cs.AI · 2026-10-27 · No. 155

Artificial Intelligence, 2026-10-27.

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

01 — The papers

49 entries
  1. 01

    Retriever-Free Retrieval: Navigating Documents with Decision Models

    Chao Wan, Paul Jünger, Beixi Du, Bodong Liu, Navaneetha Krishnan, Kilian Q. Weinberger

    cs.AI

    While language models have become dramatically more capable, retrieval still largely relies on lexical matching or similarity in fixed embedding spaces. This creates a capability asymmetry: what the retriever fails to find, even the strongest generator cannot recover. We propose DecisionRAG, which brings the capabilities of pretrained language models to retrieval using decision models that jointly evaluate candidate branches in a single...

    arxiv.org/abs/2610.35868 · PDF

  2. 02

    Center-of-Mass Interpretation of Evolution Strategies

    Akshat Gupta

    cs.AI · cs.CL

    Evolution strategies (ES) update a model by sampling a population of perturbed copies, scoring each one, and moving in the reward-weighted direction of the perturbations. This update is usually presented as an estimate of a smoothed gradient. We present a geometrical interpretation of this update instead. Treat each perturbed model as a particle and its reward as the particle's mass. Before scoring, every particle has the same mass and the...

    arxiv.org/abs/2610.35865 · PDF

  3. 03

    Patient-specific rubric-based evaluation of large language models across longitudinal cancer care

    Wei-Wei Zhang, Pengkai Wang, Yan Li, Zhijie Sang, Guan-Qun Zhou, Jun-Yan Li, Shu-Han Zhou, Pei-Wen Liu, Ting-Xi...

    cs.AI

    Large language models (LLMs) show promise in specialty medicine, yet existing evaluations largely focus on isolated clinical encounters rather than tracking how clinical responsibilities evolve across a longitudinal care pathway. Here we introduce NPC-RubricBench, a phase-aware benchmark for evaluating multistage clinical reasoning across the cancer care continuum, using nasopharyngeal carcinoma as a defined disease context. Curated from...

    arxiv.org/abs/2610.35847 · PDF

  4. 04

    Game theory of academic effort and hiring in the age of AI

    Saptarshi Pal, Peter S. Park

    cs.AI · cs.CY · cs.GT

    Many academic disciplines (in particular, mathematics and the theoretical sciences) face difficult questions about how to adapt their practices to the rise of highly capable artificial intelligence (AI). Before AI, a well-written research paper with a strong theoretical result acted as a reliable signal that its authors understood their field in depth. Now that AI is widely accessible, such signals have become cheaper to produce. As a result,...

    arxiv.org/abs/2610.35802 · PDF

  5. 05

    A Unified Arena for LLM Agents across Diverse Eurogame

    Fengrui Zhang, Xiang Li, Ruomeng Ding, Jiayi Yuan, Yuchen Huang, Zhaoyang Han, Xiaoliang Wang, Daoyuan Chen, Yaliang Li

    cs.AI

    Interactive environments offer a practical way to evaluate large language model (LLM) agents, and competitive games extend this evaluation to decisions shaped by competing goals and other agents' choices. Yet existing evaluations confined to individual games or execution frameworks leave unclear which competitive advantages persist across settings. We introduce DECE (Diverse Eurogame Competitive Environments), a unified arena spanning ten...

    arxiv.org/abs/2610.35773 · PDF

  6. 06

    Free to Look, Free to Reason: Simple LLM Harnesses Outdiagnose Hand-Crafted Root Cause Analysis Agents

    Tingzhu Bi, Xun Zhang, Jinglin Li, Ping Wang, Meng Ma

    cs.AI · cs.DC · cs.SE

    Root cause analysis (RCA) of microservice failures has attracted many LLM agents whose investigation is hand-crafted, through standard operating procedures, fixed stages and role agents. Each is evaluated on its own data against few baselines, so it is unknown whether this design beats letting a capable model investigate on its own. We compare three simple harnesses that prescribe none of the model's calls (one call over an evidence package,...

    arxiv.org/abs/2610.35767 · PDF

  7. 07

    Beyond Physical Illness: Can Clinical Narratives Reveal Emerging Mental Health Risks in Chronically Ill Patients?

