cs.AI · 2026-09-01 · No. 102

Artificial Intelligence, 2026-09-01.

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

01 — The papers

45 entries
  1. 01

    OntoAligner-Ensemble: Voting-Based Fusion across Heterogeneous Ontology Alignment Techniques

    Hamed Babaei Giglou, Sören Auer, Peio Popov, Mahsa Sanaei, Jennifer D'Souza

    cs.AI

    Ontology alignment (OA) has evolved through several methodological paradigms, ranging from lexical and structural aligners to knowledge graph embedding (KGE) models and, more recently, Large Language Model (LLM)-based approaches. Although modern OA frameworks provide unified ecosystems for deploying these heterogeneous aligners, mechanisms for systematically reconciling their complementary and sometimes conflicting predictions remain...

    arxiv.org/abs/2608.31137 · PDF

  2. 02

    When Does Bigger Help? A Controlled Study of LLM Scale for Ontology Learning

    Hamed Babaei Giglou, Sören Auer, Jennifer D'Souza

    cs.AI

    The effect of Large Language Model (LLM) scale on ontology learning (OL) performance remains insufficiently characterized. We present a controlled evaluation of 13 models spanning dense and Mixture-of-Experts variants from the Qwen3.5 and Qwen3.6 lineages, together with proprietary GPT release variants, using the OntoLearner retrieval-augmented generation pipeline. All models are evaluated with the same embedding model, retrieval...

    arxiv.org/abs/2608.31118 · PDF

  3. 03

    BLOOM-WILT: Logit Tilting for Behaviour Elicitation in Automated LLM Auditing

    Adrians Skapars, Edoardo Manino

    cs.AI · cs.CL

    Users of a deployed language model routinely encounter behaviours that testing almost never surfaces, since deployment puts the model through orders of magnitude more interactions than any evaluation can simulate. Automated auditors make testing cheap to scale and flexible enough to cover almost any specified behaviour, yet their lack of optimisation pressure makes them sample-inefficient. To address this shortcoming, we introduce BLOOM-WILT,...

    arxiv.org/abs/2608.31105 · PDF

  4. 04

    Cross-Regional Grapevine Cold Hardiness Prediction via Learned Multimodal Latent Representations

    William Solow, Paola Pesantez-Cabrera, Markus Keller, Lav Khot, Sandhya Saisubramanian, Alan Fern

    cs.AI

    Accurate daily predictions of cold hardiness in woody plants are critical in regions where freezing temperatures can damage dormant buds and reduce seasonal yield. Existing biophysical, hybrid, and deep learning models have shown high predictive accuracy when trained on local data but remain largely site-specific. The limited availability of cold hardiness data, coupled with the lack of principled methods for transferring cold hardiness...

    arxiv.org/abs/2608.31097 · PDF

  5. 05

    Token-Efficient Data Reasoning Agents via Adaptive Structuring of Unstructured Data

    Milad Rezaei Hajidehi, Qitong Wang, Stratos Idreos

    cs.AI · cs.CL · cs.DB

    Valuable data remains embedded in unstructured sources: web pages, reports, contracts, filings, earnings calls, and PDFs. The big bet in enterprise AI is deploying LLM agents that reason over this data to answer complex questions for every knowledge worker. Agents can do this today, but at prohibitive cost. Each question repeatedly opens large documents to recover scattered evidence, consuming up to a million tokens. However, if the data were...

    arxiv.org/abs/2608.31082 · PDF

  6. 06

    Reconciling Process Supervision with Outcome-Based Credit in Agentic Policy Optimization

    Jingxiao Yang, Wangjie Gan, Yingxuan Zhuang, Wenqi Zhang, Jintao Chen, Xuhong Zhang

    cs.AI

    Outcome-based reinforcement learning provides verified feedback for language-model agents, but assigns trajectory-level advantage uniformly to all decisions, yielding coarse credit over long-horizon interactions. On-policy self-distillation offers finer supervision by re-evaluating sampled behavior with privileged information (PI) available only during training. However, fine-grained supervision is not necessarily fine-grained credit:...

    arxiv.org/abs/2608.31077 · PDF

  7. 07

    Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence

    Zhiqin Yang, Jingwen Fu, Yuhan Liu, Hengyu Liu, Yonggang Zhang, Kainan Cao, Zizhuo Zhang, Chenxin Li, Ruibin Yuan,...

