cs.AI · 2026-11-15 · No. 172

Artificial Intelligence, 2026-11-15.

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

01 — The papers

55 entries
  1. 01

    AgentSSL: Can MLE Agents Leverage Unlabeled Data?

    Ethan Lin, Akanksha Sarkar, Ziang Liu, Kristin Branson, Jennifer J. Sun

    cs.AI · cs.LG

    Applying machine learning systems to new domains introduces bottlenecks in both labeled data acquisition and manual pipeline engineering. While recent MLE agents show promise in automating pipeline design, they have been studied almost exclusively in fully supervised settings, leaving them untested in realistic regimes where labeled data is scarce but unlabeled data is abundant. In this work, we introduce Agentic Semi-Supervised Learning...

    arxiv.org/abs/2611.17323 · PDF

  2. 02

    CoReMem: Cost-Internalizing Memory for Successive Coding Tasks with Prospective Valuation

    Peiwen Li, Harshit Verma, Sophia Zhou, Haiwen Wang, Ngoc Bui, Heng Chang, Fei Fei, David van Dijk, Rex Ying

    cs.AI · cs.CL · cs.SE

    Coding agents tackle successive tasks on an evolving repository, carrying forward edits and writing memory before the next task is known. Selecting memory for unknown next tasks requires balancing future usefulness against the costs of writing and reading it. The actor must also decide when acting on available memory saves effort as the task unfolds. We introduce Coding-Repository Memory (CoReMem), a cost-internalizing framework that guides...

    arxiv.org/abs/2611.17316 · PDF

  3. 03

    Classical Energies Learn to Reason 1,000x Faster than Looped Models

    Benjamin Hoover, Hugh Blayney, James C. R. Whittington

    cs.AI · cs.LG

    Looped models have emerged as a prominent paradigm for reasoning, with successes on simple reasoning puzzles such as Sudoku-Extreme and Maze-Unique. However, these models can be unstable, slow to train, and use many parameters and FLOPs to solve simple puzzles. Descent on an energy not only mitigates these issues but also offers advantages: built-in early stopping, compute that adapts to problem difficulty, fast training without...

    arxiv.org/abs/2611.17309 · PDF

  4. 04

    LiveGeo: Benchmarking Geographic Agents in Continuously Evolving Worlds

    Pengcheng Zhou, Xuanyu Liu, Yanchen Yin, Tianjie Ju, Bobo Li, Shengqiong Wu, Hao Fei, Mong-Li Lee, Wynne Hsu

    cs.AI

    We introduce GeoWorld, a controllable and continuously evolving geographic environment platform for LLM agents, and LiveGeo, a benchmark for evaluating reliable decision-making in real-world geographic environments using GeoWorld. Unlike existing evaluations that largely reason and plan over fixed geographic states, GeoWorld is grounded in real-world geographic structure and allows external world states to evolve along their own temporal...

    arxiv.org/abs/2611.17267 · PDF

  5. 05

    Ballad: Bandit-Based LLM Routing for Automated Heuristic Discovery

    Samidha Verma, Ankit Anand, Sayan Ranu

    cs.AI

    Modern automated heuristic discovery (AHD) systems increasingly rival hand-crafted heuristics by leveraging Large Language Models (LLMs) to iteratively mutate and refine solutions. A natural assumption is that more powerful and more expensive models consistently yield better heuristics. We challenge this empirically: across multiple NP-hard combinatorial optimization problems, we find no consistent advantage for larger, costlier models. This...

    arxiv.org/abs/2611.17241 · PDF

  6. 06

    Al-Ghasali: A Computational Framework for Simulating Islamic Jurisprudential Rulings via Finite State Automata and Large Language Models

    Elnaserledinellah Mahmoud Abdelwahab

    cs.AI · cs.FL

    This paper presents Al Ghasali, a computational framework designed to formalize and simulate Islamic jurisprudential (Fiqh) rulings. Building upon recent set theoretic formalizations of al sabr wa al Taqsim that extract minimal operational rules as simple Horn clause logical programs, this work proves that the semantics of closed Fiqh chapters collapse completely to deterministic Finite State Automata (FSA). We establish a formal...