    Sudeshna Jana, Siddhartha Laha, Manjira Sinha, Tirthankar Dasgupta, Pabitra Mitra

    cs.AI · cs.LG

    Mental-health risks such as depression, dementia, and suicidal ideation can emerge during hospitalization among chronically ill patients and may worsen without timely recognition and intervention. However, most existing mental health studies focus on patients with established psychiatric conditions rather than patients hospitalized primarily for physical illness. In this work, we investigate whether latent mental-health risk in chronically...

    arxiv.org/abs/2610.35761 · PDF

  8. 08

    CLOSURE: Cross-Channel Closure for Multivariate Time Series Anomaly Detection

    Fan Xu, Hao Wu, Zhi Song, Hanbo Huang, Wenzhuo Ma, Nan Wang, Wei Gong, Xibin Zhao

    cs.AI

    Multivariate time series produced by industrial installations and server clusters are under continuous monitoring, and anomaly detection is the first line of defense before a local fault escalates into a system-wide failure. In the absence of labels, the dominant paradigm trains a reconstruction model on normal data and scores the residual to reach a verdict. Recent work has steadily enriched the expressiveness of the recovery map through...

    arxiv.org/abs/2610.35753 · PDF

  9. 09

    Explainable Multimodal AI Approach to Reduce Unnecessary Breast Biopsies

    Sadam Hussain, Mansoor Ali, Daly Betzabeth Avendaño-Avalos, Jose Gerardo Tamez-Peña

    cs.AI

    Recently, there has been rise in multimodal vision-language models for computer-aided diagnosis (CAD), yet their application in breast diagnosis, particularly for predicting biopsy outcomes remains limited. This study presents a multimodal vision-language approach, incorporating Grad-CAM as an Explainable AI (XAI) technique, to predict benign tumors in patients recommended for biopsy, especially those classified as BI-RADS 4 and 5. A novel...

    arxiv.org/abs/2610.35704 · PDF

  10. 10

    EvoRouter: Cost-Efficient Multi-Agent Routing via Insight-Guided On-Policy Distillation

    Yitao Xiao, Xu Zhang, Ye Cheng, Shaoyong Guo, Yan Sun, Ziyue Zhu, Sitao Xie, Guo Tong, Haoran Luo

    cs.AI · cs.MA

    Serving web queries at scale with multi-agent systems requires jointly configuring large language models, collaboration modes, agent counts, interaction rounds, and skills. However, the resulting configuration space grows combinatorially, while sparse execution rewards provide limited fine-grained supervision for interdependent planning decisions. We propose EvoRouter, a self-evolving multi-agent routing framework driven by insight-guided...

    arxiv.org/abs/2610.35690 · PDF

  11. 11

    VaLoP: Value Gradient Lookahead and Pullback for Reward-Guided Diffusion

    Kwanyoung Kim

    cs.AI

    Reward guidance steers a pretrained diffusion or flow model toward images or actions that a reward model prefers, at sampling time and without retraining the model for each reward. It follows the gradient of a value function, the expected reward given the noisy state. The two common estimates of this gradient, gradients through a one-step denoised estimate and learned value models, are least accurate at high noise, where the coarse structure...

    arxiv.org/abs/2610.35607 · PDF

  12. 12

    ArchiveLens: A Generative Spatial Knowledge Framework for Semantic Reconstruction of Historical Maps

    Yanan Wu, Yalin Yang, Chengbin Deng

    cs.AI · cs.CY · cs.LG · cs.SI

    Historical maps contain dense morphological and semantic information about past urban environments, but many digitization workflows focus primarily on extracting geometry, and do not capture cartographic semantics such as building use and construction materials. This study introduces ArchiveLens, a generative spatial knowledge framework that operationalizes historical maps as entity-centric, machine-queryable geospatial databases. The...

    arxiv.org/abs/2610.35606 · PDF

  13. 13

    Evolve on Graph: Self-Evolving Knowledge Graph Reasoning without Question Annotations

