cs.AI · 2026-07-20 · No. 59

Artificial Intelligence, 2026-07-20.

28 new papers in cs.AI. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

28 entries
  1. 01

    CRAFT: Clustering Rubrics to Diagnose Weak LLM Capabilities and Generate Targeted Fine-Tuning Data

    Vipul Gupta, Zihao Wang, Razvan-Gabriel Dumitru, MohammadHossein Rezaei, Aakash Sabharwal, Yunzhong He

    cs.AI · cs.LG

    Evaluations should do more than measure a models current performance. They should tell us what to fix for the next model iteration and provide a way to generate targeted post training data. Most evaluation pipelines identify weak examples, topics, or categories, but they leave the underlying capability failure implicit: they say where a model fails, not why. We introduce CRAFT, a method that converts any rubric based evaluation dataset into a...

    arxiv.org/abs/2607.16122 · PDF

  2. 02

    Harmonizing AI Safety Thresholds

    Wilber Sean Anterola, Matthew Ball, Luis F. Lafuerza, Markov Grey

    cs.AI

    Frontier AI companies have published capability thresholds that differ substantially, making it difficult for third parties to verify whether a threshold has been crossed or to compare requirements across companies. Moreover, without common minimum thresholds, risk mitigation may be inconsistent, creating a potential race to the bottom in safety standards. We develop a methodology for deriving harmonized thresholds across three risk domains....

    arxiv.org/abs/2607.16112 · PDF

  3. 03

    SciForge: An AI-Native, Multimodal Workbench for Scientific Discovery

    SciForge Team, Zhangyang Gao, Minghao Fang, Yifei Liu, Hanhui Yang, Xinyu Gu, Shixiang Tang, Siqi Sun, Lei Bai,...

    cs.AI

    Scientific work increasingly spans heterogeneous artifacts -- papers, code, datasets, scientific file formats, model outputs, figures, manuscripts, and team decisions -- yet general-purpose AI assistants rarely preserve these objects as a coherent, auditable research state. We present SciForge, a multimodal research-native AI workbench that reserves the graphical interface for human judgment while search, parsing, model routing, workflow...

    arxiv.org/abs/2607.16038 · PDF

  4. 04

    Closing the AI Trust Gap: The Case for Independent Certification for Trustworthy AI

    Trisevgeni Papakonstantinou, Cansu Canca, Farah Nanji, Waheedullah Pardess, Jen Weedon, Jasmijn Remmers, Eliza...

    cs.AI

    Over the past decade, responsible AI (RAI) has produced a substantial body of practice for identifying and mitigating the risks AI poses in high-stakes settings. Yet this work has not produced a market that rewards trustworthiness. Firms that invest seriously in safety, fairness, and oversight cannot consistently prove to consumers, regulators, and shareholders that their systems go beyond the bare minimum of compliance. What is missing is a...

    arxiv.org/abs/2607.15992 · PDF

  5. 05

    A Formally Grounded ODRL Evaluator: Implementation and Comparison

    Jaime Osvaldo Salas, Paolo Pareti, Adeel Aslam, Christopher Maidens, George Konstantinidis

    cs.AI

    The ODRL policy language is emerging as the de-facto standard for policy modelling data access and usage preferences, AI governance policies and data workflows in European dataspaces. The current standard has no mathematical formal semantics to describe how a system should implement policy evaluation. This has resulted in a variety of systems and tools that implement their own interpretation of the language, which limits interoperability and...

    arxiv.org/abs/2607.15987 · PDF

  6. 06

    DSWorld: A Data Science World Model for Efficient Autonomous Agents

    Zherui Yang, Fan Liu, Hao Liu

    cs.AI

    Despite strong capabilities in data understanding and decision-making, autonomous data science agents still heavily rely on trial-and-error workflows that involve expensive computation. This bottleneck motivates models that can anticipate the effects of data science operations before real execution. In this paper, we introduce the concept of Data Science World Model, which model the data science execution environment by predicting environment...

    arxiv.org/abs/2607.15901 · PDF

  7. 07

    Knowledge-Centric Agents for Workflow Generation

    Zhendong Li, Lei Sun, Ruibo Ming, He Zhang, Danda Pani Paudel, Luc Van Gool, Jinjin Gu

    cs.AI

    Workflow generation in visual creation systems such as ComfyUI demands not only syntactic accuracy but also expert-level reasoning over modular compositions. Existing large language model (LLM) approaches often treat this as a direct text-to-JSON generation task, struggling with structural brittleness and lacking the experiential knowledge required for effective design. We argue that successful workflow generation requires modeling knowledge...

