cs.AI · 2026-09-25 · No. 124

Artificial Intelligence, 2026-09-25.

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

01 — The papers

50 entries
  1. 01

    AD-WM: Action-Discriminative World Models for Counterfactual Model Predictive Control

    Jiabin Qiu, Zixuan Chen, Hongye Cao, Jieqi Shi, Jing Huo, Yang Gao

    cs.AI · cs.RO

    Latent world models are typically trained to predict factual transitions, whereas model predictive control (MPC) must compare alternative actions from the same state. A model can therefore achieve low factual prediction error yet poorly distinguish candidate actions. We introduce AD-WM, an action-discriminative joint-embedding world model for counterfactual MPC. AD-WM combines residual latent dynamics with predictor-level action-recovery...

    arxiv.org/abs/2609.30264 · PDF

  2. 02

    A Living Benchmark for Information Retrieval from Electronic Health Records

    Jordan L. Cahoon, Chloe O. Stanwyck, Sulaiman Somani, Philip Chung, Kevin R Keet, Kameron C. Black, Andrea T....

    cs.AI

    Large language model (LLM)-based clinical assistants are increasingly being integrated into electronic health record (EHR) systems, transforming how clinicians retrieve and synthesize information from patient records. Their safety and utility depend on rigorous evaluation, yet existing benchmarks are manually curated, costly to update, and rapidly become obsolete with evolving technological advancements. We present a scalable framework that...

    arxiv.org/abs/2609.30205 · PDF

  3. 03

    ExplorationBench: Measuring AI Systems' Exploration in Verifiable Alien Worlds

    Ming Zhang, Zhenghao Xiang, Peizhong Gao, Yujiong Shen, Yuhui Wang, Zhonghan Yue, Shihan Dou, Zhangyue Yin, Junjie...

    cs.AI · cs.CL

    Scientific discovery begins where known problems end. There, AI systems must engage in exploration: framing hypotheses, designing experiments, and iterating on the results. However, evaluating this ability is difficult: (1) how to verify whether a genuinely new hypothesis holds, and (2) how to determine whether a system has discovered it through exploration or merely recalled related knowledge from pre-training data. To this end, we introduce...

    arxiv.org/abs/2609.30199 · PDF

  4. 04

    SAGE: Mitigating Long-Horizon Reasoning Biases via Topological Guidance

    Xinyue Zeng, Jiawei Zhang, Yujun Yan, Dawei Zhou

    cs.AI

    Long-horizon reasoning remains a central challenge for large language models (LLMs) under sparse-reward regimes. We argue that this brittleness arises from two biases induced by complex reasoning spaces: an exploration bias, where models are drawn toward locally plausible but structurally unstable branches, and a compounding bias, where small local deviations accumulate across depth and suppress rare rewards. We introduce Symbolic Closure...

    arxiv.org/abs/2609.30192 · PDF

  5. 05

    Jev-Mobile: Jev as an Executor for Mobile GUI Agents

    Linghua Zhang

    cs.AI · cs.SE

    Vision-language models (VLMs) have become a common foundation for autonomous mobile GUI agents, but most existing systems rely on the VLM for both planning and action grounding at nearly every interaction step, leading to substantial latency and model-serving cost. We introduce Jev-Mobile, which shifts this paradigm to low-frequency VLM planning and high-frequency lightweight execution: the VLM specifies local goals, the accessibility tree...

    arxiv.org/abs/2609.30186 · PDF

  6. 06

    Search-Aware Reinforcement Learning for Multi-Component Query Understanding in Roblox Game Search

    Nayoung Choi, Shengjian Chen, Xiaokai Wei, Wenzheng Zhang, Daiyao Yi, Rachit Pareek, Vincent Su, Michelle Gong, Jinho D. Choi

    cs.AI

    Query understanding (QU) plays a critical role in production search systems, translating raw user queries into search execution plans that drive downstream retrieval and ranking. While large language models (LLMs) have enabled QU to be framed as a structured multi-task generation problem (e.g., intent classification, query expansion), optimizing such models to produce search-engine-coupled outputs remains challenging: static, label-based...