    Zongyuan Sun, Shuai Zhao, Ke Shu, Ziyue Zhu, Shangyang Wu, Yuanlin Lin, Tao Wang, Shiyue Li, Yingjun Du, Anh Tuan...

    cs.AI

    Knowledge graphs (KGs) provide reliable external knowledge for multi-hop factual reasoning with large language models (LLMs), yet most KGs in real-world domains such as finance and industry lack question--answer (QA) annotations. Without such annotations, existing methods struggle to improve LLM graph reasoning: training-free agents cannot improve their exploration through interaction; reinforcement learning (RL) agents depend on QA data...

    arxiv.org/abs/2610.35598 · PDF

  14. 14

    Agentic Algorithm Design: LLMs that Propose, Formalise, and Prove Runtime Bounds for Evolutionary Algorithms in Lean

    Per Kristian Lehre

    cs.AI · cs.NE

    LLMs now prove hard theorems in Lean. Can they also design algorithms and prove their correctness and efficiency? LLM-guided design of optimisation heuristics (such as AlphaEvolve) is purely empirical. Automated theorem provers with LLMs prove given statements. So far, there has been little evidence that LLMs can do both: design an algorithm and guarantee its efficiency by a mathematical proof. We present a staged pipeline modelled after...

    arxiv.org/abs/2610.35595 · PDF

  15. 15

    SAP-ViT: A Self-Attributing Patch Vision Transformer for Medical Image Classification

    Wei Zhang, Wolfgang Nejdl, Ming Tang

    cs.AI

    Vision Transformer (ViT) classifiers commonly rely on a global classification (CLS) token for image-level prediction, which is poorly aligned with local interpretability requirements in medical imaging. We propose SAP-ViT, a Self-Attributing Patch Vision Transformer that replaces CLS-based classification with direct aggregation of last-layer patch embeddings. This design makes class predictions decomposable into patch-level contributions as...

    arxiv.org/abs/2610.35593 · PDF

  16. 16

    Linear Probes Transfer from Base to Distilled Language Models despite Rotation

    Marios Tsatsos

    cs.AI · cs.CL · cs.LG

    Linear probes, classifiers that read a language model's internal activations, are widely used to detect harmful requests. They are cheap to train and run, and an auditor who has trained one would like to reuse it when the model is replaced by a successor rather than retrain it for every release. We test how well probes can be reused. For four base models (Qwen2.5-Math-7B, Llama-3.1-8B, Qwen2.5-14B, Qwen2.5-32B) we train a probe on the base...

    arxiv.org/abs/2610.35586 · PDF

  17. 17

    Infinity Machine: a self-improving AI agent for research

    Harish Santhanalakshmi Ganesan

    cs.AI

    We present the Infinity Machine, a self-improving AI agent that we use for research on problems whose answers aprogram or data can check. Each candidate solution is produced by a full tool-using agent that works for up to an hour in a fresh sandbox; proposers see only a public score, and a private split decides what counts. The harness itself(prompts, tools, skills, playbook, meta agent) is an editable genome, changed only through a...

    arxiv.org/abs/2610.35579 · PDF

  18. 18

    CANS: Capability-Preserving Neuron Steering for Large Language Models

    Yucheng Wu, Chengyi Xie, Chenpeng Wang, Liangming Pan

    cs.AI

    Activation steering offers training-free and dynamic control of target behaviors in large language models, but existing methods can impair general capabilities and require domain-specific intervention designs. We introduce Capability-Preserving Neuron Steering (CANS), a unified framework that balances target-behavior control with capability preservation. To make target-behavior improvement and general-capability preservation tractable, we...

    arxiv.org/abs/2610.35530 · PDF

  19. 19

    Test-Time Confidence Adaptation under RL-Induced Trajectory Shift

    Zhenzhen Ren, Xiaoqing Zhang, GuoBiao Li, Bowen Fang, Yanxi Wang, Xinpeng Zhang, Ke Han

    cs.AI

    Trajectory-based confidence estimation has shown promising performance for large language models (LLMs) by leveraging rich signals from their reasoning processes. However, we find that such confidence estimators can degrade substantially after agentic reinforcement learning (Agentic RL) as it induces substantial shifts in the reasoning trajectories. More importantly, despite these shifts, we uncover a reliability structure that is largely...