    arxiv.org/abs/2611.17235 · PDF

  7. 07

    Cortex-FL: Agent-Mediated Collaboration for Federated Learning

    Rui Sun, Jinfeng Peng, Zehua Cheng, Jiahao Sun, Zhipeng Wang

    cs.AI · cs.MA

    Federated learning (FL) enables independent data owners to train models collaboratively without centralizing raw data. However, identifying collaborators, preparing training tasks, and coordinating execution and incentives hinder its practical adoption by organizations without specialized expertise. We present Cortex-FL, an agent-native FL system that enables users to express learning objectives in natural language and delegate the...

    arxiv.org/abs/2611.17186 · PDF

  8. 08

    Actor, Judge, or Teacher? Understanding Decision Models in Long-Horizon Agents

    Haochen Liu, Qianhao Zhu, Zixuan Wang, Dingming Li, Tongbo Chen, Peng Qiu, Yingqi Qu, Weiming Lu, Jun Xiao, Yongliang Shen

    cs.AI · cs.CL

    Decision models answer a question with a typed output, such as a choice among options with a probability for each, so one model can choose an agent's actions, evaluate actions already taken, or score every action to teach a policy with reinforcement learning. Prior work has studied them mainly as actors, judging their usefulness by how well they act. We ask whether a decision model that acts poorly can still teach well. We compare three...

    arxiv.org/abs/2611.17167 · PDF

  9. 09

    Cited but Unused: Parametric Provenance in Retrieval-Augmented Generation

    Tanzeel Abbas, Tehseen Zia, David Windridge

    cs.AI

    Retrieval-augmented generation systems attach citations to attribute claims to their sources. These citations frequently misstate provenance, and standard verification cannot detect this. We measure provenance by counterfactual value substitution: a fact in the retrieved passages is replaced with a false variant and the model re-queried. We find that across five sizes of one model family and a second comparator family, 1.2% to 15.7% of...

    arxiv.org/abs/2611.17161 · PDF

  10. 10

    CapLite: Prompt-Injection Defense for Small Language Model Agents without Model-Written Security Artifacts

    Zimo Xu, Wenzhuo Liu, Hideki Nakayama

    cs.AI · cs.CL · cs.CR

    Enforcement defenses against prompt injection, such as CaMeL, Progent, IPIGuard and DRIFT, ask the agent's own model to write a security artifact (a program, a privilege policy, a dependency graph or a constraint list) that code then enforces. We ask whether small language model (SLM) agents can be trusted to write these artifacts. Across 15 open-weight models, 13 of them between 1.7B and 12B parameters, they cannot: the policies, graphs and...

    arxiv.org/abs/2611.17115 · PDF

  11. 11

    Speed-to-Power Dominates Energy Costs for AI Data Centers: Technoeconomic Analysis of Powering AI in the Continental United States

    Alex C. Newkirk, Daniel L. Gerber, Erica R. H. Fuchs, Alex Hubbard, M. Granger Morgan, Arman Shehabi, Sarah J....

    cs.AI · eess.SY

    The rapid growth of artificial intelligence is driving demand for new data centers at large scale and on short deployment timelines. To power them, firms connect to the commercial grid or contract generation directly, but interconnection and gas-turbine delays now incentivize on-site generation. We compare grid-connected and off-grid data center energy infrastructure (AC- and DC-coupled solar-plus-storage, islanded natural gas, and grid...

    arxiv.org/abs/2611.17098 · PDF

  12. 12

    Reasoning Supervision and Capability Retention in LoRA Domain Adaptation

    Saleh Ashkboos, Dhruv Desai, Lavinia Ghita

    cs.AI · cs.CL · cs.LG

    Fine-tuning foundation models on financial data has a wide range of applications, including identifying event types from news, monitoring risk and compliance language, and answering questions over filings and earnings calls. In this setting, the main challenge is to improve task performance without degrading the generalization capabilities of the model. In this paper, we present an extensive set of ablations for fine-tuning Qwen3-8B with...

    arxiv.org/abs/2611.17072 · PDF

  13. 13

    Your Vision Foundation Model Is Secretly an EEG Foundation Model

    Guoan Wang, Feng Liu

    cs.AI

    Electroencephalography (EEG) foundation models are pretrained on thousands of hours of recordings, yet their frozen features transfer poorly to downstream tasks, and this transfer does not consistently improve with larger models or more pretraining data. We show that a vision foundation model that has never seen EEG is a stronger frozen EEG encoder than these specialized models, once the signals are rendered as images that a vision...

    arxiv.org/abs/2611.17031 · PDF

  14. 14

    Skill Adapter: Personalized Modification and Online Routing of General-Purpose Skills

