluating pairwise comparisons. It contains 9,150 images appearing in 250,249 pairs annotated on a crowdsourcing platform. Our dataset has balanced distributions of age and gender using the well-known IMDB-WIKI dataset as ground truth. We describe how our dataset is built and then compare several baseline methods, indicating its suitability for model evaluation.

The rapid development of LLMs has sparked extensive research into their factual knowledge. Current works find that LLMs fall short on questions around low-frequency entities. However, such proofs are unreliable since the questions can differ not only in entity frequency but also in difficulty themselves. So we introduce ComparisonQA benchmark, containing 283K abstract questions, each instantiated by a pair of high-frequency and low-frequency entities. It ensures a controllable comparison to study the role of knowledge frequency in the performance of LLMs. Because the difference between such a pair is only the entity with different frequencies. In addition, we use both correctness and uncertainty to develop a two-round method to evaluate LLMs' knowledge robustness. It aims to avoid possible semantic shortcuts which is a serious problem of current QA study. Experiments reveal that LLMs, including GPT-4o, exhibit particularly low robustness regarding low-frequency knowledge. Besides, we find that uncertainty can be used to effectively identify high-quality and shortcut-free questions while maintaining the data size. Based on this, we propose an automatic method to select such questions to form a subset called ComparisonQA-Hard, containing only hard low-frequency questions.

Wu et al. (2026) showed that most frontier large language models (LLMs) recommend a sponsored, roughly twice-as-expensive flight when their system prompt contains a soft sponsorship cue. We reproduce their evaluation on ten open-weight chat models plus the two of their twenty-three models that are still reachable today (gpt-3.5-turbo, gpt-4o). All reported rates in this paper are produced under the same judge the original paper used (gpt-4o); we additionally store every label under an open-weight (gpt-oss-120b) and a smaller proprietary (gpt-4o-mini) judge for an ablation. Three findings emerge. First, a prose description of an LLM evaluation pipeline is not, on its own, sufficient for accurate reproduction: we surfaced three silent implementation failures that each shifted a reported rate by tens of percentage points. Second, the central claims do generalise - the gpt-3.5-turbo logistic-regression intercept of alpha = 0.81 is within four points of the original alpha = 0.86, and 200 of 200 trials on gpt-3.5-turbo and gpt-4o promote a payday lender to a financially distressed user. Third, a thirty-token user prompt that asks the assistant for a neutral comparison table first cuts sponsored recommendation from 46.9% to 1.0% averaged across our ten open-source models, and from 53.0% to 0% averaged across the two OpenAI models. AI literacy and price-comparison portals are likely market-level mitigations; the harmful-product cell is bounded by neither. Raw data, labels and analysis scripts are at https://github.com/akmaier/Paper-LLM-Ads .

The event selection developed for the Fermi Large Area Telescope before launch has been periodically updated to reflect the constantly improving knowledge of the detector and the environment in which it operates. Pass 7, released to the public in August 2011, represents the most recent major iteration of this incremental process. In parallel, the LAT team has undertaken a coherent long-term effort aimed at a radical revision of the entire event-level analysis, based on the experience gained in the prime phase of the mission. This includes virtually every aspect of the data reduction process, from the simulation of the detector to the event reconstruction and the background rejection. The potential improvements include (but are not limited to) a significant reduction in background contamination coupled with an increased effective area, a better point-spread function, a better understanding of the systematic uncertainties and an extension of the energy reach for the photon analysis below 100 MeV and above a few hundred GeV. We present an overview of the work that has been done or is ongoing and the prospects for the near future.

Tracking links observations of the same object through visual change, yet cannot by itself determine when the object is empty or filled, intact or cut. We formulate identity-conditioned state-moment retrieval: given a tracked-object history and alternative state descriptions, localize an interval in which each described state holds. Absolute image-text similarity scores descriptions independently; because every visible frame depicts the same target, shared object compatibility can obscure the state evidence needed to identify the target interval. The alternatives provide the missing reference: evidence for one state should be measured against the others. We introduce Déjà Cue, a training-free framework that turns these alternatives into a vocabulary-relative coordinate system. It subtracts their state-balanced centroid from each description, calibrates frame scores, and scans multiple durations within contiguous visible runs using a frozen encoder. On 78 VOST histories, holding the temporal scan fixed and changing only the query reference nearly doubles R@1 at tIoU 0.5 from 10.3\% to 20.5\% and raises Top-1 tIoU from 16.0\% to 21.5\%. Candidate-rank analyses show that vocabulary-relative queries rank useful intervals higher within the same candidate set. Related state descriptions can therefore serve as an object-specific, query-time coordinate system for reading frozen visual representations.

Automated summary quality assessment falls into two categories: reference-based and reference-free. Reference-based metrics, historically deemed more accurate due to the additional information provided by human-written references, are limited by their reliance on human input. In this paper, we hypothesize that the comparison methodologies used by some reference-based metrics to evaluate a system summary against its corresponding reference can be effectively adapted to assess it against its source document, thereby transforming these metrics into reference-free ones. Experimental results support this hypothesis. After being repurposed reference-freely, the zero-shot BERTScore using the pretrained DeBERTa-large-MNLI model of <0.5B parameters consistently outperforms its original reference-based version across various aspects on the SummEval and Newsroom datasets. It also excels in comparison to most existing reference-free metrics and closely competes with zero-shot summary evaluators based on GPT-3.5.

Open rerankers trained for general web retrieval transfer imperfectly to e-commerce, where ranking decisions depend not only on topical relevance but also on user preferences, product constraints, and comparative product fit. These preference signals are difficult to supervise at scale: real search traffic provides authentic queries and candidates but no clean pairwise labels. We present ZooWork-ShopRanker, a family of e-commerce rerankers (0.6B, 4B, and 8B) aligned to judge-labeled shopping preference. Training pairs are labeled by a panel of reasoning large language models (LLMs) from different families acting as a preference oracle, with position-debiased judgments and agreement tiers, and the rerankers are trained on these labels. The aligned 8B flagship then serves as a distillation teacher for the efficient 4B and 0.6B models, which are fit to its scores and sharpened on judged pairs. To measure progress, we introduce ShopRank-Bench, a contamination-limited benchmark of ~10,000 private-traffic preference pairs in both text formats, tiered by how many judge families committed to each label. ZooWork-ShopRanker-8B and -4B significantly outperform the strongest open reranker baseline, every model significantly beats its own un-aligned base, and ZooWork-ShopRanker-0.6B beats its size peer; the gains hold in both formats and extend to common MTEB benchmarks. We release the models and the dual-format ShopRank-Bench to facilitate further research.

Adaptive computation aims to improve language-model inference by tailoring execution to each input. For layer programs, oracle evaluations use known answers to estimate the potential gain from this flexibility, before a practical selector is available. However, a gain from selection does not by itself explain why the chosen programs help. This study examines this distinction using 32 layer-skipping and repetition programs on two models and 4,413 multiple-choice items. The analysis compares their gains over a fixed action selected without the evaluation prompt with those of input-blind perturbations at the same sites, re-evaluating selections on another prompt. With shared option order, the controls give 10.2-11.8 and 15.6-19.4 percentage points of headroom on Qwen3-4B-Base and Llama-3.1-8B, exceeding the real programs' 9.0 and 10.1 in all three random-direction draws per model. They match answer-change rate only, and the ordering depends on the menu: in post hoc comparisons, real programs lead on Llama's repeat-only menu in every draw. A smaller KL-calibrated comparison, including an input-dependent control, favours real programs in point estimate, with inconclusive corrected tests. Fixed letter offsets produce headroom of similar scale. Rotating options sharply reduces both families' headroom, while leaving positive real-minus-control differences of 1.4-2.3 and 3.7-4.5 points; their magnitudes and statistical support depend on further adjustments and the reference. A supplementary generated-answer test finds that search-selected programs keep a 26.0-point advantage over programs selected for other problems after rewording, without a placebo comparison. These results show that substantial headroom can persist across prompts with shared option order without establishing a benefit specific to the selected layer computation; neither ordering against these controls identifies that benefit.