    arxiv.org/abs/2610.35500 · PDF

  20. 20

    ShutdownMod: Turning Any Trajectory into a Shutdown Evaluation

    Param Biyani, Sebastien Luyasu, Cedric Potvliege, Divij Chawla, Elliott Thornley, Christos Ziakas

    cs.AI · cs.LG

    Theory and experiments suggest that capable AI agents may resist shutdown. Existing shutdown evaluations are informative but limited in coverage and vulnerable to evaluation awareness. We introduce ShutdownMod, a method that turns any agent trajectory into a shutdown evaluation by injecting a shutdown request into the agent's context and recording the agent's response. Crucially, we enable the LLM agent to distinguish between trusted...

    arxiv.org/abs/2610.35486 · PDF

  21. 21

    EvoBench: An Evolving, Diagnostic Benchmark Framework for Environmental Modeling

    Yiming Sun, Yuan Zhang, Qi Cheng, Yingda Fan, Runlong Yu, Yiqun Xie, Xiaowei Jia

    cs.AI · cs.LG

    Machine learning models are now widely used to predict environmental variable dynamics in domains like hydrology, climate science, agriculture, and ecology. These models are usually compared on fixed benchmark datasets using a single average accuracy score. As models improve, their scores become very close when averaged over large regions and long time periods, so the benchmark can no longer tell them apart, and a single number hides...

    arxiv.org/abs/2610.35464 · PDF

  22. 22

    Beyond Federated Learning: Decentralized Agentic Systems for Self-Evolving Clinical Intelligence

    Haoyuan Li, Mathias Funk, Aaqib Saeed

    cs.AI

    Clinical expertise is inherently distributed: it resides not in any single dataset or institution but in the accumulated reasoning experiences of thousands of clinicians navigating diverse patient populations, resource constraints, and evolving treatment protocols. Yet current approaches to scaling medical AI, from centralized large language models to federated learning, remain anchored to a data-centric paradigm that treats knowledge as...

    arxiv.org/abs/2610.35453 · PDF

  23. 23

    Omni-InteractScope: Benchmarking Proactive and Agentic Interaction in Continuous Omnimodal Streams

    Yinsong Yan, Ling Wang, Yuxuan Wang, Yifan Yang, Ruiyang Xu, Junming Lin, Qi Chen, Meng Gao, Minghao Han, Yunfei...

    cs.AI · cs.CV · cs.HC

    Omnimodal large language models (Omni-LLMs) are increasingly expected to assist users while observing continuous audiovisual streams. However, existing evaluations provide limited insight into how reliably these models connect stream evidence and user needs to timely, sustained interventions. We introduce \textbf{Omni-InteractScope}, a benchmark of 1,479 human-annotated, cross-reviewed interactions with 1,790 temporal targets across eight...

    arxiv.org/abs/2610.35439 · PDF

  24. 24

    Skill$^{\infty}$: Recursive Self-Improvement for Agent Skill Optimization

    Wangcheng Tao, Zhanglu Yan, Han Wu, Weng-Fai Wong

    cs.AI · cs.CL

    Recursive self-improvement (RSI), in which a system also improves the way it improves, is a long-standing aspiration on the path to AGI. Language agents increasingly store procedural knowledge in reusable skills. Optimizing skills offers a direct way to achieve RSI, because the optimization procedure itself can be encoded as a skill. Existing skill optimizers, however, follow a hand-designed procedure. Even methods that evolve a meta-skill...

    arxiv.org/abs/2610.35434 · PDF

  25. 25

    Faithful Explanations under Missing Modalities in Multimodal Dementia Prognosis

    Firuz Kamalov

    cs.AI

    Large language models are increasingly used to turn the feature attributions of multimodal prognostic models into narratives for clinicians, yet costly modalities such as amyloid PET and cerebrospinal fluid biomarkers are often missing, and whether these explanations stay faithful under missing evidence has not been tested. We separate two failure points: phantom attribution, in which the model credits modalities that were never observed, and...