    Qijia Zhuang, Yanyi Gou, Wenbin Ma, Yuxiang Ren

    cs.AI

    Large language model (LLM) agents use external skills to reuse task procedures and experience with tools. General-purpose skills describe shared execution procedures, while specific tool choices, operating practices, and output requirements vary across users. In long-horizon tasks, subgoals, available inputs, and environmental states change as execution progresses. Agents must select currently applicable skills from an expanding skill pool...

    arxiv.org/abs/2611.17007 · PDF

  15. 15

    AnalogLayoutWorld: An Open Benchmark for Agentic Analog Layout Design

    NovaSilicon Team

    cs.AI

    Coding agents have demonstrated strong capabilities in software development, yet their ability to tackle long-horizon engineering tasks governed by physical constraints remains less understood. We study this question through analog circuit layout, which demands domain knowledge, geometric reasoning, and iterative interaction with design and verification tools. We introduce \textbf{AnalogLayoutWorld}, an open-source agent benchmark with 40...

    arxiv.org/abs/2611.16991 · PDF

  16. 16

    Primer: An AI Framework for Instructor-Centered Educational Simulation Creation

    Ethan Mollick, Lilach Mollick, Ben Przystanski, LJ Ciccarelli, Natalie Bach, Laura Zarrow

    cs.AI

    Educational simulations are a well-established pedagogical technique that gives learners opportunities to apply knowledge, respond to challenges, and reflect on their performance. High-quality simulations, however, are difficult to build, requiring instructor input, scenario design, character development, scaffolding, technical implementation, and repeated revision. This paper presents Primer, an open-source, LLM-agnostic AI-supported system...

    arxiv.org/abs/2611.16986 · PDF

  17. 17

    Compiling Known Rules into Compact Neural Agents: Weight-Space Programming on Unseen Games

    Jens Lehmann

    cs.AI · cs.LG

    Weight-space programming (WSP) uses language models to construct neural network weights without training. We test whether known game mechanics can be compiled into compact agents that generalise to held-out levels, renderings and start states within a game family. Writers receive simulator source with held-out level data removed for 20 privately authored, unpublished ARC-AGI-3-style game families. With a fixed 57k-parameter recurrent...

    arxiv.org/abs/2611.16981 · PDF

  18. 18

    The Value of Thinking: Learning When to Reason in Hybrid Decision Models

    Zhengxu Yu, Ke Xu, Meng Fang, Haitham Ammar, Weilin Luo, Jun Wang

    cs.AI

    Existing adaptive-reasoning methods shorten the explicit reasoning a model writes, or skip it by switching modes; either way the answer is still written out token by token. \emph{Rather than deciding how much to think}, we explore a different paradigm, \emph{zero-or-$T$ thinking}: a single model either answers from the implicit thinking inside one forward pass, generating no token, or performs full autoregressive reasoning at a cost of $T$...

    arxiv.org/abs/2611.16961 · PDF

  19. 19

    S1-Evo: Experience-Guided Evidence Competition Attacks on Typed System-1 Decision Models

    Kaixiang Wang, Junjie Li, Zhaojiacheng Zhou, Jiong Lou, Jie Li

    cs.AI

    Typed System-1 (S1) decision models are increasingly deployed in LLM agents for routing, moderation, and authorization to cut inference cost, yet untrusted context can still manipulate typed outputs and alter execution branches. Unlike autoregressive System-2 (S2) models, S1 interfaces score dynamic rules and options without token-by-token decoding, mismatching attacks targeting text continuation or explicit override commands. We propose...

    arxiv.org/abs/2611.16937 · PDF

  20. 20

    Universal Infectious Disease Forecasting with Mantis 2

    Carson Dudley, Reiden Magdaleno, Yutong Bi, Anthony Valencia, Xiaofeng Liu, Marisa Eisenberg

    cs.AI · q-bio.PE

    Public health agencies need to anticipate how outbreaks will unfold, when they will peak, and how long demand on health services will remain elevated. We previously developed a foundation model, Mantis, which was trained entirely on simulated outbreaks---enabling us to generate the diversity and scale of training data needed to support forecasting across diseases. However, our previous work left unresolved when simulation improves predictions...