    arxiv.org/abs/2609.30177 · PDF

  7. 07

    GRASP: Generating, Revising, and Assessing for Strategic Planning with Agentic AI

    Arunabh Srivastava, Mohammad A., Khojastepour, Srimat Chakradhar, Sennur Ulukus

    cs.AI · cs.CL · cs.LG · cs.MA

    Large Language Models (LLMs) typically exhibit a performance profile where reliability degrades as task complexity increases. We address the challenge of generating high-quality natural language executable plans for complex tasks by introducing $\textbf{GRASP}$, a strategy-aware, multi-stage planning framework. GRASP decouples the planning pipeline across specialized, context-isolated modules: it pre-compiles global macro-guidelines...

    arxiv.org/abs/2609.30147 · PDF

  8. 08

    EnigmaForge: The Question Is Hidden in the Story

    Daniel Eisner

    cs.AI

    Most benchmarks hand the model a question. EnigmaForge hands it a stack of old documents and no question at all. Buried in the letters, receipts, and logbook margins is a small logic puzzle whose solution is unique - proved by a SAT solver at generation time, with an ablation certificate showing every clue is load-bearing. Because instances are generated rather than collected, the corpus renews forever. The headline measure is intuition: task...

    arxiv.org/abs/2609.30144 · PDF

  9. 09

    Screen Before You Serve: Simulation for Production Customer Experience AI Agents at 140M Scale

    Edesio Alcoba, Kevin Rossell, Aman Gupta, Shao Tang, Jiwoo Hong, Pabel Carrillo-Mendoza, Wanderson Conceição...

    cs.AI · cs.CL

    Customer experience (CX) agents use tools and large language models to address customer requests and guide conversational interactions with an organization's products. Improving these agents, especially in regulated industries, is difficult: they must detect intent, follow complex operational policies and use tools reliably. Manual end-to-end testing offers limited coverage, while live experiments expose customers to failures that can erode...

    arxiv.org/abs/2609.30137 · PDF

  10. 10

    HEXIS: Compiling Skills into Extended Finite State Machines

    Minghao LI

    cs.AI

    Agent skills provide reusable knowledge and instructions, yet agents must repeatedly infer how to apply them and which operation should follow. This couples task reasoning with control decisions, allowing prescribed steps to be omitted or applied incorrectly. We introduce HEXIS, which compiles agent skills into extended finite state machines that separate knowledge from control flow. Skill knowledge is incorporated into local instructions...

    arxiv.org/abs/2609.30123 · PDF

  11. 11

    PrivDrift: Auditing User-Secret Leakage Under Topic Drift in Active LLM Conversations

    Luciano Maldonado

    cs.AI · cs.CL · cs.CR

    Large language models increasingly operate as persistent assistants in user-facing, shared-session, and tool-augmented settings. When users disclose sensitive information during an active conversation, that information may remain behaviorally recoverable through later prompts even after the dialogue shifts to unrelated topics. We introduce \textbf{PrivDrift}, a benchmark for auditing whether user-disclosed secrets remain recoverable after...

    arxiv.org/abs/2609.30094 · PDF

  12. 12

    Self-Play Pretraining with Zero Data

    Aditya Cowsik, Kfir Dolev, Michael Y. Li, G. Bruno De Luca, Nourya Cohen, Noah D. Goodman, Yoav Levine

    cs.AI · cs.CL

    Advances in language modeling have been driven by scaling pretraining on ever more data. Yet, the training data is still largely curated on the model's behalf. A more general approach to pretraining would let the model learn to generate the data most useful for its own improvement. This would provide an effectively unbounded source of training data, limited by compute rather than human knowledge. We introduce Self-Play Pretraining with Zero...

    arxiv.org/abs/2609.30063 · PDF

  13. 13

    SciWalker: Synthesizing Scientific Coding Problems with Operator Graphs and Execution Feedback