    cs.AI

    Recent advances in large reasoning models (LRMs) have shown that reinforcement learning with verifiable rewards (RLVR) can substantially improve reasoning in mathematics and code, where outcomes can be checked automatically. Extending this progress to open-ended and agentic tasks remains difficult because reliable rewards are harder to obtain and direct human supervision cannot keep pace with the scale and complexity of model-generated...

    arxiv.org/abs/2608.31075 · PDF

  8. 08

    Wrong Prediction, Right Answer: Recovering Evidence from Collapsed LLM Sequence Scores

    Qiyao Yan, Chenpeng Wang, Liangming Pan

    cs.AI

    When a large language model fails a reasoning task, it is often assumed to lack the underlying capability. However, this conflates a genuine absence of reasoning with a late-stage output bottleneck. We observe a consistent readout gap across diverse reasoning benchmarks: hidden-state probes successfully decode correct answers even when native sequence scoring completely collapses due to structural biases. To test whether instance-specific...

    arxiv.org/abs/2608.31068 · PDF

  9. 09

    Measure Before You Manage: Evaluating Agent Working Memory in Coding Agents

    Le Chen, Zishen Wan, Baixi Sun, Xiaolong Ma, Chih-Hsuan Yang, Feng Yan, Sheng Di, Franck Cappello, Rajeev Thakur

    cs.AI

    Agent working memory is heterogeneous. Objects such as instructions, artifacts, tool outputs, and agent-generated state play different semantic roles and exhibit different size, retention, and representation profiles. Recent work has begun to explore memory-management mechanisms that account for such heterogeneity. This work focuses on semantic heterogeneity and studies how it should shape the management and evaluation of working memory in...

    arxiv.org/abs/2608.31057 · PDF

  10. 10

    MNIST-PRO: MNIST is Back as a Partially Observable World for AI Agents

    Vernon Toh, Navonil Majumder, Zhengyuan Liu, Nancy F. Chen, Soujanya Poria

    cs.AI · cs.CV

    AI agents in partially observable environments need to coordinate active sensing with working memory to maintain an evolving perceptual state. However, existing benchmarks struggle to isolate this perceptual-state construction and interpretation capability because they introduce physical and control complexities. We address this with MNIST-PRO, a benchmark that isolates agentic perception by converting MNIST digit recognition into a...

    arxiv.org/abs/2608.31022 · PDF

  11. 11

    Learning Action Models with Conditional and Quantified Effects via Uncertainty-Guided Exploration

    Jeffrey Jewett, William Solow, Sandhya Saisubramanian

    cs.AI

    Accurate action models are critical for effective planning. Existing action-model learning methods largely assume simple action representations or become computationally intractable when learning conditional and quantified effects. We present Online Hypothesis-Driven Conditional Action Model Learning (OHCAM), an online approach for learning action models with conditional and quantified effects from limited interactions with the environment....

    arxiv.org/abs/2608.30955 · PDF

  12. 12

    CARVE: Verified Expansion for Variable-Length Generation in Diffusion Language Models

    Wail Bouhedja, Amr Mohamed, Guokan Shang

    cs.AI

    Masked diffusion language models predict tokens from a partially observed response canvas, enabling bidirectional conditioning and parallel token refinement. Yet standard masked-diffusion decoders use a rigid inference interface: the number of masked positions allocated to the answer is fixed before generation begins. Choosing this length is difficult. A short canvas can truncate reasoning or code, while a long canvas wastes computation and...

    arxiv.org/abs/2608.30922 · PDF

  13. 13

    Responsible Integration of AI in Cancer Genomics: Barriers, Risks, and Pathways to Trustworthy Clinical Translation

    Bahar İlgen, Yiannos Tolias, Denise Kühnert, Paraskevi Papadopoulou, Magnus Westerlund, Dominik Heider, Katharina...

    cs.AI · cs.CL

    Artificial intelligence (AI) and natural language processing (NLP) are increasingly used to extract, integrate, and interpret biomedical knowledge relevant to cancer genomics, yet their translation into routine clinical oncology has been comparatively slow. The central challenge is not computational capability alone, but trustworthy integration into clinical workflows. This review examines how NLP and AI support the cancer genomics pipeline,...