    arxiv.org/abs/2611.16935 · PDF

  21. 21

    CADET: Construction of PCB Routing Instances with Executable Demonstrations

    Hyungseok Song, Won-Seok Choi, Seohui Bae, Han-Seul Jeong, Junseok Park, Youngjoon Park, Soonyoung Lee

    cs.AI · cs.LG

    Printed circuit board (PCB) routing is the stage of physical layout that finds paths connecting the placed pads of each net. Public datasets in this domain are few, and most contain only the final states of routed boards, not demonstrations of the electronic design automation (EDA) engine actions that produce them. To close this gap, we propose CADET (Constructing executAble Demonstrations for Engine-grounded Training), which jointly...

    arxiv.org/abs/2611.16913 · PDF

  22. 22

    A Modular Framework for ESG Prediction through Domain-Specific Language Modeling and Graph Learning

    Sofia Baiocco, Gianluca Bonifazi, Christopher Buratti, Michele Marchetti, Camilla Mazzoli, Federica Parlapiano,...

    cs.AI

    Environmental, Social and Governance (ESG) scores are increasingly used to evaluate corporate sustainability, supporting investment decisions, ensuring regulatory compliance and assessing risk. However, current ESG evaluations largely rely on proprietary methodologies that often produce inconsistent ratings. This motivates the development of data-driven prediction frameworks. In this paper, we present ESGPred, a modular framework for...

    arxiv.org/abs/2611.16831 · PDF

  23. 23

    Scale-Induced Semantic Shift in Visual Prompt Injection Against VLMs and Web Agents

    Yiheng Zhao, Runze Ji, Chenyu Yi, Yi Yu, Bingquan Shen, Alex Kot, Xudong Jiang

    cs.AI

    Visual content in multimedia systems may be resized, compressed, or re-rendered before it is interpreted by a vision-language model. We study a security failure mode in which these transformations change the machine-readable semantics of an image: a textual instruction is not recovered at a $512\times512$ presentation resolution under our evaluation protocol but becomes recoverable after aggressive downsampling. We formulate this behavior as...

    arxiv.org/abs/2611.16744 · PDF

  24. 24

    Mind the Accuracy-Approval Gap: How Users Evaluate Sycophantic AI in Everyday Tasks

    Wajiha Naveed, Brandon Fain

    cs.AI

    Large language models (LLMs) often exhibit sycophancy, a tendency to agree with users, flatter or affirm them, and preserve their face, even when independent judgment or critical feedback would be more useful. Prior work has largely evaluated sycophancy through benchmark evaluations, but less is known about how users perceive and respond to sycophantic AI in everyday tasks. We combine benchmark evaluations with two large-scale user studies....

    arxiv.org/abs/2611.16722 · PDF

  25. 25

    Acoustic Respiratory Phase Detection on Mobile Devices

    Julian Szymanski, Tomasz Sankowski, Piotr Sulewski, Iwo Czartowski, Javier Medina Quero

    cs.AI · cs.LG

    Breathing monitoring is important for well-being, stress regulation, and guided breathing exercises, yet existing approaches often rely on contact-based sensors or controlled environments. This paper presents a non-invasive framework for respiratory phase detection using acoustic signals recorded on commodity smartphones. The proposed hybrid CNN-Transformer architecture combines local spectral feature extraction with long-range temporal...

    arxiv.org/abs/2611.16710 · PDF

  26. 26

    When Expert Disagreement Hurts: Prestige and Selectivity in LLM Decision Revision

    Yupeng Tang, Mingfeng Lin

    cs.AI · cs.CL

    When language models revise a decision after another agent disagrees, neither reversal counts nor final accuracy shows whether they are fixing mistakes or abandoning correct answers. We introduce a controlled two-pass audit that holds the question, the evidence, and the model's initial answer fixed and varies only the revision context: neutral reflection, anonymous disagreement, or disagreement attributed to a domain expert. For binary...

    arxiv.org/abs/2611.16694 · PDF

  27. 27

    Natural Gradient Learning in Predictive Coding through Lateral Circuits

    Lhea Beumer, Sander de Haan, Niclas Pokel, Pau Vilimelis Aceituno, Benjamin F. Grewe

    cs.AI

    Predictive coding (PC) trains neural networks through local energy-minimization dynamics without depending on a global error signal that backpropagation (BP) requires. Although PC is a promising alternative algorithm for efficient learning, the computational cost of inference dynamics currently outweighs the resulting learning benefits in practice. In this work, we take inspiration from optimization theory to extract more learning benefit...

    arxiv.org/abs/2611.16666 · PDF

  28. 28

    InertiaMPDD: Multimodal Personalized Depression Detection via Emotional Inertia-Inspired Dynamics Modeling

