cs.AI · 2026-11-10 · No. 169

Artificial Intelligence, 2026-11-10.

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

01 — The papers

39 entries
  1. 01

    Shortcuts and Boundaries: Verifiable RL Misalignment and Contextual Safety Learning

    Xinjie Shen

    cs.AI · cs.CR

    Reinforcement learning (RL) can improve an agent's task capability while reinforcing behavior that violates contextual execution requirements. We study this reward-driven misalignment, including reward hacking, through verifiable reward--context conflicts, where compliant task completion remains feasible while some executable shortcuts earn more reward than every compliant strategy. Encoding these conflicts in task dynamics lets us generate...

    arxiv.org/abs/2611.12865 · PDF

  2. 02

    MaxIM: Maximally Informative Incremental Summarization via Reinforcement Learning

    Jihwan Jeong, Guy Tennenholtz, Yinlam Chow, Chih-Wei Hsu, Craig Boutilier

    cs.AI · cs.LG

    AI systems must often maintain bounded memory of unbounded interaction histories. However, optimizing the memory representation, and its updates, for downstream task utility is difficult for standard reinforcement learning (RL) due to severe credit assignment bottlenecks induced by sparse, delayed rewards. We introduce MaxIM (Maximally Informative Incremental Memory), a framework that formulates incremental summarization as a...

    arxiv.org/abs/2611.12825 · PDF

  3. 03

    Automated Knowledge Acquisition Pipeline for Disassembly Instructions: A Comparison of NLP and Generative AI Frameworks

    Tim Schnieders, Tareq Maximilian Gabriel Ahrari, Oliver Petrovic, Christian Brecher

    cs.AI

    The push towards circularity and Re-X principles presents a challenge to SMEs, particularly due to increasing product complexity that impedes the adoption of disassembly automation. This paper introduces and compares two frameworks for extracting disassembly instructions from unstructured information sources, such as disassembly manuals. Our goal is to transform natural language text into a structured, curated and machine-readable format. We...

    arxiv.org/abs/2611.12816 · PDF

  4. 04

    LogCDM: Interpretable Log Anomaly Detection via Behavioral Graph Drift and Adaptive Signal Fusion

    Suryansh Talukdar, Taha Sarwat, Jin Soung Yoo

    cs.AI

    Log-based anomaly detection is increasingly dominated by large pretrained models, from BERT-scale encoders to 8B-parameter language models, which require GPUs at inference time and are difficult to deploy on the monitoring nodes where logs are produced. We present LogCDM, a compact detector that scores each log session using three complementary signals: the next-event surprise of a small causal Transformer, the distance between a...

    arxiv.org/abs/2611.12775 · PDF

  5. 05

    Sage-Taiyi: A Metacognitive Architecture for Scientific Discovery

    Weida Wang, Benteng Chen, Yigeng Jiang, Shuchen Pu, Weiping Shen, Zichao Liu, Yulin Su, Zitong Wang, Siyu Zhou, Zifu...

    cs.AI

    We introduce Sage-Taiyi, a metacognition-inspired architecture that uses accumulated scientific understanding to guide what to investigate next and how to investigate it. Through explicit monitoring and control, the system revises its understanding of evidence, assumptions, and unresolved questions, then uses these assessments to adapt research targets and select reusable reasoning methods. On Taiyi-Bench, an AI co-scientist ideation...

    arxiv.org/abs/2611.12762 · PDF

  6. 06

    Interpretability Is Not Model-Specific

    Marcus Armstrong, Navid Ayoobi, Pradham Mummaleti, Alexander Chulzhanov, Arjun Mukherjee

    cs.AI

    Interpretability tools are usually built for one model at a time: a refusal direction, a truthfulness probe, or a steering vector is found with labeled data inside the model it explains. We ask whether such tools can be carried to other models through a map between residual streams fit only on unlabeled prompts. We transfer a refusal direction, tested causally by addition and ablation, and two read-out tools, a correctness direction and a...

    arxiv.org/abs/2611.12675 · PDF

  7. 07

    TrialDesignBench: Benchmarking Language Models for Phase-I Trial Design Against Clinical Knowledge