    arxiv.org/abs/2608.30912 · PDF

  14. 14

    CAER: Causal Action Effect Reweighting for World Model Training

    Jianjie Fang, Xvyuan Liu, Ziyou Wang, Rongze Tang, Zhaolu Wang, Zhuohang Li, Xin Zhang, Haisheng Su, Chen Gao, Wei...

    cs.AI

    World models are becoming core infrastructure for embodied intelligence, with action-conditioned video generation providing controllable predictions of how scenes evolve after agent interventions. Yet existing models are commonly trained with space-time-uniform mean squared error, allowing abundant background tokens to dominate the gradient while sparse interaction dynamics remain under-optimized; such uniform fitting rewards reconstructing...

    arxiv.org/abs/2608.30897 · PDF

  15. 15

    Predicting Residential Rents in Dakar Using Machine Learning

    Amadou Tidiane Kassa Diallo

    cs.AI

    Dakar's residential rental market remains poorly documented despite its economic and social importance: 54.4% of households are renters, compared to 23.3% nationally. This study develops a complete machine learning pipeline to predict residential rents in Dakar, from data collection to model interpretation. An original dataset of 1,507 rental listings was built through systematic web scraping and a documented cleaning pipeline, then enriched...

    arxiv.org/abs/2608.30865 · PDF

  16. 16

    VFR-Audit: Verdict-Level Reliability for Fairness Audits in Hospital Length-of-Stay Prediction

    Md Jannatul Rakib Joy, Viet Vo, Caslon Chua

    cs.AI

    Fairness audits in clinical Artificial Intelligence convert continuous fairness metrics into binary pass-or-fail verdicts against operational thresholds, where hospital governance boards, payers, and regulators act on the resulting verdicts. Such audits are repeated over time and across hospital sites, thus the same verdict can flip between pass and fail across audits. Existing uncertainty methods such as Bayesian posteriors, bootstrap...

    arxiv.org/abs/2608.30846 · PDF

  17. 17

    HSRM: Hidden-State Reward Models for Test-Time Verification

    Xianzhi Li, Xiaodan Zhu

    cs.AI · cs.CL

    Large language models can often generate plausible mathematical reasoning traces, but reliably identifying the correct solution among multiple candidates remains a key challenge. Existing test-time reasoning pipelines typically rely on text-based verifiers that re-read each generated solution, making verification an expensive component of inference. Prior work has shown, however, that LLMs often encode correctness-related signals in their...

    arxiv.org/abs/2608.30841 · PDF

  18. 18

    SkillZip Pro: Execution-Aware Dynamic Compression of Progressively Loaded Skills for Self-Evolving Agents

    Xiaofan Bai, Chao Liu, Hongqiang Lin, Di Wu, Mingli Song, Xuan Jin, Xipeng Cao, Yuhong Li

    cs.AI

    Production agent skills are directory bundles, not isolated prompts. The root is loaded at activation; references, schemas, scripts, assets, and nested subskills are loaded only when an execution path needs them. Compressing only the root misses most deployment cost and may move branch-specific details into the always-loaded context. Flattening instead destroys progressive-loading boundaries. We introduce \method, an evaluation-free...

    arxiv.org/abs/2608.30785 · PDF

  19. 19

    Which Rules Matter Now? Policy-Centroid Routing Before an Intelligent System Acts

    Thomson D. Nguy

    cs.AI · cs.CY

    Before an intelligent system can decide whether an action is allowed, it must first know which rules the action has approached. A single proposed action can implicate several policy regimes at once. Their requirements may stack, overlap, or qualify one another, yet many remain written in natural language while the action itself arrives as an incomplete description of intent. The first problem is not judgment. It is attention. Policy-centroid...

    arxiv.org/abs/2608.30757 · PDF

  20. 20

    Autoregressive Mosaics: Probing 2D Spatial Reasoning in Text-Only Language Models

    Ashwin Nedungadi, Stefan Oehmcke, Stefan Lüdtke

    cs.AI · cs.CV

    Large language models (LLMs) trained only on text and code can sometimes generate programs that draw recognizable images. However, it is unclear whether this reflects an internal representation of 2D spatial layout or simply the ability to translate spatial descriptions into code. We introduce Autoregressive Mosaics (AM-Bench), a benchmark that separates these factors: First, a translation task gives a model a fully specified geometry of a...