    Chenxi Li, Wenxuan Zeng, Yun Luo, Fangchen Yu, Peng Ye, Yu Cheng, Jun Zhang

    cs.AI

    Improving the scientific coding capabilities of large language models (LLMs) requires high-quality training data. However, such data remain scarce because manually authoring realistic problems is costly and time-consuming, while systematically covering diverse scientific domains and algorithmic combinations remains challenging. To address this, we introduce SciWalker, a framework for synthesizing scientific coding problems through...

    arxiv.org/abs/2609.30054 · PDF

  14. 14

    NNV3: Expanding Neural Network Verification to New Architectures and Domains

    Anne M. Tumlin, Samuel Sasaki, Ben Wooding, Diego Manzanas Lopez, Muhammad Usama Zubair, Navid Hashemi, Hongchao...

    cs.AI

    We present NNV3, the latest version of the Neural Network Verification (NNV) tool, a MATLAB framework for formal verification of deep learning models and learning-enabled cyber-physical systems. Building on the set-based reachability foundation of NNV 1.0 (FFNNs, CNNs, NNCS) and NNV 2.0 (RNNs, SSNNs, neural ODEs), NNV3 introduces new members of the Star-set family: ModelStar for verifying networks under weight perturbation, VolumeStar for...

    arxiv.org/abs/2609.30050 · PDF

  15. 15

    Style, Not Self: Surface Cues Explain Zero-Shot Code Attribution by Large Language Models

    Ehsan Barkhordar, Surendrabikram Thapa

    cs.AI · cs.CL · cs.SE

    If a language model can recognize code it wrote, it may favor that code as a judge, and instances of one model monitoring each other could collude. We test this zero-shot on current commercial models. Five LLMs generate solutions to MBPP, HumanEval, and DS-1000, seven more to MBPP, and models act as evaluators in four tasks: picking their own solution from a pair, judging whether a single solution is their own, identifying which of two...

    arxiv.org/abs/2609.30048 · PDF

  16. 16

    How does Adversarial Influence Scale in Multi-Agent Systems?

    Addison J. Wu, Jasin Cekinmez, Michel Liao, Karthik Narasimhan, Thomas L. Griffiths

    cs.AI · cs.CY

    Multi-agent deliberation can improve performance, but what happens when some agents do not act in good faith? In practice, an agent may be deceptive and work to subvert the group, whether through its own objectives or external instruction. We study how susceptibility to deception scales as groups increase in size and deceivers become more prevalent. It is not the number of agents in the group that matters, but the proportion of deceivers. We...

    arxiv.org/abs/2609.30028 · PDF

  17. 17

    Synthetic Hospital: An Open, Verifiable, Physician-Validated Longitudinal EHR Benchmark

    Christine Park, Valerie Chen, Tim Dettmers

    cs.AI · cs.DB

    Frontier language models are rarely used in clinical workflows because the realistic, longitudinal benchmarks needed to develop them are scarce. Real electronic health record (EHR) data cannot be openly shared due to privacy, ethics or data use issues and it does not contain verifiable ground truth since the chart records only reflect what clinicians documented. We introduce Synthetic Hospital, an open, fully synthetic, fact-grounded...

    arxiv.org/abs/2609.30027 · PDF

  18. 18

    Advancing Model Research in AgentX: Long-Horizon Autonomy for Industrial Recommender Systems

    Shuang Yang, Zijie Zhuang, Changxin Lao, Pengbo Xu, Hanwen Xu, Yusheng Huang, Han Gao, Guanchen Wang, Tianbao Ma,...

    cs.AI · cs.IR

    Sustaining industrial recommendation research requires using the results of one experiment to decide what to investigate next. We present AgentX-Model, the next generation of AgentX's model research framework, which connects proposal development and model experimentation within sandboxes defined by business inputs and prediction tasks. AgentX-Model adopts a dual-agent architecture comprising a Research Agent and a Model Agent. The Research...

    arxiv.org/abs/2609.30001 · PDF

  19. 19

    Augur: A Synthetic Decision Lab for Rehearsing Reactions to Product and Policy Changes

    Rahul Khedar, Mayank Malhotra, Avinash Karn

    cs.AI · cs.CL · cs.MA

    Before a product or policy change ships, the question that matters is how people will react to it. Augur rehearses that reaction offline: it builds a typed knowledge graph from the change documents, populates a grounded persona market, simulates the interaction, and returns an auditable decision memo recommending one of five actions. We assemble Gold-50, fifty real product and policy episodes whose real-world outcome is known, adjudicated...