    Yihan Hank Tang, Peng Yang, Jiayi Xin, Tianqi Shang, Xuyang Chen, Ying Yuan, Yi Lian, Qi Long

    cs.AI · cs.CL · stat.AP

    AI is used in much of the clinical trial pipeline. However, selecting the statistical design of a trial, a crucial step that determines how drug doses are tested on humans and evaluated, has seen almost no AI progress. LLMs appear to be a natural fit given their strengths in biomedical knowledge and statistical reasoning. Nevertheless, there is currently no appropriate way to evaluate such abilities because recent regulatory and...

    arxiv.org/abs/2611.12640 · PDF

  8. 08

    Beyond Sunny Skies: Using Large Language Models to Predict Urban Traffic in Adverse Weather

    Zhu Xiao, Kuan Feng, Tong Li, Chenxi Liu, Gang Wang, Zhuo Tang, Kenli Li

    cs.AI

    Urban traffic flow prediction is a cornerstone of intelligent transportation systems, yet accurate forecasting under adverse weather conditions remains a significant challenge. Existing data-driven models, while effective for routine patterns, often struggle with the sparse data and complex non-linear shifts associated with rare meteorological events. These methods typically treat environmental contexts as shallow numerical features, failing...

    arxiv.org/abs/2611.12635 · PDF

  9. 09

    SciMARS: Multi-Agent Recursive Self-Improvement for Closed-Loop Scientific Discovery

    Weimin Wu, Han Liu

    cs.AI

    We propose SciMARS, a framework for recursive task-local adaptation of multi-agent harnesses in closed-loop scientific discovery. Multi-agent systems coordinate analysis, experimental design, and verification as scientific evidence evolves. However, two problems limit their effectiveness: (i) without shared memory, agents lose observations and repeat work; (ii) fixed role procedures, handoffs, and memory policies perpetuate mistakes despite...

    arxiv.org/abs/2611.12552 · PDF

  10. 10

    AuDiR: Diagnosing Audio Reasoning with Rule and Percept Interventions

    Chengwei Wei, Yi Ma, Nancy F. Chen

    cs.AI

    Answer accuracy alone does not distinguish failures in acoustic perception, rule knowledge, and rule application. AuDiR (Audio Diagnostic Reasoning) examines these distinctions through controlled input interventions. Each item contains an audio clip, a multiple-choice question, a task-general rule, and a textual description of the acoustic observations needed to answer. Three conditions progressively supply the rule and observations; a fourth...

    arxiv.org/abs/2611.12478 · PDF

  11. 11

    AutoBuddy: Evaluating Proactive, Always-On Agents on Task Discovery and Execution in a Simulated Workplace

    Shiqi Chen, Daniel Madrigal Diaz, Wei-Ning Chen, Gbola Afonja, Fangkai Yang, Rujia Wang, Chetan Bansal, Victor...

    cs.AI · cs.LG

    As LLM agents become more autonomous, they are increasingly expected to run as always-on assistants on a user's behalf, identifying work to be done and completing it without being asked. Yet existing benchmarks usually give the agent its task, whereas in knowledge work the requests sit in the user's workspace and the agent must first recognise which obligations exist. We study proactive task discovery and execution, in which an agent must...

    arxiv.org/abs/2611.12393 · PDF

  12. 12

    Reconstructing hourly traffic on every street of a capital from a sparse counting network: a graph neural network applied to Paris

    Xavier Jurado, C{é}dric Wemmert, Nicolas Reiminger

    cs.AI

    Micro-scale air quality models require hourly traffic data on every road segment, whereas permanent counters cover only a small part of the network. A graph neural network (GNN) was developed to reconstruct hourly traffic flows on the 32,163 road segments of Paris intra-muros from the 1,573 segments equipped with a counter (4.9%). The model adapts the Graph Neural Network for Urban Interpolation (GNNUI) to a real, sparse counting network....

    arxiv.org/abs/2611.12379 · PDF

  13. 13

    Detecting Shadow AI: Unsanctioned LLM Agents on Enterprise Endpoints: A Taxonomy, an Open Detector and a Controlled Evaluation

    Jeremy Canale, Fabien Soulis

    cs.AI · cs.CR

    Shadow IT, the use of technology that the IT organisation has not approved, is a long-standing governance problem. We argue that autonomous AI agents can make it grow much faster: agents make building tools nearly free, act with their user's privileges, and leave behind scripts, automations and MCP servers that are themselves unsanctioned. A simple compounding model shows that, under its assumptions, shadow IT grows exponentially once agentic...

    arxiv.org/abs/2611.12377 · PDF

  14. 14

    TANSAR: Editable and Attributable Correlation Matrix Memories under Correlated Keys, with Rule-Constrained Multi-Hop Knowledge Editing