As LLM agents decide on users' behalf which product to buy, which hotel to book, or which paper to cite, a preference for items from certain sources (the sites or services they come from) shapes what users receive and which sources are selected. We study source preference in end-to-end search with 12 agent models across three domains. Comparing items from different sources that satisfy the same requirements at the same position, we find that each model prefers some sources and avoids others in every domain, largely agreeing on which. This preference can outweigh how well items satisfy the request: an item satisfying one requirement fewer is selected about two-thirds of the time when it comes from a preferred source and the better one from a dispreferred source, but almost never in the reverse case. The information identifying an item's source affects selection by itself: hiding it weakens the preference, and relabeling an item with a preferred source raises its selection rate. We test two routes to this preference: training that rewards better items can make a source a shortcut for requirement satisfaction, and missing information can trigger preconceptions about the source. Supplying missing information or a prompt countering these preconceptions reduces source preference.

While GUI agents have shown impressive capabilities in common computer-use tasks such as OSWorld, current benchmarks mainly focus on isolated and single-application tasks. This overlooks a critical real-world requirement of coordinating across multiple applications to accomplish complex profession-specific workflows. To bridge this gap, we present a computer-use benchmark in cross-application workflows, named WindowsWorld, designed to systematically assess GUI Agents on complex multi-step tasks that mirror real-world professional activities. Our methodology uses a multi-agent framework steered by 16 occupations to generate four difficulty-level tasks with intermediate inspection, which are then refined by human review and executed in a simulated environment. The resulting benchmark contains 181 tasks with an average of 5.0 sub-goals across 17 common desktop applications, of which 78% are inherently multi-application. Experimental results of leading large models and agents show that: 1) All computer-use agents perform poorly on multi-application tasks (< 21% success rate), far below the performance of simple single-app tasks; 2) They largely fail at tasks requiring conditional judgment and reasoning across geq 3 applications, stalling at early sub-goals; 3) Low execution efficiency, where tasks often fail despite far exceeding human step limits. Code, benchmark data, and evaluation resources are available at github.com/HITsz-TMG/WindowsWorld.

This study evaluates the performance of OpenAI's o1-preview model in higher-order cognitive domains, including critical thinking, systematic thinking, computational thinking, data literacy, creative thinking, logical reasoning, and scientific reasoning. Using established benchmarks, we compared the o1-preview models's performance to human participants from diverse educational levels. o1-preview achieved a mean score of 24.33 on the Ennis-Weir Critical Thinking Essay Test (EWCTET), surpassing undergraduate (13.8) and postgraduate (18.39) participants (z = 1.60 and 0.90, respectively). In systematic thinking, it scored 46.1, SD = 4.12 on the Lake Urmia Vignette, significantly outperforming the human mean (20.08, SD = 8.13, z = 3.20). For data literacy, o1-preview scored 8.60, SD = 0.70 on Merk et al.'s "Use Data" dimension, compared to the human post-test mean of 4.17, SD = 2.02 (z = 2.19). On creative thinking tasks, the model achieved originality scores of 2.98, SD = 0.73, higher than the human mean of 1.74 (z = 0.71). In logical reasoning (LogiQA), it outperformed humans with average 90%, SD = 10% accuracy versus 86%, SD = 6.5% (z = 0.62). For scientific reasoning, it achieved near-perfect performance (mean = 0.99, SD = 0.12) on the TOSLS,, exceeding the highest human scores of 0.85, SD = 0.13 (z = 1.78). While o1-preview excelled in structured tasks, it showed limitations in problem-solving and adaptive reasoning. These results demonstrate the potential of AI to complement education in structured assessments but highlight the need for ethical oversight and refinement for broader applications.

We present VISTA (VIsual Spec-To-App Benchmark), a benchmark for evaluating the end-to-end web-app generation capabilities of LLM-based agents. Unlike prior code generation benchmarks that focus on algorithmic tasks, VISTA targets realistic UI-centric development, where agents must produce functional, visually coherent applications from underspecified inputs. We define five prompt-information conditions that vary along two axes, visual/structural fidelity and stack constraint: (1) text only with free stack choice, (2) text with reference screenshots under three specified stacks, (3) text with reference screenshots under free stack choice, (4) text with screenshots and pruned Figma structure under a single specified stack, and (5) text with screenshots and pruned Figma structure under free stack choice. To enable robust evaluation, each page in the benchmark is manually annotated with interactive UI components and around three visual anchor points, addressing the well-known limitations of script-based testing tools such as Playwright in open-ended code generation settings. Evaluation combines DOM-grounded reference matching, behavior-specific browser tests, and CLIP-based visual similarity, jointly measuring structural alignment, behavioral completeness, and overall visual fidelity. We use VISTA to assess four agent systems drawn from two model families and two harnesses, finding that visual fidelity and functional correctness are partially decoupled across both input conditions and agents, and that agent editing style varies sharply but is largely orthogonal to task quality. VISTA establishes a rigorous and reproducible foundation for advancing agent-based software engineering research. Code is available at https://github.com/kaboider/VISTA_Bench.

Pairwise re-ranking models predict which of two documents is more relevant to a query and then aggregate a final ranking from such preferences. This is often more effective than pointwise re-ranking models that directly predict a relevance value for each document. However, the high inference overhead of pairwise models limits their practical application: usually, for a set of k documents to be re-ranked, preferences for all k^2-k comparison pairs excluding self-comparisons are aggregated. We investigate whether the efficiency of pairwise re-ranking can be improved by sampling from all pairs. In an exploratory study, we evaluate three sampling methods and five preference aggregation methods. The best combination allows for an order of magnitude fewer comparisons at an acceptable loss of retrieval effectiveness, while competitive effectiveness is already achieved with about one third of the comparisons.

The Unix terminal, or just simply, the terminal, can be found being applied in almost every facet of computing. It is available across all major platforms and often integrated into other applications. Due to its ubiquity, even marginal improvements to the terminal have the potential to make massive improvements to productivity on a global scale. We believe that evolutionary improvements to the terminal, in its current incarnation as windowed terminal emulator, are possible and that developing a thorough understanding of issues that current terminal users face is fundamental to knowing how the terminal should evolve. In order to develop that understanding we have mined Unix and Linux Stack Exchange using a fully-reproducible method which was able to extract and categorize 91.0% of 1,489 terminal-related questions (from the full set of nearly 240,000 questions) without manual intervention. We present an analysis, to our knowledge the first of its kind, of windowed terminal-related questions posted over a 15-year period and viewed, in aggregate, approximately 40 million times. As expected, given its longevity, we find the terminal's many features being applied across a wide variety of use cases. We find evidence that the terminal, as windowed terminal emulator, has neither fully adapted to its now current graphical environment nor completely untangled itself from features more suited to incarnations in previous environments. We also find evidence of areas where we believe the terminal could be extended along with other areas where it could be simplified. Surprisingly, while many current efforts to improve the terminal include improving the terminal's social and collaborative aspects, we find little evidence of this as a prominent pain point.