    arxiv.org/abs/2609.29952 · PDF

  20. 20

    ENDOPROMPT: Victim-Side Pseudo-References for Utility Degradation

    Qingyu Wu, Zeyu Feng, Yongda Yu, Yuzhe Luo, Hua Cheng

    cs.AI · cs.CR

    Prompt injection can degrade benign task performance without eliciting harmful content. Yet many attack objectives depend on task labels or predefined target responses. We present ENDOPROMPT, a white-box method that learns utility-degrading prefixes from unlabeled instructions. Its generator takes the request text as input. Clean victim continuations serve as pseudo-references: local search identifies prefixes that reduce continuation...

    arxiv.org/abs/2609.29948 · PDF

  21. 21

    Neuro-symbolic AI for Industrial Configuration

    Danilo Valerio, Philipp Kogler, Stefan Bischof, Thomas Hubauer, Huzefa Rangwala

    cs.AI

    Large Language Models (LLMs) have shown impressive performance on a wide range of generative tasks. Yet their probabilistic nature makes them, in isolation, fundamentally unsuited for industrial product configuration, where outputs must be syntactically valid, semantically consistent with a knowledge base of hundreds of features and rules, and producible by an existing manufacturing chain. We argue that Neuro-symbolic (NeSy) AI methods lay...

    arxiv.org/abs/2609.29947 · PDF

  22. 22

    Who Holds the Pen? Let Specifications, Not Agents, Sign Off

    Haiqing Li, Xin Ma, Yinhao Wu, Wenliang Zhong, Feng Jiang, Thao M. Dang, Xiao Hu, Hehuan Ma, Yuzhi Guo, Junzhou Huang

    cs.AI · cs.MA

    Large language model agents increasingly combine generation, decision-making, execution, and self-evaluation within a single agentic loop. Although they operate under external specifications such as task instructions, guidelines, output schemas, and reusable skills, these specifications typically remain context for the same model that acts and declares completion, leaving no independent specification authority boundary. We identify two...

    arxiv.org/abs/2609.29921 · PDF

  23. 23

    Qwen-Planner-Agent: A Closed-Loop AI-for-AI Framework for Real-World Mobile Planner Agents

    Tingyu Qu, Weigao Sun, Yuecheng Liu, Yucheng Zhao, Yi Zhu, Yifeng Ding, Qiyi Wang, Sihan Cao, Pengkun Jiao, Hanlei...

    cs.AI

    The rapid progression of large language models is extending AI from passive content generation into the active workflows of engineering and scientific discovery. This shift raises a compelling question: can AI be both the object of development and an active participant in building next-generation AI systems? We explore this question by building Qwen-Planner-Agent within a closed-loop AI-for-AI framework for scalable development and iterative...

    arxiv.org/abs/2609.29892 · PDF

  24. 24

    Ontology-Mediated Neurosymbolic Constraint Acquisition from Multiple Stakeholders

    Stefan Bischof, Juliana Kainz, Danilo Valerio

    cs.AI

    Neurosymbolic research typically assumes a pre-existing symbolic specification, leaving the upstream challenge of acquiring and formalizing requirements and constraints largely unaddressed. We present an architecture that fills this gap by using an OWL configuration ontology to mediate between neural constraint sources and downstream consumers. In this framework, LLM assistants elicit soft stakeholder preferences, while hardware...

    arxiv.org/abs/2609.29876 · PDF

  25. 25

    When Can Agents Forget Their Reasoning? ICLR for Long-Horizon Agent Context Compression

    Mingxuan Wang, Fei Luo, Bo Wang, Guorun Yao, Yinglong Guo, Chao Ning, Hongyue Chen, Yanbiao Ma, Jungong Han

    cs.AI · cs.CV

    Long horizon language model agents continually accumulate reasoning history, increasing context length and inference cost even after earlier decisions have been executed and observed. Unlike static Chain of Thought compression, removing historical reasoning can change future actions and the resulting interaction trajectory. We study when such reasoning can be safely forgotten. We propose Interaction Aware Compression for Long Horizon...