    Changzeng Fu, Songyang Wang, Chang Gao, Xinyi Zhang, Peilin Li, Mo Meng, Jiarui Wu, Mingze Li, Hongwei Ding, Shiqi...

    cs.AI

    Multimodal depression screening estimates risk from speech, visual behavior and language. Current methods mainly predict labels, with limited evidence of departures from a non-depressed reference. Recording-level supervision also leaves fine-grained emotional dynamics unannotated. Motivated by emotional inertia, the persistence of affect, InertiaMPDD learns healthy next-state patterns using a world-model-inspired latent predictor. Using...

    arxiv.org/abs/2611.16647 · PDF

  29. 29

    Safety as a Budget: Calibrating the Control Channel of Constrained GRPO for Vision-Language Models

    Bo Han

    cs.AI · cs.CV

    Reinforcement learning can teach vision-language models (VLMs) to decline harmful image-text requests, but how safe the result becomes is set indirectly, through reward weights found by trial runs. Stating safety as budgets on the rate of harmful assistance and the rate of over-refusal, enforced by Lagrange multipliers inside GRPO with an off-the-shelf scorer as the cost, is the natural fix, and it fails twice. The multiplier compares the...

    arxiv.org/abs/2611.16628 · PDF

  30. 30

    Folio: Recoverable Multi-Resolution Context Folding for Long-Horizon Language Agents

    Yubo Ruan, Tao Peng, Jiao Zhang, Chuanguo Ma, Lei Xu, Han Zhou, Wenwu Wang, Xiafei Lv, Xingjie Zhou, Guiju Fan, Hao...

    cs.AI

    Long-horizon language agents accumulate tool results and replies until the history no longer fits the context window. Current agents shrink this history by having a model summarize it, so each compaction rereads and rewrites the history it replaces, and cache-aware triggers decide when to compact while taking the size of the result as given. We present Folio, a context manager that records, folds, and recovers history through one set of...

    arxiv.org/abs/2611.16627 · PDF

  31. 31

    Studies on Sign Language Retrieval in Low-Resource Dictionary Settings

    Ushnish Sarkar, Vineet Kumar Rakesh, Bhaswar Chattopadhyay, Tapas Samanta

    cs.AI

    Most sign languages have no annotated corpus, only small dictionaries with one or a few example videos per sign. This study examines how well a pose encoder trained on a single sign language serves such languages without any target-language training. An encoder trained with metric learning on American Sign Language (ASL-Citizen) is evaluated frozen on six datasets of Turkish, Russian, Indian, Argentinian, Pakistani and Sri Lankan sign...

    arxiv.org/abs/2611.16621 · PDF

  32. 32

    A Dual-Branch Graph and Convolutional Network for Interpretable Movement EEG Classification

    Maryam Ostadsharif Memar, Behzad Nazari

    cs.AI · cs.HC · cs.LG · eess.SP

    Decoding upper-limb movements from scalp electroencephalography (EEG) is an important problem for brain-computer interfaces (BCIs), but many deep learning models provide limited insight into the brain regions underlying their predictions. We propose a two-branch architecture that combines an LGGNet-inspired local-global graph branch with an EEGNet-style convolutional branch for movement-versus-rest classification. The graph branch groups 61...

    arxiv.org/abs/2611.16609 · PDF

  33. 33

    Singularity-Bench: Can Agents Build Agents?

    Yang Zhou, Krish Agarwal, Zhuoming Chen, Zerui Wang, Zhenyu Zhang, Wenshuang Li, Xinpeng Wei, Zhichen Zeng, Jingyu...

    cs.AI

    Frontier AI agents increasingly succeed on realistic, long-horizon tasks and are beginning to improve the systems through which they operate. Yet existing benchmarks often restrict agents to narrow action spaces, use simplified environments, or rely on verification methods that are unreliable for evaluating arbitrary agent-generated systems. We introduce Singularity-Bench, an open-ended benchmark for autonomous AI development with six...

    arxiv.org/abs/2611.16591 · PDF

  34. 34

    AstroMemBench: A Benchmark for Memory Systems in Embodied Spacecraft Agents

    You Wu, Guhong Zhang, Hongwei Li, Xinyue Hong, Yuan Jia

    cs.AI · cs.RO

    Long-term spacecraft autonomy requires embodied agents to use operational history under communication delays, time-critical operations, environmental uncertainty, complex physical interactions, power and computational constraints, and safety and reliability requirements. We introduce AstroMemBench and a Scenario-Challenge-Capability design method that maps these requirements to executable memory tests. The benchmark covers 16 memory...