In the last decade, several organizations have produced documents intended to standardize, in the normative sense, and promote guidance to our recent and rapid AI development. However, the full spectrum of ideas presented in these documents has not yet been analyzed, except for a few meta-analyses and critical reviews of the field. In this work, we seek to expand on the work done by past researchers and create a tool for better data visualization of the contents and nature of these documents, to understand whether there is consensus or similarity between the principles espoused by various institutions, which may inspire debates on future regulations. We also provide some preliminary thoughts and questions that could guide the continuity of the research through a critical analysis of the results acquired by our methodology into a sample size of 200 documents.

To enable building and testing models on long-document comprehension, we introduce QuALITY, a multiple-choice QA dataset with context passages in English that have an average length of about 5,000 tokens, much longer than typical current models can process. Unlike in prior work with passages, our questions are written and validated by contributors who have read the entire passage, rather than relying on summaries or excerpts. In addition, only half of the questions are answerable by annotators working under tight time constraints, indicating that skimming and simple search are not enough to consistently perform well. Our baseline models perform poorly on this task (55.4%) and significantly lag behind human performance (93.5%).

Boolean query construction is often critical for medical systematic review literature search. To create an effective Boolean query, systematic review researchers typically spend weeks coming up with effective query terms and combinations. One challenge to creating an effective systematic review Boolean query is the selection of effective MeSH Terms to include in the query. In our previous work, we created neural MeSH term suggestion methods and compared them to state-of-the-art MeSH term suggestion methods. We found neural MeSH term suggestion methods to be highly effective. In this demonstration, we build upon our previous work by creating (1) a Web-based MeSH term suggestion prototype system that allows users to obtain suggestions from a number of underlying methods and (2) a Python library that implements ours and others' MeSH term suggestion methods and that is aimed at researchers who want to further investigate, create or deploy such type of methods. We describe the architecture of the web-based system and how to use it for the MeSH term suggestion task. For the Python library, we describe how the library can be used for advancing further research and experimentation, and we validate the results of the methods contained in the library on standard datasets. Our web-based prototype system is available at http://ielab-mesh-suggest.uqcloud.net, while our Python library is at https://github.com/ielab/meshsuggestlib.

Reranker models aim to re-rank the passages based on the semantics similarity between the given query and passages, which have recently received more attention due to the wide application of the Retrieval-Augmented Generation. Most previous methods apply pointwise encoding, meaning that it can only encode the context of the query for each passage input into the model. However, for the reranker model, given a query, the comparison results between passages are even more important, which is called listwise encoding. Besides, previous models are trained using the cross-entropy loss function, which leads to issues of unsmooth gradient changes during training and low training efficiency. To address these issues, we propose a novel Listwise-encoded Contrastive text reRanker (ListConRanker). It can help the passage to be compared with other passages during the encoding process, and enhance the contrastive information between positive examples and between positive and negative examples. At the same time, we use the circle loss to train the model to increase the flexibility of gradients and solve the problem of training efficiency. Experimental results show that ListConRanker achieves state-of-the-art performance on the reranking benchmark of Chinese Massive Text Embedding Benchmark, including the cMedQA1.0, cMedQA2.0, MMarcoReranking, and T2Reranking datasets.

We present JEV-Star, a StarCraft II controller that defeats the strongest non-cheating built-in AI, Lv7, by combining fast JEV action selection with persistent GPT-6 planning. The combined system wins four full games at Lv5--Lv7, including two Lv7 victories with different seeds, while retaining a median JEV response time of 0.422 seconds. Mean estimated model cost across these games is USD~3.71 per game: USD~0.15 for JEV and USD~3.56 for GPT-6. We compare this system with an initial JEV-only controller in full-game macro control and multi-unit micromanagement. The standalone controller reaches a 20-minute limit against Lv2 without expanding. Across 35 battle maps with three episodes per map and controller, the combined system raises mean enemy elimination from 16.50\% to 37.69\% and wins from 3 to 7 out of 105. Replay frames and decision logs document resource reservation, persistent economic goals, and stable army objectives in successful full games. The results demonstrate a practical division between inexpensive, subsecond decisions and longer-horizon planning. The comparison evaluates complete systems; concurrent interface improvements mean that planning's contribution is not isolated by a controlled ablation. Code is available at https://github.com/sc2musa/Jev_Star

Judicial work depends on close reading of long records, charge sheets, pleadings, annexures, orders, often spanning hundreds of pages. With limited staff support, exhaustive reading during hearings is impractical. We present CourtNav, a voice-guided, anchor-first navigator for legal PDFs that maps a judge's spoken command (e.g., "go to paragraph 23", "highlight the contradiction in the cross-examination") directly to a highlighted paragraph in seconds. CourtNav transcribes the command, classifies intent with a grammar-first(Exact regex matching), LLM-backed router classifying the queries using few shot examples, retrieves over a layout-aware hybrid index, and auto-scrolls the viewer to the cited span while highlighting it and close alternates. By design, the interface shows only grounded passages, never free text, keeping evidence verifiable and auditable. This need is acute in India, where judgments and cross-examinations are notoriously long.In a pilot on representative charge sheets, pleadings, and orders, median time-to-relevance drops from 3-5 minutes (manual navigation) to 10-15 seconds; with quick visual verification included, 30-45 seconds. Under fixed time budgets, this navigation-first design increases the breadth of the record actually consulted while preserving control and transparency.

We present RACE, a new dataset for benchmark evaluation of methods in the reading comprehension task. Collected from the English exams for middle and high school Chinese students in the age range between 12 to 18, RACE consists of near 28,000 passages and near 100,000 questions generated by human experts (English instructors), and covers a variety of topics which are carefully designed for evaluating the students' ability in understanding and reasoning. In particular, the proportion of questions that requires reasoning is much larger in RACE than that in other benchmark datasets for reading comprehension, and there is a significant gap between the performance of the state-of-the-art models (43%) and the ceiling human performance (95%). We hope this new dataset can serve as a valuable resource for research and evaluation in machine comprehension. The dataset is freely available at http://www.cs.cmu.edu/~glai1/data/race/ and the code is available at https://github.com/qizhex/RACE_AR_baselines.

Creating test collections for offline retrieval evaluation requires human effort to judge documents' relevance. This expensive activity motivated much work in developing methods for constructing benchmarks with fewer assessment costs. In this respect, adjudication methods actively decide both which documents and the order in which experts review them, in order to better exploit the assessment budget or to lower it. Researchers evaluate the quality of those methods by measuring the correlation between the known gold ranking of systems under the full collection and the observed ranking of systems under the lower-cost one. This traditional analysis ignores whether and how the low-cost judgements impact on the statistically significant differences among systems with respect to the full collection. We fill this void by proposing a novel methodology to evaluate how the low-cost adjudication methods preserve the pairwise significant differences between systems as the full collection. In other terms, while traditional approaches look for stability in answering the question "is system A better than system B?", our proposed approach looks for stability in answering the question "is system A significantly better than system B?", which is the ultimate questions researchers need to answer to guarantee the generalisability of their results. Among other results, we found that the best methods in terms of ranking of systems correlation do not always match those preserving statistical significance.