    arxiv.org/abs/2609.29875 · PDF

  26. 26

    A Risk-Adaptive and Evidence-Constrained Framework for Generative AI Feedback in Programming Education

    Shihao Wang

    cs.AI

    Generative artificial intelligence can turn learning analytics into personalized support, but feedback systems must decide when to intervene, which evidence to use, and how much assistance to provide. We developed a risk-adaptive, evidence-constrained framework for introductory programming using 2993 failed-submission states from 215 students. Student-disjoint models predicted persistent failure and related outcomes; four matched feedback...

    arxiv.org/abs/2609.29874 · PDF

  27. 27

    PUBG Ally: A Conversational Embodied Agent as an AI Teammate

    Beomsoo Kim, Byeongju Kim, Dohyun Kim, Dongwon Kim, Eunchong Kim, Hongmin Kim, Hyeojung Im, Hyeonbin Hwang,...

    cs.AI · cs.CL · cs.HC

    We introduce PUBG Ally, an embodied agent for PUBG: BATTLEGROUNDS that can reason, act autonomously, and play alongside players as a voice-enabled teammate. Building such a teammate requires combining two difficult capabilities: it must perceive and respond to a constantly changing game world under strict latency constraints while interacting naturally with players, keeping its speech synchronized with its actions. Ally therefore combines...

    arxiv.org/abs/2609.29837 · PDF

  28. 28

    Decoding Imagined Speech: A Strictly Subject-Independent Approach Using EEG

    Frederik Møllskov Trier, Xiaopeng Mao, Sadasivan Puthusserypady

    cs.AI

    Imagined speech decoding from electroencephalography (EEG) has gained increasing attention as a potential communication pathway for individuals with severe motor impairments, yet reported performance often relies on evaluation protocols that do not clearly reflect cross-subject generalization. This study presents a transparent baseline investigation of a multi-class imagined speech EEG dataset under a strictly subject-independent evaluation...

    arxiv.org/abs/2609.29820 · PDF

  29. 29

    Learning to Ideate for Scientific Impact

    Shubham Kale, Aniketh Garikaparthi, Manasi Patwardhan

    cs.AI · cs.CL

    Scientific ideation is increasingly mediated by large language models, but current ideation systems are usually trained and evaluated on immediately judgeable proxies such as novelty, clarity, and feasibility. This leaves open whether delayed signals of scientific uptake can be used as feedback for steering models toward research directions with higher expected \emph{impact}. We study this question using citation-normalized impact as a noisy...

    arxiv.org/abs/2609.29802 · PDF

  30. 30

    Hallucination Neurons and Where to Find Them: An Investigation into the existence of Hallucination Neurons

    Huseyin Cavus, Sebin Sabu, Joshua Spear, Jaskaran Singh Kawatra, Pavithra Rajendran

    cs.AI

    Interpretable machine learning for Large Language Models (LLMs) increasingly relies on sparse probing methods that identify small sets of neurons claimed to detect and causally influence behaviors such as factuality recall, safety alignment, and hallucination. These claims have important implications for model auditing and behavioral steering, yet they are rarely tested against known failure modes of $L_1$-regularized probing in correlated,...

    arxiv.org/abs/2609.29781 · PDF

  31. 31

    Breaking the Environment Wall: Evolving LLM Agent Environments for Recursive Self-Improvement

    Yukai Wu, Yuanjing Yang, Le Zhou, Shaokun Han, Haoyu Wang, Zirui Tang, Weihuang Zheng, Maxm Pan, Xuanhe Zhou, Fan Wu

    cs.AI

    Many real-world tasks (e.g., office workflows, scientific experimentation) require LLM agents to interact repeatedly with their environments for context-dependent operations. However, such environments are often not agent-ready. First, information is often scattered and fragmented across the environment. Second, relevant evidence in the environment is often mixed with misleading information and conflicting versions. Third, environments evolve...