    arxiv.org/abs/2611.16590 · PDF

  35. 35

    Large Language Models as Digital Twins: a Distribution-Aware Questionnaire-Based Evaluation

    Francesco Di Cursi, Chiara Boldrini, Andrea Passarella, Marco Conti

    cs.AI · cs.CY

    This paper investigates whether Large Language Models can answer a personality questionnaire as a specific individual would. Given a user's social-media posts, the model completes the BFI-2-60 Big Five questionnaire as that user. The predicted responses are converted into trait scores and compared with the user's actual scores. We evaluate GPT-4, Gemma, Llama 3.1, and Mistral on the MyPersonality dataset. To determine whether predictions...

    arxiv.org/abs/2611.16586 · PDF

  36. 36

    SPARC: Accurate Photonic Matrix Multiplication via Representative Vectors

    Yasuhiro Fujiwara, Tatsuhiro Nakamori, Hideyuki Kawashima

    cs.AI

    Photonic neural network accelerators have emerged as a promising solution for reducing the power consumption of deep neural network (DNN) inference by executing matrix multiplication on analog photonic hardware. However, their inference accuracy is limited by low-bit quantization required for photonic processing and by analog photonic noise. This paper proposes an approach for improving inference accuracy by exploiting the high similarity...

    arxiv.org/abs/2611.16561 · PDF

  37. 37

    AI has its own style in mathematical proving

    Xiaokai Li, Ziyu Zhou, Qibin Cheng, Yangcheng Wu, An Zeng, Ying Fan

    cs.AI

    As large language models increasingly generate mathematical proofs, whether they develop a proving style distinct from that of human mathematicians remains an open question. This question is particularly pressing as mathematicians increasingly voice concerns that proofs generated by large language models are difficult to interpret. Here we ask three large language models to independently reprove all 465 propositions of Euclid's...

    arxiv.org/abs/2611.16527 · PDF

  38. 38

    Lost in Delegation: Studying the Effectiveness of Task Orchestration in Generative Search

    Tamara Stojanovska, Elisabeth Kirsten, Leon Swazinna, Muhammad Bilal Zafar

    cs.AI · cs.CL

    LLMs have quickly evolved from models used in isolation to agentic systems that delegate tasks to external tools and other LLMs to solve complex assignments. This agentic augmentation has led to impressive capability gains. However, when and how delegation improves performance remains poorly understood. For example, it is unclear whether delegation helps when tasks involve post-cutoff information that the orchestrating LLM cannot reliably...

    arxiv.org/abs/2611.16526 · PDF

  39. 39

    SignRot: LLM Quantization with Massive Outlier-Aware Sign-Adjusted Rotation

    Jaehun Gim, Jaewoo Kim, Gyuwan Kim, Seo Yeon Park

    cs.AI

    While quantization compresses LLMs and accelerates inference, outlier activations impede efficient low-bit representation. In particular, massive outliers cause substantial performance degradation. Although rotation-based methods that rely on randomized Hadamard transforms for online inference aim to mitigate this, they can produce fragmented distributions with empty bins when a massive outlier dominates a token's activation. This...

    arxiv.org/abs/2611.16502 · PDF

  40. 40

    Recalibrating a Typed-Decision Model in an Afternoon: A Hands-On Recipe for Laya's Confidence Scores

    Mohammed Nayeem Khan, Aliyas Ahmad Misri

    cs.AI · cs.SE

    A typed-decision model such as Laya reads a text and a list of options that the caller defines, for example ticket categories, and returns a probability for each option. Code around it compares the top probability with a threshold to answer, abstain or escalate to a person. Earlier work reports, for a Turkish model, that temperature scaling can raise held-out calibration error (ECE). This tutorial gives a five-step recipe (measure, diagnose,...

    arxiv.org/abs/2611.16499 · PDF

  41. 41

    How many LLM-labelled rows does a decision encoder need, and how wrong can the labels be?