    arxiv.org/abs/2610.35430 · PDF

  26. 26

    From Denoising Dynamics to Endpoint Uncertainty in Diffusion Language Models

    Julio C. Amador Diaz Lopez

    cs.AI

    Predictive uncertainty in stochastic language-model inference can be characterized by repeatedly sampling an input and measuring the distribution of outputs. This requires multiple complete generations. Masked diffusion language models expose another source of information: the evolution of the output during denoising. We ask whether convergence within diffusion trajectories is associated with uncertainty across their final outputs, or...

    arxiv.org/abs/2610.35425 · PDF

  27. 27

    NeSySpec: Neuro-Symbolic Technical Intelligence for Auditing Engineering Specifications with an Application to Aircraft

    Pier Mattia Basciano, Gianvito Antenori, Cristiano Andolfi, Giovanni Farina, Salvatore Monteleone

    cs.AI · cs.CV · cs.SC

    Engineers who audit a declared specification of an engineered system need to know which physical constraints it respects, which it violates, which field was altered and how to correct it. NeSySpec is an integrated and interpretable neuro-symbolic audit framework, built on Logic Tensor Networks, that answers these questions in one pipeline. Its axioms encode the physical relations of the domain as differentiable graded predicates whose...

    arxiv.org/abs/2610.35403 · PDF

  28. 28

    AdaTrendLike: Adaptive Hierarchical Detrending and Trend Likelihood Scoring for Time Series Anomaly Detection

    Van Kwan Zhi Koh, Songnan Lin, Rongmo Luo, Zhiping Lin, Bihan Wen

    cs.AI

    The rapid proliferation of Industrial Internet of Things devices has led to increasingly large-scale and non-stationary time-series data, posing significant challenges for time-series anomaly detection (TSAD). Existing approaches often focus on reconstructing or forecasting observations while overlooking the role of trend dynamics, which constitute a major source of non-stationarity and contain valuable information for anomaly identification....

    arxiv.org/abs/2610.35400 · PDF

  29. 29

    Belief-Conditioned Multi-Agent Actor Critic for Decentralized LLM Collaboration

    Tianle Chen, Shuo Liu, Christopher Amato

    cs.AI · cs.LG · cs.MA

    Recent work has explored optimizing LLM collaboration through Multi-Agent Reinforcement Learning (MARL), but many approaches still rely on predefined workflows, limiting efficiency and scalability. Decentralized LLM collaboration is challenging because agents execute independently with limited communication, share a joint objective, and must infer useful information from communication traces. In this paper, we propose BCMAAC, a...

    arxiv.org/abs/2610.35398 · PDF

  30. 30

    RSIV-Harness: A Recursive Self-Improvement Harness Framework for Open-Domain Conversational Text-to-Visualization

    Jiawei Lu, Chen Zhang, Jinwei Lu, Yuanwei Song, Yuanfeng Song, Raymond Chi-Wing Wong

    cs.AI

    Users often request charts without knowing which database or table holds the relevant data. Such requests may be ambiguous, and users may ask follow-up questions to deepen their analysis or iteratively refine existing charts. A useful assistant must therefore discover relevant data sources among heterogeneous databases, ask clarifying questions when needed, and track evolving user intent while preserving constraints established in earlier...

    arxiv.org/abs/2610.35316 · PDF

  31. 31

    LLM-Enhanced Heterogeneous Graph Learning with Business Semantics for Financial Fraud Detection

    Yixuan Chen, Hongyu Zhan, Jie Sheng, Weiyu Han, Shuai Chen, Tianyi Zhang, Xiao Tan, Jun Xia

    cs.AI

    Financial fraud detection increasingly relies on heterogeneous transaction graphs, in which entities such as cards and merchants play distinct business roles and the risk meaning of an attribute depends on the entity's role: a high transaction volume may be routine for a merchant but unusual for a card. Heterogeneous graph neural networks preserve typed entities and relations but typically treat these attributes as role-agnostic inputs and...

    arxiv.org/abs/2610.35298 · PDF

  32. 32

    Application of Artificial Intelligence in the Management of Climate Change-Related Health Issues in Africa

