cs.AI · 2026-08-13 · No. 83

Artificial Intelligence, 2026-08-13.

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

01 — The papers

32 entries
  1. 01

    Constructing Dynamic Master Logic Models as Knowledge Graphs for Complex System Diagnostics Using Retrieval-Augmented Large Language Models

    Saman Marandi, Yu-Shu Hu, Mohammad Modarres

    cs.AI

    Dynamic Master Logic (DML) provides a hierarchical framework for representing system behavior by linking functional objectives to underlying structural elements. However, DML construction typically relies on expert interpretation of technical documentation, limiting scalability for complex systems. This study presents a framework for automated construction of DML models from system descriptions and their representation as Knowledge Graphs...

    arxiv.org/abs/2608.12304 · PDF

  2. 02

    VAKRA: Evaluating Multi-Hop Reasoning Across APIs and Retrieval Under Tool-Use Policies

    Ankita Rajaram Naik, Anupama Murthi, Benjamin Elder, Siyu Huo, Raavi Gupta, Abhinav Jain, Praveen Venkateswaran,...

    cs.AI

    Agents deployed in enterprise settings must reason across structured APIs and document collections, yet existing benchmarks evaluate these capabilities in isolation. We introduce VAKRA (e\textbf{V}aluating \textbf{A}PI and \textbf{K}nowledge \textbf{R}etrieval \textbf{A}gents), a benchmark of over $8{,}000$ executable APIs across $62$ domains with tasks spanning three settings of increasing difficulty: diverse API interaction styles,...

    arxiv.org/abs/2608.12282 · PDF

  3. 03

    An Agentic Workflow for Legacy HPC Modernization: Converting the Two-Electron-Integral Core of GAMESS

    Yuzhong Shen, Masha Sosonkina, Peng Xu, Mark S. Gordon

    cs.AI

    Modernizing legacy Fortran is a problem of volume: the transformations are individually routine, but the codebases can be enormous, and across much of computational science the work simply goes undone. We propose an agentic workflow that takes this work on at production scale, and we set out to measure how far such delegation can reach. In this work, three prompt-specialized agent roles operate under a version-controlled specification that...

    arxiv.org/abs/2608.12249 · PDF

  4. 04

    How to Spend Your Oracle Budget: Practical Guidance for Protein Structure Prediction Models

    Aleksandra Kalisz, Jack Simons, Krisztina Sinkovics, Noam Ghenassia, Shikha Surana, Henry Moss, Paul Duckworth

    cs.AI · cs.LG

    Foundation models for protein structure prediction remain unreliable on certain targets. External oracles can flag and correct these failures, but biological oracles are expensive, making oracle budget a critical constraint. Existing guidance methods, such as FK-steering, DPO, and Best K-of-N sampling, differ in how they spend this budget, yet no systematic comparison exists to guide method selection. To bridge this gap, we benchmark these...

    arxiv.org/abs/2608.12192 · PDF

  5. 05

    Who Thinks Best Depends on How Long You Let Them: Budget-Dependent Rankings in LLM Evaluation

    Rodrigo Guedes de Souza, Alison R. Panisson

    cs.AI · cs.CL

    Standard evaluation of large language models assumes stable model rankings across inference conditions. We challenge this assumption by varying the token generation budget, i.e., the maximum tokens a model may produce, across seven levels (64--4,096), evaluating four models on three reasoning benchmarks (56,476 inferences). We report four findings: (i) 3--19% of items exhibit non-monotone behavior (accuracy decreasing with more budget), even...

    arxiv.org/abs/2608.12150 · PDF

  6. 06

    GUIDE: Governed Unified Intelligence for Document-to-Artifact Generation in Enterprise Settings

    Shivali Dalmia, Sumukha Thoppanahalli, Mohammadreza Sediqin, Abhishek Mukherji

    cs.AI

    Enterprise guideline documents are heterogeneous and multimodal, combining narrative text, complex tables, and embedded images. Existing LLM and VLM systems face hallucinated content, table structure degradation, and lack governed workflows extending beyond extraction to validation and artifact generation. This leaves enterprises to perform this manually, consuming 2-3 days per document. To address this, we introduce GUIDE, a governed...

    arxiv.org/abs/2608.12133 · PDF

  7. 07

    Graph-Structured Rubrics: Compiling Rubrics into Typed Evaluation Graphs for LLM Judges