    Abdulhady Abas Abdulla, Jiyan Salim Mahmud, Fatemeh Daneshfar, Hussein Mohammed Ali, Mourad Oussalah, Muhammad Bilal

    cs.AI

    Correlation Matrix Memories (CMMs) store associations as sums of rank-one outer products, providing closed-form addressability, exact deletion, and linear attribution. While classical analyses assume random, orthogonal keys, semantic encoders produce correlated representations. We analyse CMMs under correlated keys using frame-theoretic coherence: (i) capacity bounds yielding an encoder-independent limit $n \le d(1+\varepsilon^2)$ for mean...

    arxiv.org/abs/2611.12374 · PDF

  15. 15

    DForkTree: Accelerating Speculative Decoding with Fork-Aware Block Diffusion Draft Trees

    Zhicheng Zheng, Cheng Zhang, Chenkai Tang

    cs.AI

    Speculative decoding speeds up language models by letting a lightweight drafter propose several future tokens that the target model verifies in parallel. Block diffusion drafters such as DFlash draft a whole block in one forward pass, and DDTree builds a draft tree from their per-position distributions. Each of these distributions assumes that the drafter's own most likely continuation is correct. A tree, however, gains over a chain only on...

    arxiv.org/abs/2611.12356 · PDF

  16. 16

    Rethinking Radar 3D Perception: Representation Learning from Raw Spectra

    Miao Zhang, Mohamed Abdelsamad, Bin Yang, Sherif Abdulatif, Benedikt Loesch, Marco Altmann, Abhinav Valada, Bin Yang

    cs.AI · cs.CV · cs.LG · cs.RO

    Raw radar spectra are widely viewed as too cluttered and noisy for direct representation learning, motivating handcrafted reductions, sparse point clouds, or compact Doppler descriptors in radar perception. We challenge this assumption and argue that the main limitation lies not in the raw representation itself, but in the absence of a learning objective that separates structured signal from noise. Handcrafted reductions partially address...

    arxiv.org/abs/2611.12334 · PDF

  17. 17

    AMSchem: Automated Schematic Visualization of AMS Circuits via Verifiable Agentic Generation

    Yichen Shi, Zhiyuan Wang, Jianing Cui, Yao Lai, Jinting Zhang, Zhuofu Tao, Hongyang Wang, Zhiping Yu, Ting Jung Lin, Lei He

    cs.AI

    For decades, the netlist-to-schematic gap has remained a persistent challenge in design automation, especially for analog and mixed-signal (AMS) circuits. Netlists encode connectivity, not visual presentation, making their manual conversion into readable schematics time-consuming and dependent on expert conventions. The same gap leaves LLM-based design tools without structured visual feedback, forcing them to iterate on circuits they cannot...

    arxiv.org/abs/2611.12333 · PDF

  18. 18

    PACE-ECG: Patient-Aware Contrastive ECG Pretraining; Leveraging Longitudinal Structure for Transferable Representations

    Riccardo Cavarra, Lupo Lovatelli, Shaheim Ogbomo-Harmitt, Jakub Grzelak, Adelaide De Vecchi, Andrew King, Oleg Aslanidi

    cs.AI

    Foundation models for physiological signals are commonly evaluated on in-domain interpretation tasks, but their ability to transfer to longitudinal clinical prognosis across healthcare systems remains uncertain. We developed PACE-ECG, an ECG pretraining framework that combines contrastive learning across temporally neighbouring recordings from the same patient with clinically guided multitask supervision. We evaluated frozen ECG...

    arxiv.org/abs/2611.12307 · PDF

  19. 19

    Reconfigurable Action Theories: A Formal Foundation for Dynamically Composable Agent Harnesses

    Jianmin Ji

    cs.AI

    Action theories typically fix their vocabulary and causal laws, whereas agent harnesses can change their tools, providers, and policies during execution. We introduce Reconfigurable Action Theories (RAT), in which actions can change the action theory itself. A theory module in RAT contains a vocabulary, causal laws, and an initializer. A RAT configuration records the active modules and the world state. Module loading and unloading are...

    arxiv.org/abs/2611.12300 · PDF

  20. 20

    Depth as a Candidate Source: Portfolio Allocation for Recurrent Test-Time Scaling in Large Language Models