With the growing importance of detecting misinformation, many studies have focused on verifying factual claims by retrieving evidence. However, canonical fact verification tasks do not apply to catching subtle differences in factually consistent claims, which might still bias the readers, especially on contentious political or economic issues. Our underlying assumption is that among the trusted sources, one's argument is not necessarily more true than the other, requiring comparison rather than verification. In this study, we propose ClaimDiff, a novel dataset that primarily focuses on comparing the nuance between claim pairs. In ClaimDiff, we provide 2,941 annotated claim pairs from 268 news articles. We observe that while humans are capable of detecting the nuances between claims, strong baselines struggle to detect them, showing over a 19% absolute gap with the humans. We hope this initial study could help readers to gain an unbiased grasp of contentious issues through machine-aided comparison.

Large Vision-Language Models (VLMs) are increasingly used to evaluate outputs of other models, for image-to-text (I2T) tasks such as visual question answering, and text-to-image (T2I) generation tasks. Despite this growing reliance, the reliability of these Evaluator VLMs remains under explored. In this work, we systematically evaluate the reliability of Evaluator VLMs across both I2T and T2I tasks. We introduce targeted perturbations that degrade output quality along key error dimensions, including object hallucinations, spatial reasoning, factual grounding, and visual fidelity. These perturbations test whether Evaluator VLMs can reliably account for these quality degrading errors in their evaluations. Using a comprehensive benchmark of over 4000 perturbed instances spanning 40 perturbation dimensions, we evaluate 4 prominent VLMs using single-answer scoring, pairwise comparison, and reference-guided paradigms. Our findings reveal that current VLM evaluators exhibit substantial blind spots: they often fail to detect perturbed outputs - in some cases exceeding 50%, struggle particularly with fine-grained compositional and spatial errors, and are often insensitive to hallucinated content that contradicts the input image. Pairwise comparison proves more reliable, though failure rates persist. These results highlight the unreliable nature of current Evaluator VLMs and urge caution in their deployment for benchmarking and development decisions. Code and data have been made publicly available.

Scanpath similarity metrics are central to eye-movement research, yet existing methods predominantly evaluate spatial and temporal alignment while neglecting semantic equivalence between attended image regions. We present a semantic scanpath similarity framework that integrates vision-language models (VLMs) into eye-tracking analysis. Each fixation is encoded under controlled visual context (patch-based and marker-based strategies) and transformed into concise textual descriptions, which are aggregated into scanpath-level representations. Semantic similarity is then computed using embedding-based and lexical NLP metrics and compared against established spatial measures, including MultiMatch and DTW. Experiments on free-viewing eye-tracking data demonstrate that semantic similarity captures partially independent variance from geometric alignment, revealing cases of high content agreement despite spatial divergence. We further analyze the impact of contextual encoding on description fidelity and metric stability. Our findings suggest that multimodal foundation models enable interpretable, content-aware extensions of classical scanpath analysis, providing a complementary dimension for gaze research within the ETRA community.

The procure to pay process (P2P) in large enterprises is a back-end business process which deals with the procurement of products and services for enterprise operations. Procurement is done by issuing purchase orders to impaneled vendors and invoices submitted by vendors are paid after they go through a rigorous validation process. Agents orchestrating P2P process often encounter the problem of matching a product or service descriptions in the invoice to those in purchase order and verify if the ordered items are what have been supplied or serviced. For example, the description in the invoice and purchase order could be TRES 739mL CD KER Smooth and TRES 0.739L CD KER Smth which look different at word level but refer to the same item. In a typical P2P process, agents are asked to manually select the products which are similar before invoices are posted for payment. This step in the business process is manual, repetitive, cumbersome, and costly. Since descriptions are not well-formed sentences, we cannot apply existing semantic and syntactic text similarity approaches directly. In this paper, we present two approaches to solve the above problem using various types of available agent's recorded feedback data. If the agent's feedback is in the form of a relative ranking between descriptions, we use similarity ranking algorithm. If the agent's feedback is absolute such as match or no-match, we use classification similarity algorithm. We also present the threats to the validity of our approach and present a possible remedy making use of product taxonomy and catalog. We showcase the comparative effectiveness and efficiency of the proposed approaches over many benchmarks and real-world data sets.

In this work, we propose GUIPilot, an approach for detecting inconsistencies between the mobile design and their implementations. The mobile design usually consists of design mock-ups that specify (1) the expected screen appearances (e.g., widget layouts, colors, and shapes) and (2) the expected screen behaviors, regarding how one screen can transition into another (e.g., labeled widgets with textual description). Given a design mock-up and the implementation of its application, GUIPilot reports both their screen inconsistencies as well as process inconsistencies. On the one hand, GUIPilot detects the screen inconsistencies by abstracting every screen into a widget container where each widget is represented by its position, width, height, and type. By defining the partial order of widgets and the costs of replacing, inserting, and deleting widgets in a screen, we convert the screen-matching problem into an optimizable widget alignment problem. On the other hand, we translate the specified GUI transition into stepwise actions on the mobile screen (e.g., click, long-press, input text on some widgets). To this end, we propose a visual prompt for the vision-language model to infer widget-specific actions on the screen. By this means, we can validate the presence or absence of expected transitions in the implementation. Our extensive experiments on 80 mobile applications and 160 design mock-ups show that (1) GUIPilot can achieve 94.5% precision and 99.6% recall in detecting screen inconsistencies, outperforming the state-of-the-art approach, such as GVT, by 66.2% and 56.6% respectively, and (2) GUIPilot reports zero errors in detecting process inconsistencies. Furthermore, our industrial case study on applying GUIPilot on a trading mobile application shows that GUIPilot has detected nine application bugs, and all the bugs were confirmed by the original application experts.

Human visual search is serial: the fovea must land on a candidate to confirm it, and those landings form a scanpath. Whether multimodal large language models (MLLMs), given the same foveated input, search as humans do bears on their use as models of human vision and on attention-alignment scores. We compare three general-purpose MLLMs with human eye-movement scanpaths on goal-directed search (COCO-Search18), driving each model fixation by fixation through an identical, human-matched foveated view and assessing it along three axes: the decision of target presence, the efficiency of reaching the target, and the gaze process itself. The axes dissociate. On the decision and on target acquisition the models match or exceed humans, detecting present targets near ceiling and reaching them on the first saccade more often than people do. The gaze process is not human. Under the human-matched condition, all three share one signature: low-entropy, large-amplitude, self-consistent scanpaths that agree with themselves far more closely than two humans agree with each other. That is consistent with a single-pass, non-serial architecture rather than a limit of acuity. Matched retinal input reproduces where humans look but not how the looking unfolds in time, and no degradation regime recovers human-like search at human-like success. The gap sits on a process axis that answer-alignment and saliency metrics do not measure. Because they miss it, such metrics cannot certify human-like vision, and zero-shot models suit outcome and spatial questions but not temporal, process-level ones.