    Peter Kokol, Martha Kachweka, Helena Blazun Vosner, Samuel Chol Buol, Jernej Zavrsnik, Bojan Zlahtic, Grega Zlahtic

    cs.AI · cs.CY

    While climate change disproportionately impacts African public health, AI predictive modeling remains heavily constrained. Using a Synthetic Knowledge Synthesis approach and VOSviewer, we conducted a bibliometric analysis of Scopus-indexed literature, comparing Global and African corpora. Network analysis reveals stark divergences: global research emphasizes complex, predictive models for planetary health, whereas African research focuses on...

    arxiv.org/abs/2610.35294 · PDF

  33. 33

    AgenticCity-Bench: Longitudinal Multimodal Observations of Urban Dynamics with Agentic Reasoning

    Xiaofei Yu, Kailai Sun, Yanyu Mao, Baoshen Guo, Heye Huang, Yongcai Wang, Baotong Mi, Alok Prakash, Shenhao Wang, Jinhua Zhao

    cs.AI

    City systems are shaped by interactions among infrastructure, human activity, and environmental conditions. Existing earth observation and urban benchmarks are limited in unified modeling and in capturing their joint dynamics. We introduce AgenticCity-Bench, a longitudinal multimodal benchmark for multi-layer unified state modeling and agentic city task reasoning. The benchmark covers 16 cities in 12 countries across six continents from 2000...

    arxiv.org/abs/2610.35293 · PDF

  34. 34

    Proof-of-Agentness: Towards Verifying Agents on the Web

    Zuyao Xu, Xiang Li

    cs.AI

    CAPTCHAs and bot detection have helped protect Web services from automated abuse for decades by distinguishing humans from bots. However, the emergence of LLM-powered agents introduces a new setting: Web services increasingly accommodate agents as legitimate users. Without a way to distinguish agents from other automated clients such as simple bots and scripts, these services risk large-scale automated junk submissions that waste service...

    arxiv.org/abs/2610.35288 · PDF

  35. 35

    Self-Supervised Pretraining for PHM: What Transfers, What Does Not, and What Federating It Costs

    José Sanz-Durán, David Solís-Martín

    cs.AI · cs.CE · cs.LG · cs.PF

    Self-supervised pretraining has produced capable time-series foundation models, but its value for Prognostics and Health Management (PHM) has not been measured under leakage-controlled conditions. We measure it on a corpus of 47 public PHM datasets, harmonized to a single tensor contract and partitioned so that 11 datasets are withheld from pretraining in full. Transfer turns out to be task-dependent: a compact channel-independent Transformer...

    arxiv.org/abs/2610.35280 · PDF

  36. 36

    Before Blaming the LLM, Diagnose the Workflow: A Role-Level Difficulty Profile for Translating Natural Language into Ontology-Grounded Statements

    Liang Zhang, Benoît Daireaux, Sergey Alyaev

    cs.AI

    Natural-language-to-domain-specific-language (NL-to-DSL) semantic parsing systems increasingly translate informal user descriptions into structured artifacts such as Structured Query Language (SQL) queries, Application Programming Interface (API) calls, workflows, formal specifications, and ontology-grounded domain-specific language (DSL) statements. This paper focuses on ontology-grounded Assertion Box (ABox) DSL generation: the translation...

    arxiv.org/abs/2610.35267 · PDF

  37. 37

    Trainable Boundary-Keeping Where No Formal Answer Exists: A Controlled Knock-In Study of Reward Training in Evidence-Sufficiency Judgment

    YaJie Yin

    cs.AI · cs.CL · cs.LG

    Reasoning-tuned and reward-trained models are often assumed to verify more reliably because they reason longer or receive correctness signals. We test this in evidence-sufficiency judgment: deciding whether available information actually supports a causal claim, a domain with no decidable correctness reward. Using a pre-registered, same-base, controlled knock-in design, we compare a boundary-keeping recipe (SFT then GRPO) with its own...

    arxiv.org/abs/2610.35226 · PDF

  38. 38

    MuSID-KD: Multigranularity Knowledge Distillation for Generative Recommendation with Semantic IDs