    Chaoyuan Hao, Wentao Yue, Yanyan Wu, Boyuan Gao, Tianyou Lai, Maolin Wang, Yongxin Ni, Hanwen Du, Youhua Li

    cs.AI

    Recurrent latent reasoning in large lanugage models (LLMs) scales test-time computation by increasing recurrent depth, naturally framing inference as a problem of deciding when to stop. We identify a previously overlooked limitation of this single-depth view through systematic preliminary analysis: deeper recurrence can lose correct solutions found at shallower depths, while depth-specific success sets remain broadly non-nested even after...

    arxiv.org/abs/2611.12293 · PDF

  21. 21

    Representational Alignment between Deep Neural Networks and Human Brain in Speech Processing under Audiovisual Noise

    Cheng Luo, Jian Zhu, Zhoujian Sun, Yunyi Qi, Yu Qi, Wenhui Sun, Wenyuan Yu

    cs.AI

    Speech comprehension in the human brain is an incremental process that begins with acoustic processing and advances to linguistic processing. While recent studies have revealed that the hierarchy of deep neural networks (DNNs) correlates with the ascending auditory pathway, the exact nature of this DNN-brain alignment remains underexplored. In this study, we investigate how DNN representations align with the brain's acoustic-to-linguistic...

    arxiv.org/abs/2611.12291 · PDF

  22. 22

    ECOS: Environment-Calibrated On-Policy Self-Distillation for Language Agents

    Chenhao Zhang, Zhongan Wang, Mingxuan Li, Hehe Fan, Zheng Zhu, Ming Li

    cs.AI

    On-policy self-distillation lets a language agent act as its own Teacher by conditioning on privileged context such as skills written from its own trajectories. Its guidance, however, is weighted by how much this context shifts token likelihoods rather than by whether it improves behavior, so errors in self-written skills return through later updates. We propose environment-calibrated on-policy self-distillation, which uses environmental...

    arxiv.org/abs/2611.12232 · PDF

  23. 23

    PARIS: A multi-agent LLM framework for end-to-end, PRISMA-guided systematic literature reviews with pre-synthesis corpus quality assessment

    Christophe Cruz, Hussam Ghanem, Samir Jabbar, Ait Kbir, Hocine Cherifi

    cs.AI

    Systematic literature reviews (SRs) remain slow and labor-intensive, and most automation tools address single stages of the workflow. We present PARIS (PRISMA Agentic Research Intelligence System), an open-source framework in which a conductor agent running in Claude Code orchestrates 15 specialized large language model (LLM) agents, from scoping a research question to exporting a manuscript draft. Agents are specified declaratively,...

    arxiv.org/abs/2611.12222 · PDF

  24. 24

    Learning to Act with World Models by Valuing What Comes Next

    Chenghao Gao, Zhi Zhang, Dian Jin, Yihe Pan, Doudou Zhou

    cs.AI

    A sparse terminal reward tells an agent little about its steps. Much of the missing information is implicit in the environment's dynamics, because each state transition can change the conditions for success long before the reward arrives. A world model trained on real transitions can learn to predict what each action changes, but a predicted observation does not by itself show whether success has become more likely. With a binary terminal...

    arxiv.org/abs/2611.12200 · PDF

  25. 25

    FraudBench: A Legal Evaluation of AI Deception

    Kevin Wei, Sumaya Nur Adan, Stephan Llerena, Mark Gitau, Jakob Merane, Anita Srinivasan, Colette Le Brannan, Keethan...

    cs.AI · cs.CY · cs.LG

    We introduce FraudBench, an evaluation of large language models' (LLMs) propensities to recommend, assist, or directly take actions that would constitute fraud under U.S. law. Our evaluation contains a novel dataset of 159 scenarios based on real-world U.S. court cases and validated by legal experts. We present each scenario to LLMs via three tasks at varying levels of autonomy: advising users, drafting messages for users to send, and acting...

    arxiv.org/abs/2611.12167 · PDF

  26. 26

    Let the Fixer Decide: Training a Code Localizer from the Fixer's Likelihood

    Khalil Hennara, Muhammad Hreden, Zeina Aldallal, Sara Chrouf, Safwan AlModhayan

    cs.AI · cs.SE

    Code localizers are usually trained to predict the files a reference patch edits, but the code a fixer needs to read is not the same as the code it changes. We propose Fixer-Guided Localization (FGL): the localizer proposes several localizations, a frozen fixer scores each by how likely it makes a verified patch, and the localizer is trained on these scores with weighted supervised fine-tuning, without running tests and without reinforcement...