    arxiv.org/abs/2609.29773 · PDF

  32. 32

    AI-based detection of worsening heart failure from low-resolution telemonitoring data

    Erik Aerts, Yinan Yu, Annika Rosengren, Michael Fu, Martin Lindgren, Falk Dippel, Martin Adiels, Helen Sjöland

    cs.AI

    Objective: Heart failure (HF) presents a healthcare challenge due to its high comorbidity burden, aging patient population and frequent hospitalizations. Remote monitoring offers a promising approach to managing HF patients by early detection of health deterioration. Developing autonomous systems to detect signs of worsening in telemonitoring data is of interest to reduce the workload of healthcare personnel. Methods: We propose the TRACER...

    arxiv.org/abs/2609.29742 · PDF

  33. 33

    C3M: Cross-Session Multimodal Memory Maintenance for Long-Horizon Tasks

    Xueshu Chen, Yan Wang, Zihao Xue, Jiefu Li, Zhenfang Liu, Jayden Chen, Zhen Bi, Jungang Lou

    cs.AI · cs.CL · cs.CV · cs.IR

    Long-horizon tasks require preserving and later recovering cross-session evidence under a bounded, query-blind memory budget. Existing compression can discard fine-grained visual cues or conflate semantically similar but incompatible observations. We present C3M, a cross-session multimodal memory organization that maintains a bounded active index over persistent source text-image evidence. Relation-aware updates consolidate safe redundancy...

    arxiv.org/abs/2609.29735 · PDF

  34. 34

    The Gold in Bias: Maturing the AI Design Process through Verification

    Samira Maghool, Paolo Ceravolo

    cs.AI

    Bias in AI systems is typically framed as a flaw to be minimized, yet it also serves as a critical indicator of underlying weaknesses in data, modeling assumptions, and system design. Existing approaches often treat bias as an isolated problem rather than as evidence that can strengthen verification and governance across the AI lifecycle. This paper aims to reconceptualize bias as a diagnostic tool that supports rigorous AI verification. We...

    arxiv.org/abs/2609.29730 · PDF

  35. 35

    A General Framework for Budgeted Threshold Incentives on Request

    Zhuolin Wu, Chengrui Zhu, Wenhua Nie, Kenny Ye Liang, Junming Lin, Haiyang Li, Zhilin Li, Wenjia Geng, Zeyu Wu,...

    cs.AI

    On-demand delivery platforms pay riders through incentive activities whose tiers are set from recent completions of riders with a similar history. Operators request such plans for changing periods, rider populations, payment rules and budgets, often for holidays or bad weather, where randomized trials are scarce and take months to collect. We present a request-driven framework that composes four stages (conditional prediction, population...

    arxiv.org/abs/2609.29724 · PDF

  36. 36

    SWE-Prometheus: Measuring Engineering Governance Improvements in Real-World Repositories

    Jiajun Wu, Leixin Sun, Zihan Tan, Yitao Liu, Shuo Li, Jiaru Qian, Shanghaoran Quan, Chuangxin Zhao, Yangxu Liao,...

    cs.AI · cs.SE

    Large language model based coding agents have made substantial progress on repository-level software engineering tasks. Existing repository benchmarks, however, usually start from a human-identified issue and evaluate whether a patch satisfies a functional signal. We present SWE-Prometheus, a benchmark for the broader task of improving repository engineering governance. Each task provides a fixed snapshot and an open-ended objective,...

    arxiv.org/abs/2609.29465 · PDF

  37. 37

    Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures

    Ruoqi Guo, Yi Liu, Gelei Deng, Yuekang Li, Lida Zhao, Yutao Wu, Simin Chen, Ying Zhang, Leo Yu Zhang

    cs.AI · cs.CL · cs.CR

    Detectors of alignment failures screen deployed language models and score alignment benchmarks. Most are generative judges that spend a decoding pass on every criterion, and classifiers that read token probabilities, such as Llama Guard, still score one fixed label per call. Jev, a model trained with reinforcement learning for calibrated decisions (RLCD), answers many typed questions about one input with calibrated probabilities in a single...