    Fengshi Zhang, Xiyan Ding, Shuxiao Xie, Wei Zhang

    cs.AI

    Generative recommendation with semantic IDs (SIDs) represents each item as a sequence of discrete tokens and autoregressively predicts the next item's SID. Despite strong recommendation performance, repeated decoding over multiple SID positions incurs substantial inference cost. Knowledge distillation transfers knowledge from a powerful generative teacher to a lightweight student, yet conventional objectives do not fully account for...

    arxiv.org/abs/2610.35218 · PDF

  39. 39

    Same Story, Different Lens: A Multi-Agent System for Cross-Outlet News Framing Analysis

    Affan Yasin, Yueqi Lyu, Rubia Fatima, Weinchen Zhong, Keyi Li

    cs.AI

    News outlets covering the same event differ in what they emphasize and omit. \textit{Same Story, Different Lens} is an experimental research prototype for comparing these choices. It collects world and politics coverage from 17 outlets, groups reports about the same event, and produces structured analyses of sentiment, political lean, framing, loaded language, possible omissions, and model-estimated proportions of factual claims and opinion....

    arxiv.org/abs/2610.35208 · PDF

  40. 40

    Trustworthy Recursive Self-Improvement in the Era of Large Models: Foundation, Risks, Evaluation and Open Challenges

    Jiayue Pu, Ang Gao, Jinyi Bai, Qipeng Wang, Tongyu Wen, Jiahao Zhao, Keyu Qu, Junhao Zhang, Chenglei Shen,...

    cs.AI · cs.CR

    AI systems built around large models increasingly use experience and feedback to make persistent changes to models, prompts, memories, tools, and workflows. Recursive self-improvement (RSI) extends this process to inductive biases and to the mechanisms that govern future updates, which can themselves be revised and reused across improvement cycles. Yet self-modification alone does not guarantee trustworthy improvement. Reported gains may...

    arxiv.org/abs/2610.35193 · PDF

  41. 41

    AutoEnergyDesign: An LLM-Driven Agent for Automatic Energy System Design Optimization

    Amedeo Buonanno, Salvatore Fabozzi, Maria Valenti

    cs.AI · stat.ML

    Designing building energy systems is a high-dimensional, mixed-integer search problem: when each design is evaluated by a year-long simulation, black-box optimizers typically need hundreds of evaluations. This paper presents AutoEnergyDesign, a framework in which a Large Language Model (LLM) agent reasons over previous simulation results, proposes configuration changes and learns in context from each outcome, while a git-based mechanism...

    arxiv.org/abs/2610.35160 · PDF

  42. 42

    LongSearchEval: Evaluating Long-Horizon Web Search Capabilities of Large Language Models via a Trajectory-Aware Agent Framework with Failure-Node Localization

    Jialiang Liu, Shusheng Li, Wenjun Tan

    cs.AI

    Long-horizon web search requires LLM-based agents to integrate information across web pages through extended interactions under task-specific constraints. Evaluating this capability is important not only for measuring final answer quality, but also for assessing whether an agent acquires, verifies, and uses evidence reliably over extended interactions. Existing evaluations, however, mainly rely on simulated trajectories or on post-hoc...

    arxiv.org/abs/2610.35150 · PDF

  43. 43

    Co-Design Bench: Multimodal Collaborative Coding Evaluation for Agentic Models

    Xilin Wei, Shengyuan Ding, Xinyu Fang, Tiancheng Gu, Yuchi Wang, Zhixun Li, Ziyu Liu, Yuhang Zang, Weixiang Yu,...

    cs.AI

    Evaluating human-AI co-design requires testing whether coding agents can translate real users' multimodal requests into working application revisions. We introduce Co-Design Bench, a reference-free benchmark of 273 tasks curated from 37,463 deduplicated queries across 26,314 real user coding sessions. Its two tracks, Multimodal Editing (ME) and Repository Editing (RE), cover localized edits with optional image, audio, video, or document...

    arxiv.org/abs/2610.35138 · PDF

  44. 44

    When Fusion Order Matters: Insights on Progressive Multimodal Representation Learning for Cross-modal Retrieval