    arxiv.org/abs/2611.12164 · PDF

  27. 27

    Toward Sustainable Agentic AI: Carbon Tradeoffs Across Iterative Self-Refinement and Tool-Augmented Coding

    Boris Ruf, Adrien de Mailly Nesle, Marcin Detyniecki

    cs.AI

    Agentic language model systems can improve performance either by iterating on their own outputs or by using external tools in grounded environments. While these strategies can reduce error rates and substitute for larger models in some settings, their environmental cost remains relatively underexplored. We present two complementary empirical studies that estimate the energy and carbon footprint of agentic AI across settings of increasing...

    arxiv.org/abs/2611.12128 · PDF

  28. 28

    System Optimizations for Cost-Efficient Agent Harnesses

    Jongseok Park, Jiaxiang Yu, Eric Zhou, Tony Hong, Sunga Kim, Yusuf Afifi, Ian Wong, Ion Stoica, Alvin Cheung

    cs.AI

    AI agent harnesses play the critical role of providing LLMs with an interface to a computing environment. Recent studies show that AI agents' task-execution accuracy depends mostly on the LLM used, while harness-side variances such as system prompts or tools have minimal impact. Rather, such harness-side variances show a larger impact on the cost of agent executions, achieving cost reductions up to 2.6 times on the same model and task. To...

    arxiv.org/abs/2611.12122 · PDF

  29. 29

    SCALE: Small-Model-First Concept Abstraction with LLM-Guided Experience Internalization

    Hong Su

    cs.AI · cs.RO

    Autonomous agents must continually acquire reusable knowledge from experience without relying on costly large language model (LLM) reasoning for every decision. However, existing experience-based approaches often struggle to transform accumulated observations and reasoning into compact knowledge that lightweight models can independently apply. This paper proposes SCALE, a small-model-first framework that integrates selective LLM reasoning,...

    arxiv.org/abs/2611.12120 · PDF

  30. 30

    Joi-Bench-Task: Benchmarking Task Coordination in Full-duplex Voice Agents through Interactive Simulation

    Xiangheng He, Mingjun Zhao, Zhehao Fan, Zhengjia Li, Xiaopeng Sun, Qingqing Xiao, Haolan Chen, Yu Xu

    cs.AI

    Full-duplex voice agents enable natural, hands-free interaction, allowing users to refine requests, redirect ongoing work, and seek clarification while the agent is speaking. However, existing voice-agent benchmarks insufficiently isolate coordination between task execution and conversation. We introduce a benchmark that assesses this coordination by examining whether agents track what is being executed, what has been completed, what has been...

    arxiv.org/abs/2611.12118 · PDF

  31. 31

    OGDA: Ontology-Grounded Data Agents for Reliable Analysis over Heterogeneous Data Lakes

    Boyi Zhang, Hong Ting Tsang, Yisen Gao, Qiao Xiao, LI Yufei, Haoyu Huang, Zhongwei Xie, Jiaxin Bai, Yangqiu Song

    cs.AI · cs.CL

    Full-pipeline data analysis over real-world data lakes requires LLM agents to locate and integrate information across large collections of tables with different schemas. Existing data agents follow task-specific exploration, which exhausts the context window in massive lakes. As the context fills, the agent's reasoning degrades, leading it to locate and process incorrect data files. These errors propagate into the final answer. To overcome...

    arxiv.org/abs/2611.12114 · PDF

  32. 32

    SkillDuet: Co-Evolving Models and Skills through Response Feedback

    Xingguang Ji, Ziqiang Dong, Yubo Zhang, Xi Leng, Yang Yang, Guanjun Jiang

    cs.AI · cs.LG

    During reinforcement learning, experience can be both internalized in LLM parameters and retained externally as reusable textual skills. Parameter updates alter the model's behavior and the interaction experience from which new skills are extracted. These skills, in turn, guide the model's subsequent interactions and parameter updates. As the model's capabilities evolve, previously beneficial skills may become redundant or detrimental. We...

    arxiv.org/abs/2611.12109 · PDF

  33. 33

    From Fluent Text to Ontology-Compatible Definitions: A Quality-Control Agentic Workflow