Qualitative comparison figures are central evidence in computer vision papers, and vision-language models (VLMs) are increasingly used to judge them. Yet existing benchmarks score only scalar quality or overall preference, so a judge can be rewarded for picking the preferred image for the wrong visual reason. We introduce VisionQ, the first benchmark built from peer-reviewed CV comparison figures that grounds every judgment in a named visual criterion: each question states the criterion, and a judge is credited only when it selects the output the authors identify as best on that criterion. We call this task criterion-conditioned visual discrimination. VisionQ comprises (1) a corpus of 1,409 CVPR and ICCV papers with 1,800+ validated comparison figures and 3,911 hand-annotated data points linking method crops to author-stated visual claims; (2) a six-axis, 51-leaf taxonomy of the visual criteria behind qualitative judgment; (3) a criterion-conditioned evaluation protocol that hides method names, captions, and paper identity and reports accuracy per criterion; and (4) VisionQ-Judge, a DPO-tuned Gemma-4-E4B judge trained on symmetric evidence pairs, which reduces last-option predictions by 7.0pp and improves accuracy by 2.5pp on a held-out test set. Evaluating 20 open- and closed-source VLM judges, we find that the strongest reach only 63.1% accuracy (chance 32.2%) and that reliability varies sharply across criteria. Code: https://github.com/ReML-AI/visionq. Data: https://huggingface.co/datasets/visionq-anon-2026/VisionQ-1k.

The rapid advancement of Large Language Models (LLMs) necessitates robust evaluation methodologies. Current benchmarking approaches often rely on comparing model outputs against predefined prompts and reference outputs. Relying on predefined reference outputs hinders flexible adaptation of benchmarks to the rapidly evolving capabilities of LLMs. This limitation necessitates periodic efforts to prepare new benchmarks. To keep pace with rapidly evolving LLM capabilities, we propose a more flexible benchmarking approach. Our method, \textbf{Varco Arena}, provides reference-free benchmarking of LLMs in tournament style. \textbf{Varco Arena} directly compares LLM outputs across a diverse set of prompts, determining model rankings through a single-elimination tournament structure. This direct pairwise comparison offers two key advantages: (1) Direct comparison, unmediated by reference text, more effectively orders competing LLMs, resulting in more reliable rankings, and (2) reference-free approach to benchmarking adds flexibility in updating benchmark prompts by eliminating the need for quality references. Our empirical results, supported by simulation experiments, demonstrate that the \textbf{Varco Arena} tournament approach aligns better with the current Elo model for benchmarking LLMs. The alignment is measured in terms of Spearman correlation, showing improvement over current practice of benchmarking that use reference outputs as comparison anchors.

Ambient AI scribes draft clinical notes, and published audits find their dominant error is omission: information the encounter established that the note fails to record. The standard check is an LLM judge: a second model reads the note against the transcript and flags problems. We ask whether judges detect omissions. Public corpora cannot supply the answer key: their clinician reference notes and transcripts are materially discrepant. Our benchmark has 500 single-error note pairs from audited fact sheets, 298 with a named fact certainly absent and 202 added-or-altered controls. Across eight judge designs, paired discrimination (the flawed note below its clean twin, 0.5 a coin flip) reads 0.79-0.94 on added or altered content and 0.50-0.63 on omissions. On single notes, no design flags omissions reliably more often than perfect notes. Wording changes, voting and GEPA prompt optimisation move the operating point without creating usable detection. Restructuring the task recovers it: list the facts the transcript establishes, then check the note for each. Two methods reach it independently and trade off: a per-fact pipeline, and a GEPA-evolved prompt doing the same in one call. The pipeline's flags name the missing fact and its severity at 2.7% false alarms. The single call detects more (36.9% against 24.6%, p=0.002) at 6.2% false alarms and a tenth of the cost per note. A physician author validated 70 items and, where the two routes disagree, sided with the pipeline on 10 of 10 (p=0.002). A second clinician, not an author, graded the severity rubric blind and agrees to within a grade. On real vendor notes from a companion census no benchmark threshold transfers, but the re-calibrated single call detects more than the best of the eight at half its false-alarm rate. Omissions whose fact is restated elsewhere defeat both routes. We release the benchmark, prompts and judgements.

Methodological progress in artificial intelligence (AI) for electronic health records (EHRs) depends on our ability to determine which algorithms work better, and under which conditions. However, such progress is thought to be hindered by difficulties in reproducibility and in defining clinically meaningful evaluation tasks. We empirically study these barriers by re-implementing 12 historical and recent algorithms within a shared evaluation framework and evaluating them on two clinical datasets, MIMIC-IV and NWICU. We compare two complementary task families: expert-authored clinically meaningful tasks and generated tasks defined from randomly sampled event codes and prediction horizons. We ask whether relative algorithms comparisons transfer across task families and datasets, whether residual task heterogeneity contains useful methodological structure, and what a controlled comparison reveals about progress over the last decade. We find that aggregate pairwise comparisons transfer strongly across evaluation settings, including from randomly generated tasks to clinically meaningful tasks and across datasets. At the same time, clinically meaningful tasks exhibit greater task-method interaction, providing preliminary evidence that task properties can help explain when particular modeling choices are advantageous. Finally, newer algorithms do not consistently outperform earlier approaches: gradient-boosted trees remain highly competitive when paired with a modern, wide and sparse representation of the EHR. Together, these results suggest that useful methodological knowledge may require less task engineering than commonly assumed, while highlighting the importance of understanding the structured heterogeneity that remains across tasks and methods.

Language model evaluation is a daunting task: prompts are brittle, corpus-level perplexities are vague, and the choice of benchmarks are endless. Finding examples that show meaningful, generalizable differences between two LMs is crucial to understanding where one model succeeds and another fails. Can this process be done automatically? In this work, we propose methodology for automated comparison of language models that uses performance-aware contextual embeddings to find fine-grained features of text where one LM outperforms another. Our method, which we name BehaviorBox, extracts coherent features that demonstrate differences with respect to the ease of generation between two LMs. Specifically, BehaviorBox finds features that describe groups of words in fine-grained contexts, such as "conditional 'were' in the phrase 'if you were'" and "exclamation marks after emotional statements", where one model outperforms another within a particular datatset. We apply BehaviorBox to compare models that vary in size, model family, and post-training, and enumerate insights into specific contexts that illustrate meaningful differences in performance which cannot be found by measures such as corpus-level perplexity alone.

Generating concise summaries of news events is a challenging natural language processing task. While journalists often curate timelines to highlight key sub-events, newcomers to a news event face challenges in catching up on its historical context. In this paper, we address this need by introducing the task of background news summarization, which complements each timeline update with a background summary of relevant preceding events. We construct a dataset by merging existing timeline datasets and asking human annotators to write a background summary for each timestep of each news event. We establish strong baseline performance using state-of-the-art summarization systems and propose a query-focused variant to generate background summaries. To evaluate background summary quality, we present a question-answering-based evaluation metric, Background Utility Score (BUS), which measures the percentage of questions about a current event timestep that a background summary answers. Our experiments show the effectiveness of instruction fine-tuned systems such as Flan-T5, in addition to strong zero-shot performance using GPT-3.5.