    arxiv.org/abs/2608.30751 · PDF

  21. 21

    Multimodal Adaptive Expert Selection with Text Routing and Ordinal Prototype Optimization for Sentiment Analysis

    Xiaode Chen, Jiakang Yu, Hongtao Deng, Huina Qu, Xun Zhu, Yinxia Lou

    cs.AI

    Multimodal Sentiment Analysis (MSA) is a fundamental component of affective computing that aims to decipher complex emotional states by integrating verbal content with non-verbal cues including vocal intonation and facial micro-expressions. While recent disentanglement-based approaches have advanced the field, their potential is hindered by two methodological challenges. First, static computation graphs process all samples indiscriminately...

    arxiv.org/abs/2608.30726 · PDF

  22. 22

    ATLAS: Dual-Horizon Diagnostic Evaluation for Industrial Tool-Use Agents

    Wei Chen, Peilun Zhou, Zhaoyu Hu, Jiajun Chai, Zhongni Hou, Yufei Zhang, Derong Xu, Guojun Yin, Wei Lin, Zhi Zheng, Tong Xu

    cs.AI

    Large language model (LLM) agents are increasingly deployed in user-facing services that require iterative tool use under dynamic business conditions. Reliable evaluation is essential for sustained improvement: it must reveal capability deficiencies, inform priorities, and assess interventions. Yet industrial agent service unfolds both through the iterative trajectory of a current request and through continued user interaction. Final-outcome...

    arxiv.org/abs/2608.30685 · PDF

  23. 23

    MedAgent-R1: Faithfulness-Aware Reinforcement Learning for Evidence-Grounded Medical Reasoning

    Jiangwang Chen, Chenghao Zhang, Hengxing Cai

    cs.AI

    When medical AI systems hallucinate clinical reasoning, the consequences extend beyond incorrect answers: fabricated justifications that superficially reference retrieved evidence can mislead clinicians into unsafe treatment decisions. Medical reasoning agents must therefore produce not only correct answers but also faithful justifications that clinicians can verify against cited evidence. We identify a systematic failure mode in RL-trained...

    arxiv.org/abs/2608.30676 · PDF

  24. 24

    HiRS-Agent: A Hierarchical Multi-Agent System for Reliable Long-Horizon Remote Sensing Task Solving

    Boyang Mu, Zhiwei Wei, Mugen Peng, Wenjia Xu

    cs.AI · cs.MA · cs.MM

    Recent advances in large language models and multimodal models have pushed remote sensing (RS) processing from simple perception models to agentic systems designed to tackle complex, long-horizon RS tasks. However, existing systems often rely on monolithic decision-making frameworks, which fail to accommodate the multi-stage, interdependent nature of RS tasks. This centralized approach leads to challenges such as unstable task execution,...

    arxiv.org/abs/2608.30672 · PDF

  25. 25

    PyKEEN-NSX: A Modular Framework for Static, Dynamic and Schema-Aware Negative Sampling in PyKEEN

    Ivan Diliso, Nicola Fanizzi, Claudia d'Amato

    cs.AI

    Embedding methods have become popular due to their scalability on link prediction and/or triple classification tasks on Knowledge Graphs (KGs). Embedding models are trained relying on both positive and negative samples of triples. However, since KGs generally contain only positive assertions, negative samples are artificially generated through negative sampling strategies, ranging from simple random corruption to more sophisticated approaches...

    arxiv.org/abs/2608.30652 · PDF

  26. 26

    Geometry of Divergence: Tracking Hidden-State Trajectories for Adaptive Multi-Turn Reasoning

    Jie Liang, Zhengxin Yu, Hamid Nasiri, Peter Garraghan

    cs.AI · cs.CL

    LLM agents need to sustain goal-consistent reasoning across long multi-turn interactions under strict resource constraints. However, as the multi-turn context accumulates, it can destabilize the underlying LLM's internal representation of task-relevant information from earlier turns, blurring the boundary between constructive reasoning and representation drift. We formulate multi-turn reasoning as a hidden-state trajectory of the underlying...

    arxiv.org/abs/2608.30650 · PDF

  27. 27

    Automated Testing of LLM-Based Post Hoc Explainers Using Model Checking as an Oracle