    arxiv.org/abs/2609.29429 · PDF

  38. 38

    RD-JEPA: Predictive latent pretraining for few-trajectory transfer across reaction--diffusion equations

    Chenhao Si, Ming Yan

    cs.AI · cs.LG

    Learning surrogates for time-dependent partial differential equations often requires a new simulation corpus when the governing operator changes. We introduce RD-JEPA, a joint-embedding predictive architecture for self-supervised pretraining on reaction-diffusion trajectories. A single model is pretrained on five parameterized systems and then adapted to three held-out systems whose reaction operators and trajectories are excluded from...

    arxiv.org/abs/2609.29403 · PDF

  39. 39

    Wearable ECG Quality Assessment: A Deep Learning and Ambulatory Context-Awareness Approach

    Xiaopeng Mao, Marike Weisbjerg, Sadasivan Puthusserypady

    cs.AI · eess.SP

    This paper presents and evaluates a Deep Learning-based (DL-based) Signal Quality Assessment (SQA) model to distinguish between clean and noisy ambulatory Electrocardiograms (ECG). The model is trained on Copenhagen Center for Health Technology-Contextualized Arrhythmia Database (CACHET-CADB), which, to the best of our knowledge, is the first ambulatory ECG database with both physical and patient-reported contextual data. The model shows...

    arxiv.org/abs/2609.29396 · PDF

  40. 40

    An auditable conditional-strategy framework for open-ended decision-making in complex lung cancer

    Daoyun Wang, Zhicheng Huang, Huaiyuan Sun, Jiaqi Xu, Xiaowei Xu, Zhibo Zheng, Zhongxing Bing, Yuxiao Lin, Yicheng...

    cs.AI

    Complex lung cancer decisions can involve several defensible pathways whose eligibility, sequencing and safety depend on unresolved information. Effective support must make explicit how patient conditions govern pathway eligibility, deferral and redirection. MedGPT Clinical Explorer (MCE) organizes alternatives, decision-changing unknowns, safety constraints and fallback into a conditional strategy for clinician review. To evaluate this...

    arxiv.org/abs/2609.29381 · PDF

  41. 41

    Epistemic-Probabilistic Model for Guarded Multi-Agent LLM Coordination

    Mehdi Nasiri, Mohammad Saeed Arvenaghi, Sadegh Vaezi, Ebrahim Ardeshir-Larijani

    cs.AI

    Multi-agent large language models (LLMs) have become ubiquitous in applied AI, yet their theoretical foundations remain surprisingly understudied. Viewed through the lens of multi-agent systems theory, several shortcomings come to light: a lack of social intelligence, the absence of coordination mechanisms among agents, unknown emergent behavior, and interactions between agents that are bounded by natural language. We address two of these...

    arxiv.org/abs/2609.29366 · PDF

  42. 42

    Beyond Simple Input-Output Assessment Tasks: Leveraging Automated Programming Assessment for Non-Trivial Courses

    Artur Jordao

    cs.AI

    The public visibility of Artificial Intelligence (AI) is growing rapidly, driven by the positive impact of its applications across diverse fields of knowledge. In this new chapter, courses that cover the foundations of AI and machine learning become essential for understanding their role and potential in contemporary society. Therefore, understanding fundamental concepts and elementary algorithms through the close integration of theory with...

    arxiv.org/abs/2609.29363 · PDF

  43. 43

    The Last Human Gate: Forward Deployed Engineering for Governance Automation

    Jeremy Canale

    cs.AI · cs.SE

    Enterprise governance requires decisions, evidence, and accountable authority; it does not require every review task to retain its current human implementation. We develop a task-substitution framework for Digital Governance Frameworks (DGF), treating each gate as an executable contract. Substitution requires sufficient accessible information, valid decision and authority checks, and a reduction in total human work after exceptions,...

    arxiv.org/abs/2609.29345 · PDF

  44. 44

    SkinAgent AI: A Safety-Grounded Multimodal Agentic Framework for Non-Diagnostic Skincare Support