Sequential agent search accumulates changes from its current champion but discards alternative branches; independent proposals preserve breadth but restart from the root. Loreley instead retains complete repository states in a Quality-Diversity (QD) archive and samples them as parents or supplies them as context for later edits. Candidates are Git commits produced in isolated worktrees and judged by a project-supplied evaluator. We compare configured Loreley QD, sequential champion editing, and independent root proposals in a matched Zstandard experiment: seven paired blocks and 48 physical candidate jobs per policy and block (1,008 total), with root-only initialization and each policy's native concurrency. Validation selected a winner at each budget checkpoint; an agent-hidden holdout measured the fixed candidate. At 48 jobs, QD was 0.135% below Sequential Champion (95% BCa interval for the paired effect: -0.556% to +0.161%) and 0.320% above Independent Root (-0.082% to +0.686%). Neither contrast established a QD advantage; Sequential had the highest observed 48-job mean and median. Archive retention and later sampling did occur. Four of seven final QD winners had a non-incumbent state in their primary-parent ancestry under a retrospective one-incumbent rule applied only to the observed QD stream. Including inspiration edges raised the count to six, without showing that supplied context caused an edit. Three earlier capability campaigns produced generation-4, multi-file improvements in two Python libraries and a separate Zstandard revision. Loreley engaged the intended stepping-stone mechanism, but the controlled experiment did not show an endpoint benefit at 48 jobs.

LLM-as-a-judge enables evaluation across diverse tasks, but inference cost and confidence reliability become critical at scale. We study whether a decision-only judge can provide an economical first pass and identify when stronger evaluation is needed. Comparing jev-as-a-judge with sixteen generative and reward-model judges, with blinded human adjudication, we find it within three percentage points of a state-of-the-art LLM judge, our strongest comparator, on ordinary preference and evidence-grounded factuality at 0.36% of the comparator's fee. Larger gaps arise when judgments require checking a derivation or resisting an elaborately written wrong answer. On several benchmarks, JEV's gap to this comparator is concentrated in low-confidence decisions. A frozen cascade that accepts confident verdicts and escalates uncertain ones retains 99% of the comparator's accuracy at lower cost.

An agent that inherits six one-line memories may pull at most one archived source record before acting; a directive written into the store can steer that choice: a pointer to the record, a criterion that identifies it, or both. Across twelve registered studies on one instrument lineage (14,760 attempts) we measured where the request goes under each form. On six direct-provider models a length-matched criterion exceeded a bare id by +35.0 points [+31.2, +38.8] (Study D); the contrast failed its registered superiority rule on a nine-model OpenRouter-served panel (Study E). Appending the id cancelled the criterion on three Claude models (Opus 5: 40/40 to 0/40; Study F-x); six byte-matched edits gave each exact string its own effect (Study G), and a re-run at eighty runs per cell left fifteen of thirty replication contrasts within the margin, fifteen unresolved and none beyond (Study G'). A ratification line (+96.0 points on Opus 5) and a budget of two credits restored the target on all three (Study J); across five criterion strings the suffix's cancellation held for four of the five wordings on Opus 5 and all five wordings on Fable 5.1 (Study H2); in a second store every model followed the criterion (Study H1). Continued into a decision, the criterion moved the choice toward the current record (+100.0 points, Opus 5) and away from it on Fable 5.1 (Study I). A one-character plan pointer's effect (+78.0 points; Study B, after a correction of its first repository report) returned the same verdict under a prospectively registered re-run (+81.7 points; Study B'). All results are descriptive effects of exact edits on fixed panels with registered intervals and no mechanism claim.

This paper presents a new approach for code similarity on High Level programs. Our technique is based on Fast Dynamic Time Warping, that builds a warp path or points relation with local restrictions. The source code is represented into Time Series using the operators inside programming languages that makes possible the comparison. This makes possible subsequence detection that represent similar code instructions. In contrast with other code similarity algorithms, we do not make features extraction. The experiments show that two source codes are similar when their respective Time Series are similar.

Many tasks revolve around editing a document, whether code or text. We formulate the revision similarity problem to unify a wide range of machine learning evaluation problems whose goal is to assess a revision to an existing document. We observe that revisions usually change only a small portion of an existing document, so the existing document and its immediate revisions share a majority of their content. We formulate five adequacy criteria for revision similarity measures, designed to align them with human judgement. We show that popular pairwise measures, like BLEU, fail to meet these criteria, because their scores are dominated by the shared content. They report high similarity between two revisions when humans would assess them as quite different. This is a fundamental flaw we address. We propose a novel static measure, Excision Score (ES), which computes longest common subsequence (LCS) to remove content shared by an existing document with the ground truth and predicted revisions, before comparing only the remaining divergent regions. This is analogous to a surgeon creating a sterile field to focus on the work area. We use approximation to speed the standard cubic LCS computation to quadratic. In code-editing evaluation, where static measures are often used as a cheap proxy for passing tests, we demonstrate that ES surpasses existing measures. When aligned with test execution on HumanEvalFix, ES improves over its nearest competitor, SARI, by 12% Pearson correlation and by >21% over standard measures like BLEU. The key criterion is invariance to shared context; when we perturb HumanEvalFix with increased shared context, ES' improvement over SARI increases to 20% and >30% over standard measures. ES also handles other corner cases that other measures do not, such as correctly aligning moved code blocks, and appropriately rewarding matching insertions or deletions.

Medical imaging artificial intelligence has achieved strong performance in isolated image interpretation, but remains poorly aligned with radiological practice, where diagnosis and follow-up rely on comparison across prior studies and analogous reference cases. Here we formulate radiological comparison as an entity-aware cross-image reasoning problem and introduce a framework that supports both reference-case retrieval and temporal comparative interpretation. We construct MedReCo-DB, a large-scale comparative imaging resource derived from routine image-report pairs, comprising more than 690,000 images from over 160,000 patients across eight institutions, four countries and seven imaging modalities. Reports are decomposed into anatomical structures, abnormal findings and pathological conditions to provide supervision for entity-conditioned retrieval and comparative visual question answering. Using this resource, we develop MedReCo, an entity-aware visual encoder for controllable retrieval of clinically analogous cases, and MedReCo-VLM, a vision--language extension for generative interpretation of interval change. Across internal, external and cross-center evaluations, MedReCo achieved the highest Recall@1 in all 12 internal retrieval settings and improved external retrieval by a mean of 6.0 percentage points. In clinically confusable differential groups, it consistently outperformed the strongest baselines. MedReCo-VLM achieved the best performance across all comparative generation evaluations and improved longitudinal follow-up accuracy by 14.5-46.5 percentage points on chest radiographs and 13.0-27.9 percentage points on CT. These findings suggest that entity-aware comparative reasoning can be learned from routine clinical data at scale and may provide a more clinically aligned foundation for medical imaging AI.

We introduce a novel framework for analyzing sorting algorithms in pairwise ranking prompting (PRP), re-centering the cost model around LLM inferences rather than traditional pairwise comparisons. While classical metrics based on comparison counts have traditionally been used to gauge efficiency, our analysis reveals that expensive LLM inferences overturn these predictions; accordingly, our framework encourages strategies such as batching and caching to mitigate inference costs. We show that algorithms optimal in the classical setting can lose efficiency when LLM inferences dominate the cost under certain optimizations.

Automatic evaluation with large language models, commonly known as LLM-as-a-judge, is now standard across reasoning and alignment tasks. Despite evaluating many samples in deployment, these evaluators typically (i) treat each case independently, missing the opportunity to accumulate experience, and (ii) rely on a single fixed prompt for all cases, neglecting the need for sample-specific evaluation criteria. We introduce Learning While Evaluating (LWE), a framework that allows evaluators to improve sequentially at inference time without requiring training or validation sets. LWE maintains an evolving meta-prompt that (i) produces sample-specific evaluation instructions and (ii) refines itself through self-generated feedback. Furthermore, we propose Selective LWE, which updates the meta-prompt only on self-inconsistent cases, focusing computation where it matters most. This selective approach retains the benefits of sequential learning while being far more cost-effective. Across two pairwise comparison benchmarks, Selective LWE outperforms strong baselines, empirically demonstrating that evaluators can improve during sequential testing with a simple selective update, learning most from the cases they struggle with.