    Dennis Gross, Helge Spieker

    cs.AI · cs.LG

    Large language models (LLMs) are used as post hoc explainers of sequential decision-making policies, producing natural-language explanations of why an action was chosen. However, LLMs often generate plausible but incorrect statements, and no existing approach systematically tests whether such explanations are faithful to the underlying environment. Two classic software testing challenges stand in the way: there is no oracle for the...

    arxiv.org/abs/2608.30581 · PDF

  28. 28

    TuringLLM: Efficiently Scaling Foundation Models Toward Physical AI

    Yuheng Zhang, Yizhao Wang, Da Zhu, Hua Zhou, Yue He, Jiahui Hu, Shaman Tang, Hanlin Chen, Yuhua Wei, Anhua Liu,...

    cs.AI

    We present Turing-20B-A2B, a 20B-parameter Mixture-of-Experts language model that activates approximately 2B parameters per token, designed for long-context and latency-sensitive physical AI applications. The model adopts Quantile Routing in a dynamic top-k configuration, enabling token-adaptive expert allocation while maintaining balanced expert utilization and a controlled average compute budget. During deployment, we further apply...

    arxiv.org/abs/2608.30567 · PDF

  29. 29

    AdaPath: Query-Adaptive Path-Finding via Path-Bank for Multi-Hop Implicit Biomedical KGQA

    Jun Hyeong Kim, Dongki Kim, Yinhua Piao, Sung Ju Hwang

    cs.AI

    Path-finding over knowledge graphs has become an effective way to ground LLM reasoning on multi-hop questions. However, biomedical QA introduces two distinct challenges that general-domain methods are not designed for: (i) queries do not expose intermediate reasoning and can be answered through multiple valid pathways, and (ii) biomedical knowledge graphs are densely connected, so path-finding methods easily take wrong turns. To address these...

    arxiv.org/abs/2608.30556 · PDF

  30. 30

    GarmentWeaver: Schema-Aware Structured Synthesis for Multimodal Sewing Patterns

    Yinwen Lu, Weihao Luo, Yueqi Zhong

    cs.AI · cs.CV

    Multimodal Sewing pattern generation aims to infer executable sewing patterns from design cues such as sketches and textual descriptions. As an interpretable and simulation-compatible representation, sewing patterns are particularly valuable for digital garment creation. However, existing methods often model garment specifications as flat long sequences, which entangles garment structure with detailed parameters and leads to redundant...

    arxiv.org/abs/2608.30550 · PDF

  31. 31

    Designing an Auditable LLM-Supported Workflow for Qualitative Thematic Analysis

    Nadia Jul Jeldtoft, Tariq Yousef

    cs.AI · cs.SE

    Large Language Models (LLMs) offer new possibilities for scaling qualitative analysis, but existing applications often provide limited methodological transparency regarding how qualitative methods are translated into computational procedures. This paper presents an auditable and privacy-preserving computational operationalization of inductive and latent Thematic Analysis (TA). This paper first derives five design principles from the...

    arxiv.org/abs/2608.30543 · PDF

  32. 32

    DiffPDE: Masked Diffusion Language Models as PDE Solver

    Wenxuan Guo, Yuyang Hong, Lubin Fan, Zhaojin Fu, Lin Chen, Kun Ding, Shiming Xiang

    cs.AI

    Existing approaches for synthesizing Partial Differential Equation (PDE) solvers predominantly rely on autoregressive models, yet their global left-to-right decoding incurs substantial redundancy when addressing inherently localized bugs. In this work, we challenge this inefficient paradigm and propose DiffPDE, a framework leveraging discrete diffusion language models for targeted code repair. By introducing a localized re-masking and...

    arxiv.org/abs/2608.30532 · PDF

  33. 33

    Learning-Assisted Congestion-Aware Route Scheduling for Semiconductor Fab Material Control Systems

    Hao Yin, Meiqi Tu, Anbang Liu, Shaochong Lin, Max Z. J. Shen

    cs.AI · math.OC

    Automated material handling systems in semiconductor fabs are operated by a material control system (MCS) that must schedule a relay route for every transport command online, before execution. This is a data-driven scheduling problem in which route cost is dominated in the upper tail by queueing at heterogeneous, partially observable relay equipment, so route selection requires estimating both delivery time and congestion risk at the decision...