    Muhammad Muhtasim Shahriar, Abdullah Mohammad Sayem, Tze Hui Liew, M. F. Mridha, Md. Mahiuddin

    cs.AI

    Consumer-facing skincare AI must coordinate visual evidence, product information, tool use, and user-facing actions within explicit evidence and safety boundaries. This study evaluates SkinAgent AI, a non-diagnostic multimodal framework that combines visual concern routing with grounded and auditable LLM-based orchestration. The architecture includes routing for Acne, Pores, and Wrinkles; photograph-based skin-type estimation; count-informed...

    arxiv.org/abs/2609.29341 · PDF

  45. 45

    When No One Owns the Judgment: Accountability Under Contribution Dissolution in Human-AI Collaboration

    Hengzhi Ye

    cs.AI · cs.HC

    Communities often respond to potentially AI-assisted work by asking three questions: Was AI used? Was that use disclosed? Can hidden use be detected? These questions place AI use itself at the center of accountability while overlooking a deeper problem: unowned judgment. Evaluations, claims, decisions, and creative directions can be shaped by AI with no accountable human or institution prepared to stand behind them. We develop this argument...

    arxiv.org/abs/2609.29312 · PDF

  46. 46

    From Text Decisions to Pixels: An Study of Jev-Style Visual Choice Model

    Xunlan Zhou, Xianliang Yang, Li Zhao

    cs.AI · cs.LG

    Visual software often needs a decision over supplied alternatives rather than a generated explanation. We present PixelJev, a native-image decision interface that maps an image, a task instruction, and a runtime candidate set to a structured choice and candidate-conditioned probabilities using small open multimodal models. Its initial realization unifies recognition and multiplechoice visual question answering through an existing...

    arxiv.org/abs/2609.29283 · PDF

  47. 47

    ALOE: Semantically Addressed Low-Rank Operators for Knowledge Editing

    Zeyan Li, Hu Xu, Jianfeng Xu

    cs.AI

    Knowledge editing changes what a model knows by modifying parameters so that a requested fact updates while unrelated behavior is preserved. This is usually treated as a write problem, but editing also involves an address problem: deciding which hidden states should receive the new residual. An update that activates too narrowly memorizes one prompt, while one that activates too broadly disrupts neighboring knowledge. Parametric editors...

    arxiv.org/abs/2609.29269 · PDF

  48. 48

    Baszta: Data-Centric Fine-Tuning of a Polish Multi-Label Safety Classifier

    Adam Górski, Mateusz Jąkalak, Rafał Jakubowski

    cs.AI

    We develop a multi-label Polish content-safety classifier by fine-tuning allegro/herbert-base-cased (124M) across five categories (hate, vulgarity, sexual content, crime, self-harm) using a Focal + R-Drop objective, and evaluate the resulting model against Bielik Guard (Sójka) on the shared out-of-distribution Gadzi Język benchmark. Both systems are given per-category threshold tuning on the same calibration split. Under that matched protocol...

    arxiv.org/abs/2609.29266 · PDF

  49. 49

    Policy as Code: A Coroutine-Bridge Harness for Fast-Reasoning Reliability on CAR-bench

    Ivan Matveev

    cs.AI · cs.CL

    CAR-bench evaluates whether tool-using agents stay reliable under real-world uncertainty, executing every tool inside the evaluator so that each tool-result exchange is a separate agent round-trip. A conventional next-action agent can batch parallel tool calls, but a chain of dependent calls costs it one model call per round of results. We present a coroutine-bridge harness in which the model's only action is to emit a Python program that...

    arxiv.org/abs/2609.29251 · PDF

  50. 50

    Towards An LLM-Driven Unified Conversion Framework for BT and FSM in Autonomous Intelligent Systems

    Zhang Qi, Yang Shuo, Zhu Zhengqiu, Zhou Peng, Jiao Peng

    cs.AI

    Finite state machine (FSM) and behavior trees (BT) are widely adopted behavioral modeling paradigms for autonomous intelligent systems. While functionally equivalent and inter-convertible in principle, existing transformation methods between FSM and BT face major challenges in preserving behavioral completeness and avoiding model complexity explosion. To overcome these issues, we propose an LLM-driven unified conversion framework that enables...

    arxiv.org/abs/2609.29228 · 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.