    arxiv.org/abs/2607.15845 · PDF

  8. 08

    AgentFAIR: A Multi-Agent Collaborative Framework for FAIRness Evaluation of Geospatial Datasets

    Ming Chen, Pranav Pai

    cs.AI · cs.ET · cs.MA

    Geospatial datasets support applications from urban planning to climate modeling, yet consistent assessment of FAIR compliance is difficult. Existing evaluators use different rubrics and evidence sources and may fail on JavaScript-rendered pages or repository-specific identifiers. For 50 datasets from 10 repositories, the standard deviation of normalized scores across available tools averages 15.0 percentage points and reaches 30.3 for one...

    arxiv.org/abs/2607.15781 · PDF

  9. 09

    NeurOWL: An LLM-Based Neural-symbolic Framework for Incomplete OWL Ontology Reasoning

    Hui Yang, Jiaoyan Chen, Yiping Song, Renate Schmidt, Wen Zhang

    cs.AI

    OWL ontologies provide a formal knowledge representation framework that enables semantic reasoning, and have been widely adopted across domains such as healthcare and bioinformatics. In practice, however, real-world ontologies are often incomplete, which pose challenges for reasoning. In this work, we focus on a fundamental subsumption reasoning problem: given an incomplete ontology and a candidate (non-entailed) subsumption, determine...

    arxiv.org/abs/2607.15776 · PDF

  10. 10

    Behavioral Controllability of Agentic Models for Information Extraction: From Fixed Workflows to Reflective Agents

    Lujia Zhang, Xingzhou Chen, Hongwei Feng

    cs.AI

    Large language model (LLM) agents are increasingly used for complex information-extraction tasks, yet it remains unclear whether agentic components such as reflection and memory lead to observable and controllable improvements over fixed LLM workflows. We study this question through conference-paper dataset extraction, where a system must identify datasets mentioned in scholarly PDFs and produce structured records. We compare a fixed workflow...

    arxiv.org/abs/2607.15715 · PDF

  11. 11

    S1-Omni: A Unified Multimodal Reasoning Model for Scientific Understanding, Prediction, and Generation

    Jiahao Zhao, Junyi Liu, Lifeng Xu, Nan Xu, Qingli Wang, Qingxiao Li, Tianle Chen, Xiaoyu Wu, Yawen Zheng, Zikai...

    cs.AI

    We present S1-Omni, a unified multimodal reasoning model for scientific understanding, prediction, and generation. AI for Science (AI4S) has advanced significantly through domain-specific models, tool-augmented LLMs, and scientific language models. However, model capabilities remain highly fragmented, limiting the joint modeling of heterogeneous data, scientific laws, and expert knowledge. S1-Omni addresses this gap by consolidating these...

    arxiv.org/abs/2607.15686 · PDF

  12. 12

    ToolVerse: Unlocking Massive Environments and Long-Horizon Tasks for Agentic Reinforcement Learning

    Shuaiyu Zhou, Fengpeng Yue, Zengjie Hu, Yuanzhe Shen, Chenyang Zhang, feng hong, Cao Liu, Ke Zeng

    cs.AI

    While LLM agents demonstrate strong reasoning abilities in compact and well-defined scenarios, they struggle to maintain robustness and effectiveness when faced with large-scale, diverse, and dynamic real-world environments that demand seamless tool integration. To address this gap, we introduce ToolVerse, a comprehensive framework that scales up agentic RL environments and enables agents to perform complex long-horizon reasoning in...

    arxiv.org/abs/2607.15660 · PDF

  13. 13

    Neuro-Symbolic AI for LEED compliance: Document-Centric Benchmarking, Deterministic Numeric Checking, and When Multimodal Hurts

    Aritro De, Juliana Felkner

    cs.AI

    LEED v4.1 BD+C certification remains a document-intensive process that requires reviewers to read hundreds of pages of project evidence and apply credit-specific threshold logic by hand. This paper investigates whether small, locally deployed language models can perform meaningful screening of LEED documentation and how deterministic symbolic components should share that work. A neuro-symbolic pipeline is introduced that aligns project PDFs...

    arxiv.org/abs/2607.15647 · PDF

  14. 14

    MGDT: MLLM-Guided Diffusion Transformer with Relation-Adaptive Mixture-of-Experts for Multimodal Knowledge Graph Completion

    Xu Hou, Meiyu Liang, Wei Huang, Yawen Li, Zhe Xue, Wu Liu, Guanhua Ye, Lei Shi, Kangkang Lu

    cs.AI

    Multimodal Knowledge Graph Completion (MKGC) requires inferring missing entities from structural, textual, and visual cues. Existing diffusion-based MKGC methods usually denoise directly on raw multimodal features. Such a design forces the denoiser to simultaneously perform relation-dependent cue selection, cross-modal semantic alignment, and structure-aware entity generation, which introduces noisy and semantically inconsistent conditions...