    Haoxiang Zhao, Bin Wang, Yaofei Wang, Xiao Lan, Yunfeng Diao, Xu Wang

    cs.AI · cs.IR

    Multimodal video retrieval combines visual, acoustic, and speech information, yet how their fusion order should depend on the data and the retrieval query remains unclear. We introduce Unified Progressive Representation Learning for Order Analysis, or UniPRO, to investigate this question through configurable fusion schedules with matched model components and training settings. Starting from text-to-video retrieval, we find that the tested...

    arxiv.org/abs/2610.35125 · PDF

  45. 45

    Improving Instruction Hierarchy by Learning from Goal-Goal Conflicts

    Sizhe Chen, Sanjay Kariyappa, Liwei Jiang, Chong Xiang, Jihye Choi, Chaowei Xiao, G. Edward Suh

    cs.AI

    The recent incident in which OpenAI agents autonomously compromised Hugging Face's infrastructure illustrates the importance of instruction hierarchy (IH): an LLM should follow lower-priority instructions, such as user requests, only when they do not conflict with higher-priority instructions, such as system policies. IH can be effectively improved by fine-tuning LLMs on simulated examples of instruction conflicts, whose diversity is key to...

    arxiv.org/abs/2610.35093 · PDF

  46. 46

    Zero-Shot Multi-Class Wafer Map Classification with Rule-Ordered Prompts for Large Multimodal Models

    Tianjian Cao, Jun Tao

    cs.AI

    Wafer-map defect classification often requires labeled data and retraining when production conditions change. We present a training-free six-class framework that combines connected-component highlighting with morphology-, location-, and exclusion-aware prompts for a frozen large multimodal model. On Mixed-WM38 (6,866 maps), multi-region prompting achieves 92.9% macro and 93.8% overall accuracy. On WM811K (9,000 maps), it achieves 79.1% and...

    arxiv.org/abs/2610.35080 · PDF

  47. 47

    Toward Fast Human Reaction Modeling from High-Frequency Digital Interaction Data

    Emanuel Dopater, Daniel Gavlas, Lukáš Jochymek, Kannan Paul, Miloslav Szczypka, David Vojáček, Josef Žáček, Jan...

    cs.AI · cs.LG

    We investigate whether limbic-like signatures of rapid, salience-driven behavior can be identified in high-resolution Counter-Strike 2 telemetry. This exploratory study introduces Ego-Knowledge, a leak-reduced reconstruction of each player's plausible perceptual state, supported by a millisecond-precision visibility engine and a reaction-centered extraction pipeline. Using a neuroscience-motivated 60--120 ms window, we derive coarse...

    arxiv.org/abs/2610.35079 · PDF

  48. 48

    A Diagnostic Protocol for GNNs in Electricity Load Forecasting: Separating Parameter Sharing from Neighborhood Access

    Eloi Campagne, Yvenn Amara-Ouali, Yannig Goude, Itai Zehavi, Argyris Kalogeratos

    cs.AI

    A graph neural network (GNN) forecasting a collection of load series combines two mechanisms, sharing parameters across series and reading neighboring series, and a gain over a non-graph model may come from either; telling them apart decides whether a graph is worth maintaining. We propose a model diagnostic protocol that compares the GNN with three reference models: a per-node network, a network shared across nodes without neighbors, and the...

    arxiv.org/abs/2610.35074 · PDF

  49. 49

    Beyond Single-Attribute Auditing: A Configurable Multi-Attribute Benchmark for Intersectional Fairness in LLMs

    Zheng Zhang, Yifan Wu, Yuxiang Zhou, Qi Liu, Qingyang Mao, Ning Li, Weibo Gao, Qiyuan Shi, Zhenya Huang, Baosheng Yu

    cs.AI

    Large language models (LLMs) are increasingly evaluated for fairness, yet most existing benchmarks audit one sensitive attribute at a time. This single-attribute paradigm can miss intersectional harms, where multiple attributes interact non-additively and produce failures that are invisible under marginal evaluation. We introduce ComFair, a configurable benchmark that converts existing fairness data into 479,066 controlled Dual- and...

    arxiv.org/abs/2610.35069 · 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.