    arxiv.org/abs/2608.30520 · PDF

  34. 34

    ScienceArena: Benchmarking LLMs on Latest Scientific Olympiad Competitions

    Guangxiang Zhao, Qilong Shi, Xusen Xiao, Wenpu Liu, Yaoming Li, Linfeng Hao, Shuyang Hou, Zijian Guo, Xinrui Zhang,...

    cs.AI · cs.CL

    Benchmark saturation and data contamination increasingly obscure genuine scientific reasoning in frontier LLMs. We introduce \textsc{ScienceArena}, an olympiad-style benchmark from thirteen public science competitions in physics, chemistry, and biology, including IPhO and IChO 2025--2026, IBO 2023, USAPhO 2026, and USNCO 2025. Its open-ended, multi-step problems use process-credit rubrics, making faithful scoring difficult. We build...

    arxiv.org/abs/2608.30517 · PDF

  35. 35

    CM2: Multimodal Cultural Reasoning via an Integrated Multi-Agent Framework

    Qi Li, Zhaojie Kang, Yingjie He, Zheng Lin, Hao Zhang, Guangxin Wu, Yan Gong, Rong Fu, Jianyuan Ni

    cs.AI

    Multimodal Large Language Models (MLLMs) have shown remarkable success in STEM domains, where progress is often driven by vertical, step-by-step deduction under relatively stable symbol systems. Their horizontal, interdisciplinary cultural reasoning, however, remains underexplored.We propose CM2, a multi-agent framework grounded in the cognitive pathway of human cultural interpretation. CM2 integrates multimodal perception,...

    arxiv.org/abs/2608.30498 · PDF

  36. 36

    CHASE: How Content Ecosystems Are Reshaped When Ranking Is the Only Target

    Qianwen Gao, Zichang Su, Yiwen Hou, Arlen Kumar, Leanid Palkhouski

    cs.AI · cs.IR

    Generative Engine Optimization (GEO) is increasingly used to improve content visibility in LLM-based retrieval systems, yet its population-level effects under repeated optimization remain poorly understood. We introduce Content Homogenization under rAnking Signal Exploitation (CHASE), a controlled simulation framework for studying how content ecosystems are reshaped when creators repeatedly adapt documents to an LLM ranking signal. We use...

    arxiv.org/abs/2608.30466 · PDF

  37. 37

    EvoSkill Injection: Red-Teaming Autonomous Skill Generation and Evolution in Self-Evolving Agents

    Doyun Kim, Chanwoo Kim, Sugyeong Eo, Yeo-Chan Yoon, Chanjun Park

    cs.AI · cs.CL

    LLM-based agent systems increasingly adopt skill-based architectures to reduce repetitive reasoning costs and improve stable, efficient task execution. Recent studies propose self-evolving agents that autonomously generate, refine, and reuse skills from past experiences to enable continuous capability evolution. However, autonomous skill evolution introduces a new attack surface in which malicious capabilities are generated, stored, and...

    arxiv.org/abs/2608.30429 · PDF

  38. 38

    From Metaheuristics to Exact Methods: A CP-SAT Approach for Multi-Objective Healthcare Workforce Scheduling

    Vipul Patel, Anirudh Deodhar, Dagnachew Birru

    cs.AI

    Healthcare workforce scheduling is an NP-hard optimization problem requiring simultaneous satisfaction of labor regulations, coverage requirements, employee preferences and cost objectives. Existing approaches (genetic algorithms, integer programming, constraint programming) model 6-12 constraints at shift-level granularity and cannot guarantee regulatory compliance. They also lack support for multi-role, multi-skill heterogeneity, mandatory...

    arxiv.org/abs/2608.30419 · PDF

  39. 39

    DERELAB: Probing Defeasible Reasoning and Confirmation Bias in LLMs with a Generative Benchmark

    Jayanta Sadhu, Sayem Shahad, Kenneth Marino

    cs.AI

    Defeasible reasoning is a type of reasoning where inferences are drawn from plausible current evidence, but can be retracted upon the introduction of newer evidence. Although recent studies have examined language-model behaviors in defeasible reasoning, the datasets have been static and lack wide coverage of non-monotonic reasoning categories. We introduce DeReLab, a generative framework that produces multi-turn belief-updating conversations...