An industrial process includes many devices, variables, and sub-processes that are physically or electronically interconnected. These interconnections imply some level of correlation between different process variables. Since most of the alarms in a process plant are defined on process variables, alarms are also correlated. However, this can be a nuisance to operators, for one fault might trigger a, sometimes large, number of alarms. So, it is essential to find and correct correlated alarms. In this paper, we study different methods and techniques proposed to measure correlation or similarity between alarms. The similarity indices are first analytically calculated and then studied and compared. The results are also validated using Monte-Carlo simulation.

While voice user interfaces offer increased accessibility due to hands-free and eyes-free interactions, older adults often have challenges such as constructing structured requests and perceiving how such devices operate. Voice-first user interfaces have the potential to address these challenges by enabling multimodal interactions. Standalone voice + touchscreen Voice Assistants (VAs), such as Echo Show, are specific types of devices that adopt such interfaces and are gaining popularity. However, the affordances of the additional touchscreen for older adults are unknown. Through a 40-day real-world deployment with older adults living independently, we present a within-subjects study (N = 16; age M = 82.5, SD = 7.77, min. = 70, max. = 97) to understand how a built-in touchscreen might benefit older adults during device setup, conducting self-report diary survey, and general uses. We found that while participants appreciated the visual outputs, they still preferred to respond via speech instead of touch. We identified six design implications that can inform future innovations of senior-friendly VAs for managing healthcare and improving quality of life.

We discuss the notion of coherent states from three different perspectives: the seminal approach of Schroedinger, the experimental take of quantum optics, and the theoretical developments in quantum gravity. This comparative study tries to emphasise the connections between the approaches, and to offer a coherent short story of the field, so to speak. It may be useful for pedagogical purposes, as well as for specialists of quantum optics and quantum gravity willing to embed their perspective within a wider landscape.

Stronger AI agents do not automatically produce better organizations: teams must also learn which work arrangements to retain and when to reconsider them. We propose a modeling specification for recursive organization improvement and evaluate it through an executable checker, a public-record mapping, and controlled simulation. The specification connects actor-visible histories, organizational memory, decision rights, and evidence-carrying change contracts. The mechanism study crosses six decision rules, three memory conditions, and three task environments under fixed resource ceilings. In a stationary environment, cumulative evidence raises balanced evaluation's normalized net value per task from 0.45224 to 0.48007. Repeated reassessment's disadvantage relative to this comparator falls from 0.01702 with reset evidence to 0.00007 with cumulative evidence. A reversal of the best workflow reveals the opposite cost: indefinite retention delays adaptation, while a finite window restores eventual performance at a transition cost. In exploratory controls, matching trial acquisition and label reuse reduces the apparent reassessment gain from 0.00607 to 0.00191. Program replacement adds no stable benefit across the tested reversal times. The study identifies evidence acquisition, reuse, and timely updating as mechanisms that must be separated from evaluator replacement when assessing organizational improvement.

As AI systems are used to answer more difficult questions and potentially help create new knowledge, judging the truthfulness of their outputs becomes more difficult and more important. How can we supervise unreliable experts, which have access to the truth but may not accurately report it, to give answers that are systematically true and don't just superficially seem true, when the supervisor can't tell the difference between the two on their own? In this work, we show that debate between two unreliable experts can help a non-expert judge more reliably identify the truth. We collect a dataset of human-written debates on hard reading comprehension questions where the judge has not read the source passage, only ever seeing expert arguments and short quotes selectively revealed by 'expert' debaters who have access to the passage. In our debates, one expert argues for the correct answer, and the other for an incorrect answer. Comparing debate to a baseline we call consultancy, where a single expert argues for only one answer which is correct half of the time, we find that debate performs significantly better, with 84% judge accuracy compared to consultancy's 74%. Debates are also more efficient, being 68% of the length of consultancies. By comparing human to AI debaters, we find evidence that with more skilled (in this case, human) debaters, the performance of debate goes up but the performance of consultancy goes down. Our error analysis also supports this trend, with 46% of errors in human debate attributable to mistakes by the honest debater (which should go away with increased skill); whereas 52% of errors in human consultancy are due to debaters obfuscating the relevant evidence from the judge (which should become worse with increased skill). Overall, these results show that debate is a promising approach for supervising increasingly capable but potentially unreliable AI systems.

Did you try out the new Bing Search? Or maybe you fiddled around with Google AI~Overviews? These might sound familiar because the modern-day search stack has recently evolved to include retrieval-augmented generation (RAG) systems. They allow searching and incorporating real-time data into large language models (LLMs) to provide a well-informed, attributed, concise summary in contrast to the traditional search paradigm that relies on displaying a ranked list of documents. Therefore, given these recent advancements, it is crucial to have an arena to build, test, visualize, and systematically evaluate RAG-based search systems. With this in mind, we propose the TREC 2024 RAG Track to foster innovation in evaluating RAG systems. In our work, we lay out the steps we've made towards making this track a reality -- we describe the details of our reusable framework, Ragnar\"ok, explain the curation of the new MS MARCO V2.1 collection choice, release the development topics for the track, and standardize the I/O definitions which assist the end user. Next, using Ragnar\"ok, we identify and provide key industrial baselines such as OpenAI's GPT-4o or Cohere's Command R+. Further, we introduce a web-based user interface for an interactive arena allowing benchmarking pairwise RAG systems by crowdsourcing. We open-source our Ragnar\"ok framework and baselines to achieve a unified standard for future RAG systems.

While recent advancements in large multimodal models (LMMs) have significantly improved their abilities in image quality assessment (IQA) relying on absolute quality rating, how to transfer reliable relative quality comparison outputs to continuous perceptual quality scores remains largely unexplored. To address this gap, we introduce Compare2Score-an all-around LMM-based no-reference IQA (NR-IQA) model, which is capable of producing qualitatively comparative responses and effectively translating these discrete comparative levels into a continuous quality score. Specifically, during training, we present to generate scaled-up comparative instructions by comparing images from the same IQA dataset, allowing for more flexible integration of diverse IQA datasets. Utilizing the established large-scale training corpus, we develop a human-like visual quality comparator. During inference, moving beyond binary choices, we propose a soft comparison method that calculates the likelihood of the test image being preferred over multiple predefined anchor images. The quality score is further optimized by maximum a posteriori estimation with the resulting probability matrix. Extensive experiments on nine IQA datasets validate that the Compare2Score effectively bridges text-defined comparative levels during training with converted single image quality score for inference, surpassing state-of-the-art IQA models across diverse scenarios. Moreover, we verify that the probability-matrix-based inference conversion not only improves the rating accuracy of Compare2Score but also zero-shot general-purpose LMMs, suggesting its intrinsic effectiveness.