    Mohammed Nayeem Khan, Aliyas Ahmad Misri

    cs.AI

    A decision encoder such as Laya reads a question with named options (for example, which department should handle a ticket) and a text, and picks an option. It reads both in one forward pass and returns a probability for every option, without writing any text. We ask how many LLM-written training rows such an encoder needs and how wrong those labels may be. We ran 19 fine-tunes of Laya (ModernBERT-large) on nested subsets of a 2,818-row pool...

    arxiv.org/abs/2611.16498 · PDF

  42. 42

    ReA-Bench: Benchmarking Responsible Agent Auditing

    Zipeng Ye, Shenyu Dai, Yong Xie, Kun Wang, Jiyang Guan, Zhikai Chen, Jiaqi Weng, Jialing Tao, Hui Xue

    cs.AI

    As agents perform tasks autonomously in local and cloud environments, auditing their execution trajectories can help service providers identify risks and improve agent harnesses and foundation models. Our analysis of production and red-team trajectories shows that some risks are repeatedly missed across auditing configurations. Overall recall obscures which risks are missed and whether higher recall comes with more false positives on...

    arxiv.org/abs/2611.16493 · PDF

  43. 43

    Time and Space: A Dual-Axis, Evidence-Grounded Context Substrate for Personal Agents

    Haitao Cheng, Jerry Hu, Longdong Mao, Dong Huang, Dongming Li, Lijuan Zhang, Mengting Zhang

    cs.AI

    We argue that a binding constraint for personal agents is not model capacity but the form in which context is represented: the agent does not know which entity a phrase denotes, when a fact held, or which source record licenses a claim. We call the missing representation spatio-temporal context (STC) and define it on two axes. The temporal axis carries event time, validity intervals and ingestion time. The spatial axis is a relational space...

    arxiv.org/abs/2611.16492 · PDF

  44. 44

    HeMeR: Heterogeneous Memory Reconciliation for Embodied Agents via Structured KV Reuse

    Saehun Chun, Wonje Choi, Jinwoo Jang, Taeyoon Kwack, Honguk Woo

    cs.AI

    Embodied agents make decisions by combining information from heterogeneous memory modules, including declarative memory for explicit knowledge, procedural memory for learned routines, and working memory for current observations. During interaction, the memory contents required for decision making change with the agent's state, goal, and task progress, while many contents remain shared across consecutive decisions. However, existing memory...

    arxiv.org/abs/2611.16487 · PDF

  45. 45

    Contain, Conform, Compare (Extended Version): A Red-Teamed Evaluation Kit for Small Coding Agents and the Full Record of Its Experiments

    Nguyen Minh Thang

    cs.AI

    A hosted score in the Gemma 4 Developer Agent competition is one noisy number, so development needs a local evaluator that is fast, safe for agent-written code, and matching the hosted scorer's prompts. drydock-eval evaluates a small coding agent (Gemma 4 E4B) at about 250 runs per hour on one RTX 5090. Contain runs each job in a fresh container without network and passed 200 scripted escape tests; conform provides eight checks that compare a...

    arxiv.org/abs/2611.16485 · PDF

  46. 46

    One Model, Two Precisions: Does Disagreement Between Quantized Copies Tell You When a Small Model Is Wrong?

    Mohammed Nayeem Khan, Allan Kevin T

    cs.AI

    Local language models often exist at several precisions, and quantization is known to change individual answers. This study asks whether the disagreement between two precisions of the same weights, an 8-bit copy that answers and a lower-precision copy that reads the same prompt, works as a per-question error score for abstention, escalation and re-asking. The cost is one extra forward pass over fewer bytes, with no sampling and no training....

    arxiv.org/abs/2611.16478 · PDF

  47. 47

    How Should Planning Agents ReSHAPE Their Search Space?

    Yilin Zhang, Xinran Zhao, Tong Chen, Ziming Yuan, Tongshuang Wu

    cs.AI · cs.CL

    Planning agents and benchmarks treat a user's initial specification as fixed. Yet the requests users write exclude plans they would gladly take, since they rarely discover the possible trade-offs they would accept until seeing the options. Agents already revise requests through interaction, but whether this helps planning is unknown. We formalize this step as the ReSHAPE task, which judges a revision by whether its search space matches the...

    arxiv.org/abs/2611.16466 · PDF

  48. 48

    Fine-Tuned Small Language Model for Synthetic Clinical Data Generation and Predictive Healthcare Analytics

    Mihnea Sebastian Burlacu, Ionut Anghel, Tudor Cioara

    cs.AI

    The reduced availability of medical datasets represents an important challenge in the development of predictive models for remote healthcare solutions, especially when the available data are imbalanced or difficult to extend through traditional methods. Small Language Models (SLMs) have become a promising alternative to Large Language Models (LLMs) for addressing these limitations due to their lower computational requirements and adaptability...