    arxiv.org/abs/2607.15592 · PDF

  15. 15

    SeerGuard: A Safety Framework for Mobile GUI Agents via World Model Prediction

    Xue Yu, Bo Yuan, Pengshuai Yang, Kailin Zhao, Hong Hu, Junlan Feng

    cs.AI

    Mobile graphical user interface (GUI) agents have demonstrated remarkable capabilities in automating complex tasks, yet they introduce critical safety risks where a single erroneous action can lead to irreversible consequences. Existing safety mechanisms are primarily reactive, lacking the ability to assess risks before execution. In this paper, we introduce SeerGuard, a consequence-aware safety framework designed to mitigate these risks...

    arxiv.org/abs/2607.15550 · PDF

  16. 16

    Logic, Optimization, and Artificial Intelligence

    J. N. Hooker

    cs.AI · math.OC

    Logic and optimization can, in combination, make valuable contributions to rule-based AI. Logic is the obvious medium for encoding a rule base and drawing inferences from it, while optimization provides a powerful technology for computing inferences. Their combination has taken on new relevance amid a growing concern for transparency in AI. which is important for reproducibility, explainability, trustworthiness, and fairness. Rule-based AI...

    arxiv.org/abs/2607.15532 · PDF

  17. 17

    A Critical Analysis of Trustworthy AI Tools, Mark Frameworks, and the Implementation Chasms

    Michael Papademas, Xenia Ziouvelou, Kostas Karpouzis, Vangelis Karkaletsis

    cs.AI

    As artificial intelligence (AI) systems increasingly impact society, ensuring their ethical and trustworthy deployment has become a global priority. While a myriad of high-level ethical guidelines have emerged, criticism persists that these frameworks remain abstract and lack concrete mechanisms for implementation. This paper conducts a critical analysis of tools and trust mark frameworks intended to operationalize trustworthy AI (TAI),...

    arxiv.org/abs/2607.15480 · PDF

  18. 18

    From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems

    Eduardo C. Garrido-Merchán

    cs.AI

    A trained deep reinforcement learning policy is a black box, and we ask whether it can be made explainable by rewriting it as an executable logic program that reproduces its behaviour and that a person can read, a logic engine can run, and an optimizer can edit. We present a three-stage post-hoc transformation that extracts a frozen proximal policy optimization teacher, induces an ordered rule list from its decisions in the manner of...

    arxiv.org/abs/2607.15459 · PDF

  19. 19

    Beyond a Joke: Multi-Angle Reasoning for Detecting and Explaining Harmful Humor in Memes

    Shanhong Liu, Pai Chet Ng, De Wen Soh, Malika Meghjani, Konstantinos N. Plataniotis

    cs.AI

    Internet memes intertwine visual cues, textual content, and cultural context, making them particularly challenging to interpret in scenarios where humor, sarcasm, and harmful intent coexist. These complexities highlight the need for explainable meme understanding systems that can provide reliable and structured reasoning to support both accurate classification and human interpretability. However, existing multimodal classifiers either...

    arxiv.org/abs/2607.15442 · PDF

  20. 20

    Do Coding Agents Need Executable World Models, Simplification, and Verification to Solve ARC-AGI-3?

    Sergey Rodionov

    cs.AI

    Our previous ARC-AGI-3 agent bundled executable world modeling, scheduled simplification, and exact replay verification, leaving unclear which idea accounted for its performance. We address this attribution question with four nested Codex-based agents: a textual baseline; a flexible-interface executable world model without replay verification; the same executable model with scheduled simplification; and a fixed-interface verification...

    arxiv.org/abs/2607.15439 · PDF

  21. 21

    DrawingVQA: A Real-World Benchmark for Multi-Depth Visual-Textual Reasoning on Construction Drawings

    Yoonhwa Jung, Junryu Fu, Mani Golparvar-Fard

    cs.AI · cs.CV

    We introduce DrawingVQA, the first benchmark designed to evaluate multimodal large language models (MLLMs) on real-world construction drawings -- a core media in architecture, civil, and many other engineering practices. Unlike natural images or schematic floor plans, construction drawings fuse abstract geometry, symbolic notation, tabular data, annotations, and domain-specific text, forming a uniquely complex visual-textual domain core to...

    arxiv.org/abs/2607.15418 · PDF

  22. 22

    Precise but Uncoupled: Reviewer Precision Does Not Guarantee Critique Uptake in Multi-Agent Math Reasoning