    Xi Chen, Jie Mu, Mo Xuan, Qun Shao

    cs.AI

    Rubric-based evaluators commonly treat rubrics as prompt context or flat criteria: they specify what to judge but leave criterion composition implicit, even when natural-language rules state it. We introduce Graph-Structured Rubrics (GSR), which compiles a rubric into a response-independent typed evaluation graph before observing responses. Criterion nodes elicit judgments; transformation, reduction, and gating operators compose them through...

    arxiv.org/abs/2608.12097 · PDF

  8. 08

    Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence

    Mengru Wang, Junfeng Fang, Shuofei Qiao, Zhenqian Xu, Haoming Xu, Haoxiong Wang, Shumin Deng, Linyi Yang, Zhixiang...

    cs.AI · cs.CL · cs.HC · cs.LG · cs.MA

    AI models have achieved remarkable success across diverse domains, yet the mechanisms underlying their capabilities and the risks they may pose remain poorly understood. As AI development becomes faster and increasingly automated, mechanistic exploration remains largely manual, widening the gap between what models can do and our ability to understand and control them. To bridge this gap, we introduce Mechanist, an agentic system that uses AI...

    arxiv.org/abs/2608.12036 · PDF

  9. 09

    CTBench: Evaluating Troubleshooting Capabilities of AI Agents in Realistic Telecom Network Operations

    Xingyu Yan, Tingting Dai, Antonio De Domenico, Mohamed Sana, Nicola Piovesan, Changchang Li, Bowen Liu, Kun Jiang,...

    cs.AI

    Agents are increasingly considered for automating network operations and maintenance, where engineers must diagnose network faults, optimize configurations to enhance services, and reduce operational costs while acting under strict constraints. However, existing evaluations fail to accurately model real network characteristics or assess agents under partially observable telecom environments with diverse vendors, devices, protocols, and...

    arxiv.org/abs/2608.12002 · PDF

  10. 10

    Claim-Level Reliability Assessment for Efficient Test-Time Reasoning

    Sen Xu, Wei Wang, Shixi Liu, Jixin Min, Yingwei Dai, Zhibin Yin, Yirong Chen, Junlin Zhang

    cs.AI · cs.CL

    We propose claim-level falsification as a principle for test-time scaling and instantiate it through Claim-Level Reliability Assessment (CLR), a training-free framework that reallocates test-time compute from additional solution sampling to targeted verification. Since whole-trace evaluation often obscures decisive errors due to signal dilution from routine tokens, CLR condenses each reasoning trace into a compact set of decision-critical...

    arxiv.org/abs/2608.11994 · PDF

  11. 11

    Retry, Switch, or Abstain? Learning Strategy-Aware Tool-Use Policies via Controlled Error Injection

    Chaoran Chen, Vy Nguyen, Ziji Zhang, Abhinav Gullapalli, Ziyi Wang, Yuxuan Lu, Dakuo Wang, Jing Huang, Zhou Yu, Jin Lai

    cs.AI

    Tool-using LLM agents are commonly trained and evaluated in environments where tool calls succeed reliably, yet deployed tools can fail transiently, persistently, or silently. Robust recovery therefore requires more than repeated retries: an agent may need to retry the same path, switch to an alternative, or recognize that no viable path remains. We present BENCH2ROBUST, a framework that converts failure-free tool-use benchmarks into...

    arxiv.org/abs/2608.11977 · PDF

  12. 12

    ExRole: From Team Trajectories to Executable Roles in Multi-Agent Language Models

    Zhou Liu, Chaoyang Han, Zewei Pan, Zeli Su, Wentao Zhang

    cs.AI

    Roles provide an interpretable interface for organizing language-model agents, yet most multi-agent systems treat them as hand-written prompt labels disconnected from learned behavior and parameter updates. We argue that a useful role should instead be an executable control variable: it should summarize behavior predictive of future utility, guide subsequent interaction, and identify the trainable capacity responsible for that behavior. We...

    arxiv.org/abs/2608.11949 · PDF

  13. 13

    OEIS Open: How many conjectures can language models turn into theorems?