    arxiv.org/abs/2611.16460 · PDF

  49. 49

    Rational Alignments of Superintelligences via Debates

    Thanawat Sornwanee

    cs.AI

    Artificial superintelligences (ASI) is artificial intelligences with greater capability. However, as human principal has to use it, we have to ensure that the agent will perform in the interest of the human. We investigate the framework of ASI-assisted question answering where ASI agents know the correct answer but the human does not. We provide some example of mechanism for rational alignment, where the agent utility is unchanged, but the...

    arxiv.org/abs/2611.16455 · PDF

  50. 50

    FPSRG: Heterogeneous User Simulation First-Person Post-Training and Multidimensional Semantic Response Grids

    Ruimin Pei, Haibo Liu, Fang Zhang, Xunhua Guo

    cs.AI

    Simulating heterogeneous individuals with large language models is an active research direction, and heterogeneous user simulation requires models with different characteristics. We study profile construction: given dimensions, items, and scoring rules, build model configurations that can be retrieved by multidimensional target scores. We introduce First-Person Semantic Response Grids (FPSRG). Shared post-training first teaches the model to...

    arxiv.org/abs/2611.16445 · PDF

  51. 51

    Small Language Models for Inference-Capability Routing: Effects of Model Capacity and Prompt Optimization on Downstream Quality and Efficiency

    Sailendra Kolluru, Maheshkumar Duvvarapu

    cs.AI

    Optional reasoning, retrieval, web search, and tool use can improve large language model responses but incur unnecessary computation when activated indiscriminately. This study investigates whether prompt optimization can compensate for limited router capacity and whether classification gains translate into downstream efficiency. The proposed framework uses prompt-driven small language models to make four independent capability decisions,...

    arxiv.org/abs/2611.16414 · PDF

  52. 52

    Evidence-Governed Adoption of Self-Generated Updates in Autonomous AI Agents

    Subodh Lonkar

    cs.AI · cs.MA

    Autonomous agents modify prompts, memories, tools, workflows, and policies using interaction histories. Yet a plausible modification is not necessarily suitable for persistent adoption: candidate selection is adaptive, evaluators may be imperfect, and local gains can hide degradation against an earlier baseline. We introduce Evidence-Governed Evolution (EGE), a framework for governing adoption of self-generated agent modifications. EGE...

    arxiv.org/abs/2611.16378 · PDF

  53. 53

    DIAGNO: Diagonal Spherical Neural Operators for Heterogeneous Earth Dynamics Modeling

    Herui Li, Bin Lu, Haonan Qi, Lei Zhou, Luoyi Fu, Xinbing Wang, Meng Jin

    cs.AI · cs.LG

    Accurate forecasting of Earth's dynamic systems is vital in geophysics, where neural operators offer a powerful data-driven paradigm. Standard operators often treat the Earth as a flat Euclidean plane, introducing geometric artifacts. In contrast, Spherical Neural Operators (SNOs) resolve this mismatch by operating within the spherical spectral space, naturally adapting to spherical geometries. However, for computational efficiency, existing...

    arxiv.org/abs/2611.16356 · PDF

  54. 54

    From More to Better: Causal Inference and Digital Experimentation in the Age of AI

    Winston Chou, Mårten Schultzberg, Lo-Hua Yuan, Wenjing Zheng, Avi Feller, David Holtz, Widad Machmouchi, Sven...

    cs.AI · stat.AP

    Artificial intelligence (AI) is quickly expanding the capacity of organizations to produce and analyze data. We argue that this expansion shifts the leverage of data scientists from performing individual analyses to assessing the credibility and importance of findings and determining when evidence generalizes across contexts. Drawing on a roundtable of academic researchers and industry practitioners, we examine three ways in which data...

    arxiv.org/abs/2611.16335 · PDF

  55. 55

    Benchmarking AI risk behaviors

    Luhan Mikaelson, Robert Adragna, Emmett Brosowsky, Hayley Clatterbuck

    cs.AI · cs.LG

    We evaluate LLM risk propensities across a range of contexts and task demands. We evaluate models for how risk averse or risk tolerant they are in various conditions, as well as how stable and consistent their behavior is across conditions. We present a toolkit for developing model risk profiles that can be used to predict model behavior and which can be adapted to include new evaluations of risk propensities. We also examine how these...

    arxiv.org/abs/2611.16318 · 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.