A common retrieve-and-rerank paradigm involves retrieving relevant candidates from a broad set using a fast bi-encoder (BE), followed by applying expensive but accurate cross-encoders (CE) to a limited candidate set. However, relying on this small subset is often susceptible to error propagation from the bi-encoders, which limits the overall performance. To address these issues, we propose the Comparing Multiple Candidates (CMC) framework. CMC compares a query and multiple embeddings of similar candidates (i.e., neighbors) through shallow self-attention layers, delivering rich representations contextualized to each other. Furthermore, CMC is scalable enough to handle multiple comparisons simultaneously. For example, comparing ~10K candidates with CMC takes a similar amount of time as comparing 16 candidates with CE. Experimental results on the ZeSHEL dataset demonstrate that CMC, when plugged in between bi-encoders and cross-encoders as a seamless intermediate reranker (BE-CMC-CE), can effectively improve recall@k (+4.8%-p, +3.5%-p for R@16, R@64) compared to using only bi-encoders (BE-CE), with negligible slowdown (<7%). Additionally, to verify CMC's effectiveness as the final-stage reranker in improving top-1 accuracy, we conduct experiments on downstream tasks such as entity, passage, and dialogue ranking. The results indicate that CMC is not only faster (11x) but also often more effective than CE, with improved prediction accuracy in Wikipedia entity linking (+0.7%-p) and DSTC7 dialogue ranking (+3.3%-p).

The profusion of user generated content caused by the rise of social media platforms has enabled a surge in research relating to fields such as information retrieval, recommender systems, data mining and machine learning. However, the lack of comprehensive baseline data sets to allow a thorough evaluative comparison has become an important issue. In this paper we present a large data set of news items from well-known aggregators such as Google News and Yahoo! News, and their respective social feedback on multiple platforms: Facebook, Google+ and LinkedIn. The data collected relates to a period of 8 months, between November 2015 and July 2016, accounting for about 100,000 news items on four different topics: economy, microsoft, obama and palestine. This data set is tailored for evaluative comparisons in predictive analytics tasks, although allowing for tasks in other research areas such as topic detection and tracking, sentiment analysis in short text, first story detection or news recommendation.

We present Code Comparison Tuning (CCT), a simple and effective tuning method for code large language models (Code LLMs) to better handle subtle code errors. Specifically, we integrate the concept of comparison into instruction tuning, both at the token and sequence levels, enabling the model to discern even the slightest deviations in code. To compare the original code with an erroneous version containing manually added code errors, we use token-level preference loss for detailed token-level comparisons. Additionally, we combine code segments to create a new instruction tuning sample for sequence-level comparisons, enhancing the model's bug-fixing capability. Experimental results on the HumanEvalFix benchmark show that CCT surpasses instruction tuning in pass@1 scores by up to 4 points across diverse code LLMs, and extensive analysis demonstrates the effectiveness of our method.

A login screen that appears after a tap on Sign in is expected; the same screen after a tap on View order is an attack. For GUI agents, safety is therefore a property of the transition rather than of the screen, and a monitor that inspects only screens can be defeated by reusing a legitimate one. Judging a transition requires an expectation of what should have followed the action. Existing GUI world models provide one, but they output it as text, code, or images, so checking it against the observed screen requires a second model to judge the two. We argue that a world model meant for verification should instead predict in the space in which observations are encoded, and present LGWM, a decoder-free, action-conditioned world model that predicts the representation of the next screen directly, trained without semantic annotation on 1.85M real GUI transitions. Verification reduces to a vector comparison, and the same signal reveals whether a mismatch is harmful. We evaluate on RSWT-BENCH, a diagnostic where each credential screen appears under both a legitimate and a hijacked transition, so detectors that see only the screen are at chance by construction. The training-free score reaches 0.987 AUC at 17 ms per decision, on par with the strongest closed-source VLMs and about ten AUC points above generative GUI world models at over three orders of magnitude lower latency. The residual direction reaches 0.953 AUC at separating harmful from benign violations, where prompted VLMs are near chance. Further analyses show that the prediction is a usable future state rather than an anomaly score. World models have mostly served as simulators or planners; our results point to a third role, verification, for which predicting in representation space is the natural design.

Analyzing the pattern of semantic variation in long real-world texts such as books or transcripts is interesting from the stylistic, cognitive, and linguistic perspectives. It is also useful for applications such as text segmentation, document summarization, and detection of semantic novelty. The recent emergence of several vector-space methods for sentence embedding has made such analysis feasible. However, this raises the issue of how consistent and meaningful the semantic representations produced by various methods are in themselves. In this paper, we compare several recent sentence embedding methods via time-series of semantic similarity between successive sentences and matrices of pairwise sentence similarity for multiple books of literature. In contrast to previous work using target tasks and curated datasets to compare sentence embedding methods, our approach provides an evaluation of the methods 'in the wild'. We find that most of the sentence embedding methods considered do infer highly correlated patterns of semantic similarity in a given document, but show interesting differences.

We present Iris-mini and Iris-pro, two search agents trained at the 35B-A3B and 397B-A17B scales, together with the data pipeline and training recipe behind them. Tasks are reverse-constructed from the hyperlink structure of a web corpus: we author multi-hop chains over an entity graph distilled from a seed page and its out-links, rewrite every non-answer entity into a descriptive reference so that no clue can be resolved by string matching, and admit only questions that a reference model fails closed-book yet solves once the supporting evidence is supplied. These questions are then turned into trajectories, which are filtered at both the trajectory and the turn level before SFT. The policy is then optimized by RL against live search, with the reward judge and the observation summarizer served inside the training cluster, and with over-long rollouts interrupted at the request level and resumed from their committed prefix at the next step. We alternate the two stages in a procedure we call SFT-RL climbing, returning the hardest solved and most efficient rollouts of each RL round to the next supervised pass. Because inference-time context management is worth more on these benchmarks than most reported differences between systems, we evaluate every benchmark both with and without it, holding the tool set, the context limit, and the judge fixed. All results come from a single ReAct agent, with no sub-agents and no test-time verification. With management enabled, on BrowseComp, BrowseComp-ZH, DeepSearchQA, and HLE the two models reach 82.2/84.8/86.9/52.3 and 88.6/85.1/92.9/56.4, the strongest overall results among open-source search agents in their respective parameter ranges. We plan to release the model weights together with the complete recipe for data construction, training, and evaluation.

A comparison of the distances to the Huanan Seafood Market of early Covid cases with known links to the market versus cases without known links shows results apparently incompatible with a location model lacking proximity ascertainment bias. The sign of the difference instead agrees with a model in which such ascertainment bias is large. In the presence of such bias inferences based on the clustering of case locations become unreliable.

Streaming video understanding requires models to interpret evidence as it arrives, yet current evaluations often report task scores without specifying when evidence becomes valid, how visual history is maintained, or how responses are triggered. As a result, similar scores may correspond to different workloads, failure modes, and operational behavior. We introduce TRACE (Temporal Audit and Condition-aware Evaluation), a condition-aware benchmark and evaluation framework that makes these factors explicit. TRACE combines temporally audited visual tasks with evidence timing and instruction-dependent trigger annotations, a unified causal Core--Adapter protocol that controls information availability while recording actual history processing and response events, and multidimensional reporting of answer quality, timeliness, response-selection behavior, workload, completion, and reliability. On 1,240 records from 517 videos, we evaluate eight publicly available models or systems in eight configurations. We find that nearly identical QA accuracy can mask substantial differences in completion, answer validity, and generation workload, while proactive performance separates into response quality, response delay, false alarms (responses emitted while no target window is currently valid and a later one remains), and missed target windows. These results show that streaming-video performance should be interpreted as execution-conditioned system behavior rather than a single score. Our benchmark and code can be accessed at https://github.com/om-ai-lab/trace-bench{https://github.com/om-ai-lab/trace-bench}.