    Tom Adamczewski

    cs.AI

    We construct OEIS Open, a benchmark based on 492 open mathematical conjectures from the OEIS, formalized in Lean by Tsoukalas et al. Whereas these conjectures had previously been attempted only with a bespoke agent, our open-source evaluation code runs any generic language model (LM) against them, and is secure against LM cheating attempts. We find that LMs equipped with a minimal set of tools resolve 147 of these conjectures with a budget of...

    arxiv.org/abs/2608.11941 · PDF

  14. 14

    Policy-as-logic for robust reasoning over rules

    Rahul Nair, Bastian Lipka, Elizabeth Daly

    cs.AI · cs.LG · cs.SC

    In many practical applications of generative AI systems, from tax rules to airline baggage allowance, responses to natural language queries must respect written policies or rules. We present a hybrid symbolic approach that expresses policies in formal logic and at inference time exploits the representation power of language models for fact extraction to ground predicates, and an answer set solver for reasoning such that responses are...

    arxiv.org/abs/2608.11905 · PDF

  15. 15

    Agent Skills Can Be Harmful: An Empirical Study of Skill-Induced Failures in LLM Agents

    Gen Dong, Yanjie Gao, Liqun Li, Tianyin Xu, Yu Hua, Fan Yang

    cs.AI

    Agent skills are the de facto mechanism for extending LLM agents with reusable guidance. A skill can shape the agent's task execution, including planning, tool use, problem-solving, and validation. Prior work reported mixed results of agent skills: some skills improve task success rates, while others have no effect, increase token use and execution time, and even reduce success rates. This paper presents a comprehensive analysis of...

    arxiv.org/abs/2608.11888 · PDF

  16. 16

    The Sleeping Agent: What Gist-Based Context Compression Loses and Why

    Nicholas E. Kyrkewood

    cs.AI · cs.CL

    Gist-based context compression---summarising older conversation history into compact representations---is a common approach in long-horizon language model agents, yet its effect on different types of memory retrieval is poorly understood. We use Salience-Weighted Consolidation (SWC), a biologically-inspired compression framework motivated by sleep-based memory consolidation, as a diagnostic probe to study when gist compression helps and when...

    arxiv.org/abs/2608.11775 · PDF

  17. 17

    HyperANFIS: Enhancing Rule Representation and Interpretability in Adaptive Neuro-Fuzzy Systems via Hyperbolic Geometry

    Haoran Pei, Zhao Su, Zetao Lin, Haoran Li, Jun Shen, Qi Zhu, Lan Guo, Qingguo Zhou, Binbin Yong

    cs.AI

    The adaptive neuro-fuzzy inference system (ANFIS) is an interpretable reasoning framework capable of generating explicit IF-THEN fuzzy rules, making it suitable for tasks requiring transparent reasoning. However, existing ANFIS models generally construct rule antecedents and perform inference in Euclidean space, limiting their representational capacity and predictive performance. To address this issue, we propose Hyperbolic ANFIS...

    arxiv.org/abs/2608.11768 · PDF

  18. 18

    Harness-IF: Evaluating Instruction Following Across Instruction Surfaces in Coding Agents

    Zining Huang, Haoran Que, Hong Zeng, Ge Zhang, Zuo Wang, Jin Chen, Haodong Wang, Zhongfei Hou, Changxin Pu, Shen...

    cs.AI

    When a coding agent obeys a rule, it may simply have been going to do that anyway. Existing instruction-following benchmarks cannot tell the difference: they concentrate rules in the user turn, while coding-agent benchmarks emphasize final task success. We introduce Harness-IF, which scores operational rules one at a time from execution evidence: 60 realistic multi-turn coding items drawn from a 642-rule library, 256 rules receiving verdicts,...

    arxiv.org/abs/2608.11727 · PDF

  19. 19

    Proportional Analogies on Probability Distributions via Bayesian Updating

    Pierre-Alexandre Murena

    cs.AI

    Analogies are quaternary relations of the form "A is to B as C is to D". Among the various formalizations of analogical reasoning, proportional analogies provide an important axiomatic framework by characterizing valid analogies through a set of postulates. While proportional analogies have been extensively studied over Boolean, symbolic, and real-valued domains, their extension to probability distributions remains largely unexplored. In this...

    arxiv.org/abs/2608.11724 · PDF

  20. 20

    Making Your LLMs More Objective: Stabilizing LLM Safety Behavior Across Traits with Trait-Invariant Safety Tuning

    Lang Cao

    cs.AI

    Aligned large language models (LLMs) are expected to exhibit safety behavior based on the content of the user request: they should refuse unsafe requests and comply with safe ones. However, we show that the same request can elicit substantially different safety decisions under different traits assigned in the system prompt, a failure mode we call trait-induced safety variation. To measure this failure, we introduce refusal-based metrics:...