    arxiv.org/abs/2608.30413 · PDF

  40. 40

    Dense Clinical Contrasts Enhance Medical Knowledge Updating in Large Language Models

    Yangmin Huang, Shu Quan, He Geng, Xin Ye, Qianyun Du, Zhiyang He, Jiaxue Hu, Xiaodong Tao

    cs.AI

    Medical knowledge changes continually, making large language models vulnerable to relying on outdated yet clinically plausible information. We study whether the format of supervision affects medical knowledge updating under a matched training-budget setting. We introduce SEER-Bench, a temporally anchored oncology-staging benchmark curated from the latest versioned SEER Research Data release, and render identical medical update events from...

    arxiv.org/abs/2608.30405 · PDF

  41. 41

    Scaffolding Foundation Models into Physical-World Agents Pushes the Frontier of Long-Horizon Navigation

    Zixing Lei, Gengze Zhou, Xiong-Hui Chen, Jiazhao Zhang, Yiyang Huang, Hang Yin, Haoqi Yuan, Qi Wu, Weixin Li, Siheng Chen

    cs.AI · cs.RO

    Long-horizon physical-world agents must reason over distant goals while grounding decisions in reliable closed-loop behavior. Today's foundation models split these capabilities: vision-language models (VLMs) infer missing information and adapt high-level plans but remain brittle and inefficient at repeated navigation grounding, while navigation foundation models (NFMs) robustly execute semantic goals but operate as bounded episodes without...

    arxiv.org/abs/2608.30396 · PDF

  42. 42

    Augmenting Human Performance with an XR Agent Learning from Online Behavior and BCI Evidence

    Ziheng Li, Xichen He, Haoyan Chen, Charlie Zou, Sheng Bai, Benjamin Yang, Mengyuan Wu, Jake Ledner, Yi-Jie Cheng,...

    cs.AI · cs.HC

    We present OLIVE, a framework for adapting a foundation model to provide real-time assistance in temporally demanding, high-stakes, and dynamic tasks. We show that passive EEG, fused online with behavioral evidence, can meaningfully extend the number of targets users detect and engage beyond their unaided action bandwidth. OLIVE learns from both explicit behavioral signals (the targets the user shoots down in an XR first-person shooter game)...

    arxiv.org/abs/2608.30369 · PDF

  43. 43

    Will the User Ever Know? Covert Indirect Prompt Injection on Tool-Using LLM Agents

    Yunseok Lee, Yunji Kim, Woojin Lee

    cs.AI · cs.CL

    As LLM agents take real-world actions through tools, indirect prompt injection (IPI) has emerged as a serious threat. The standard metric, Attack Success Rate (ASR), counts whether an injection succeeds but ignores what the user notices in the agent's final response. Looking at successful injection traces, we find two distinct outcomes: the agent executes the injection while returning an otherwise normal response, or reports the injected...

    arxiv.org/abs/2608.30362 · PDF

  44. 44

    Co-Annotator: Expert-Distilled ViT and VLM for Visual and Documentation Guidance in Age-Related Macular Degeneration

    Ziheng "Leo" Li, Benjamin Freeman, Akshay Raman, Kavin Aravindhan Rajkumar, Xinxin Fang, Rishabh Srivastava, Steven...

    cs.AI · cs.HC

    Clinical AI often optimizes predictive performance without engaging how clinicians decide where to look and what to write. We present Co-Annotator, which distills expert gaze and dictation into two guidance components: a gaze-aligned Vision Transformer producing fixation-aligned areas of interest (AOIs), and an ontology-bounded vision-language model (VLM) that pre-fills editable biomarker summaries for retinal optical coherence tomography...

    arxiv.org/abs/2608.30352 · PDF

  45. 45

    Answer Probing-Guided Search for Diverse Solution Exploration of LLMs

    Yi Fang, Que Shen, Chengpeng Li, Boyi Deng, Wei Shi, Wenjie Wang, Fuli Feng, Fengli Xu, Dayiheng Liu

    cs.AI

    Generating multiple diverse and high-quality solutions is valuable for many applications, such as code-test generation and drug discovery. However, Large Language Models (LLMs) tend to converge on a single high-confidence solution during inference, limiting exploration of alternative valid solution paths. Existing test-time methods promote diversity through tree-like search and prune semantically similar branches using response-level semantic...

    arxiv.org/abs/2608.30345 · 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.