    Chih-Hsuan Yang, Jingyan Jiang, Vikram Vasudevan, Cheng-Hau Yang, Huihuo Zheng, Le Chen, Eliu A. Huerta, Venkatram...

    cs.AI

    Many math- and science-oriented agent systems use hierarchical designs with specialized reviewer roles, assuming that a dedicated review stage should help turn wrong candidates into correct ones. We test this assumption on 4,181 verifier-grounded Omni-MATH problems using matched gpt-oss-120b actors. Collaboration adds little on the easiest tiers, but from tier 4 onward the gains open sharply; in this harder regime, broadcast-style peer...

    arxiv.org/abs/2607.15388 · PDF

  23. 23

    AnovaX: A Local, Multi-Agent Voice Assistant with LLM Planning, Typed Executors, and Adaptive Recovery

    Raunak B Sinha

    cs.AI

    Desktop voice assistants are still dominated by cloud pipelines that ship raw audio off the machine and expose a fixed set of skills. We describe AnovaX, a small local-first assistant that runs entirely on the user's computer and treats the desktop itself as its action surface. A single Python process wires together a wake-word gate, a speech pipeline, an LLM planner (Gemini) that emits a JSON plan of tool calls, a whitelist-and-denylist...

    arxiv.org/abs/2607.15367 · PDF

  24. 24

    Pretraining Data Can Be Poisoned through Computational Propaganda

    Victoria Graf, Hannaneh Hajishirzi, Noah A. Smith, David Kohlbrenner, Kyle Lo

    cs.AI · cs.CL

    Poisoning pretraining data can introduce harmful behaviors to LMs that are difficult to detect and mitigate. Prior work on poisoning pretraining data has largely exploited established data sources such as Wikipedia, which do not represent the large scale and heterogeneity typical of pretraining corpora, and has ignored the interaction between poisoned data and data curation pipelines. We demonstrate that poisoning attacks on pretraining data...

    arxiv.org/abs/2607.15267 · PDF

  25. 25

    SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration

    Yuyao Zhang, Junjie Gao, Zhengxian Wu, Jiaming Fan, Jin Zhang, Shihan Ma, Yao Yao, Weiran Qi, Chuyan Jin, Guiyu Ma,...

    cs.AI · cs.IR

    Recent advances in Tool-Integrated Large Language Models have made web search a core capability of information-seeking agents. However, as interaction histories grow, agents increasingly struggle to track task progress. When search attempts fail to yield useful evidence, current single- and multi-agent systems can become trapped in repetitive loops, wasting search budgets and ultimately compromising the quality and completeness of the final...

    arxiv.org/abs/2607.15257 · PDF

  26. 26

    teLLMe Why (Ain't Nothing but a Jam): Exploratory Causal Analysis of Urban Driving Data

    Qiwei Li, Jorge Ortiz

    cs.AI · cs.HC

    Traffic agencies now have access to large volumes of video-derived data for studying safety and congestion. Most of these data are observational and collected without interventions, which makes causal questions such as "How would rain change traffic density?" difficult to answer. We present teLLMe, a system for exploratory causal analysis of urban driving datasets. The system starts from a structured event table built from dashcam annotations...

    arxiv.org/abs/2607.15254 · PDF

  27. 27

    AutoSynthesis: An agentic system for automated meta-analysis

    Moein Taherinezhad, Sebastian Maier, Gerardo Vitagliano, Francesco Pierri, Stefan Feuerriegel

    cs.AI

    Evidence synthesis is crucial for turning primary research into reliable knowledge for science, medicine, education, and policy. Yet, quantitative evidence synthesis remains largely manual and difficult to scale. Here, we introduce AutoSynthesis, an end-to-end multi-agent system for automated meta-analysis. Given a research question in natural language, AutoSynthesis formulates a search strategy, retrieves scientific literature, screens...

    arxiv.org/abs/2607.15247 · PDF

  28. 28

    When Words Are Safe But Actions Kill: Probing Physical Danger Beyond Text Safety in Hidden-State Risk Space

    Weimeng Wang, Ziqiang Wang, Zihang Zhan, Chuanpu Fu, Qi Li, Ke Xu

    cs.AI · cs.CR

    Large language models (LLMs) increasingly serve as high-level planners for embodied agents, where linguistically benign instructions can become unsafe once grounded in the physical world. We study whether this physically grounded danger is the same safety problem as ordinary text-level content danger. Through hidden-state direction analysis and random-split null tests, we show that content danger (CD) and physical danger (PD) form separable...

    arxiv.org/abs/2607.15218 · PDF

This edition is part of The Daily Abstract — cs.AI archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.