    Kun Feng, Chenchen Chu, Yan Liu, Haojie Sun, Jijun Tang, Chen Tian, Shuolin Xiao, Jianping He, Zhao Li

    cs.AI

    Biomedical ontologies are structured knowledge systems that must evolve continuously to represent newly emerging knowledge, but their manual maintenance remains time-consuming and laborintensive. Textual definitions are especially costly because they must be readable to humans and compatible with controlled entities, relations, and logical constraints. Large language models (LLMs) offer a promising way to assist ontology engineering tasks,...

    arxiv.org/abs/2611.12095 · PDF

  34. 34

    CRAFT-AI: Capability and Requirement Alignment for Flexible Manufacturing through Agentic AI

    Kiavash Fathi, Hans Wernher van de Venn

    cs.AI

    One of the fundamental needs for reaching resilient production infrastructure is flexible manufacturing, which requires translating changing production requirements into implementable system configurations. This paper introduces \textbf{CRAFT-AI}, an agentic AI approach combining natural language (NL) requirement interpretation, Asset Administration Shell (AAS)-based capability descriptions, and reusable engineering knowledge from existing...

    arxiv.org/abs/2611.12092 · PDF

  35. 35

    COMPASS: Composable Policy-Amortized Structured Search for LLM-Based Optimization Modeling

    Nguyen Le Minh Hoang, Van Duc Cuong, Bui Trong Duc, Huynh Thi Thanh Binh

    cs.AI

    Large language models offer a promising technique for translating natural-language optimization problems into solver code, but their reliability remains constrained by the quality of template retrieval. While recent structured methods improve over flat prompting through hierarchical taxonomy search, their traversal rules remain fixed or LLM-driven at inference time, leaving retrieval unable to improve from past successes and failures. This...

    arxiv.org/abs/2611.12060 · PDF

  36. 36

    Evaluating AI Agents for Industrial-Level Chip Floorplanning: A Framework and Empirical Study

    Nova-Silicon Team

    cs.AI

    Floorplanning is an early step in turning a logical circuit into a physical chip: it positions large circuit modules and constrains the space available for subsequent logic placement and wiring. These decisions affect congestion and timing, but their physical consequences emerge through downstream implementation. For AI agents, the task requires translating engineering constraints into spatial decisions whose quality cannot be judged by...

    arxiv.org/abs/2611.12048 · PDF

  37. 37

    Benchmarking language models and agents for scientific reasoning in evolving materials laboratories

    Xuyu Dong, Yixuan Li, Jianguo Huang, Feng Chen, Yiyun Zhou, Bo An, Zheng Liu, Da Shu

    cs.AI · cond-mat.mtrl-sci · cs.CE · cs.LG

    Large language models and the multi-agent systems built around them could accelerate materials discovery by connecting scientific knowledge with experimental decisions. Existing benchmarks establish capabilities in domain knowledge, multimodal interpretation and scientific tool use. As language models increasingly support materials research workflows, their ability to distinguish closely related material states and reason accurately with...

    arxiv.org/abs/2611.12014 · PDF

  38. 38

    Enhancing Multi-Step Chemical Mechanism Prediction with Graph-Guided Preference Data

    Yu Zhang, Ruijie Yu, Xuelin Zhao, Jinming Yang, Feng Zhu, Xiaokang Yang, Yaohui Jin, Yanyan Xu

    cs.AI

    Predicting multi-step chemical reaction mechanisms requires identifying plausible intermediates and correctly ordering the elementary reaction steps. Existing computational methods focus on single-step elementary reaction prediction, limiting their ability to generalize to unseen reaction spaces. We introduce a graph-guided framework for multi-step chemical mechanism prediction that leverages a chemical mechanism knowledge graph (ChemMechKG)...

    arxiv.org/abs/2611.12013 · PDF

  39. 39

    Infrathon: Benchmarking Language Agents for Real-World, Long-Horizon AI Infra Optimization

    Zhengyu Hu, Zheyuan Xiao, Yike Wang, Hamish Ivison, Haoyu Wang, Yige Yuan, Rulin Shao, Yuetai Li, Niqi Lyu, Yicheng...

    cs.AI · cs.CL

    In this work, we study whether frontier agent can continually improve real-world AI infrastructure over long horizons. We introduce Infrathon, a benchmark of diverse, long-horizon AI infrastructure optimization tasks across different levels. We evaluate six models across 150 runs with 24-hour budgets, totaling over 10,000 GPU-hours. Our results show that model rankings vary with the evaluation horizon, while 135 of the 150 runs achieve...

    arxiv.org/abs/2611.11995 · 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.