    arxiv.org/abs/2608.11705 · PDF

  21. 21

    HUGIN: Enhancing Vision-Language Planning for Autonomous Logistics Sorting

    Xikai Sun, Cangtian Zhou, Kebin Liu, Ke Ma, Xu Wang, Zaishu Chen, Haotian Wang, Li Liu, Yunhao Liu

    cs.AI

    Autonomous logistics sorting systems (ALSS) are an important industrial application of embodied AI, which requires joint planning over spatially disjoint camera views. We formulate this setting as Joint Multi-Scene Understanding (JMSU). With open-world visual understanding and task-planning capabilities, vision-language models (VLMs) are promising candidates for JMSU. However, directly applying existing VLMs to JMSU is non-trivial due to...

    arxiv.org/abs/2608.11692 · PDF

  22. 22

    FrontierFinance: A Challenging Benchmark for Measuring Frontier Intelligence of Finance Agents

    Yuhao Zhang, O. Ozan Koyluoglu, Thejas Venkatesh, Richard Diehl Martinez, Vishank Bhatia, Arash Alidoust, Ashwin Paranjape

    cs.AI · cs.CL

    AI agents are increasingly deployed for professional investment research, yet no benchmark captures the complexity of the full investor workflow. Existing benchmarks mainly target financial data extraction, a narrow slice that current models have largely saturated, while reference-based metrics and generic LLM-as-a-judge scoring fall short on the open-ended, long-form answers that real analyst queries demand. We introduce FrontierFinance, a...

    arxiv.org/abs/2608.11683 · PDF

  23. 23

    AgenticTwin: An Agentic LLM Framework Integrated with Digital Twin for Anomaly Detection

    Touseef Hasan, Mounika Ghanta, Souvika Sarkar, Ujjwal Guin

    cs.AI · cs.IR · cs.MA

    Digital twins are increasingly used to monitor and simulate the behavior of cyber-physical systems. Even with skilled operators, interpreting anomalies detected within digital twin pipelines is challenging, as the sheer complexity and volume of raw sensor data make thorough analysis difficult. Recent advances in large language models (LLMs) offer promising capabilities for reasoning and explanation, yet their integration into digital...

    arxiv.org/abs/2608.11679 · PDF

  24. 24

    XBridge: Entity-Grounded Latent Bridge for Heterogeneous LLM Communication

    Wooseong Yang, Wei-Chieh Huang, Weizhi Zhang, Yu Wang, Philip S. Yu, Junhyun Lee

    cs.AI

    Heterogeneous multi-agent LLM systems, where agents are powered by different model families, can outperform homogeneous configurations by reducing redundant reasoning patterns. Yet existing communication protocols either operate through text, discarding the sender's internal representations, or require architectural homogeneity for latent-level transfer. We identify the entity grounding problem in cross-architecture communication:...

    arxiv.org/abs/2608.11676 · PDF

  25. 25

    CLAIM: Leading Open-domain Active Clarification of Large Language Models with Uncertainty Measurement

    Kuangzhao Yang, Ziliang Zhao, Zhicheng Dou

    cs.AI

    In open-domain human-computer interaction scenarios, large language models (LLMs) frequently encounter user queries that are ambiguous or incomplete. In such cases, directly producing an answer often leads to overgeneralized, erroneous, or low-information responses. In contrast, asking clarifying questions can substantially improve interaction quality. However, existing approaches still rely heavily on manually annotated data or preference...

    arxiv.org/abs/2608.11631 · PDF

  26. 26

    Making AI-Generated Feedback Matter: From Provision to Student Enactment

    Omar Alsaiari, Nilufar Baghaei, Jason M. Lodge, Dragan Gaševi'c, Naomi Winstone, Hassan Khosravi

    cs.AI

    Feedback processes strongly influence student learning, yet their educational value depends on addressing two distinct challenges: providing high-quality, timely, and individualised feedback at scale, and supporting students to interpret, evaluate, and act on that feedback productively. Generative AI offers a credible means of addressing the provision challenge, but students' uptake of AI-generated feedback remains limited. We conducted a...

    arxiv.org/abs/2608.11625 · PDF

  27. 27

    MBA: Multimodal Benchmark and Agents for Real-World Business Ideation

    Hojun Choi, Jaeyo Shin, Suin Lee, Hyunjung Shim

    cs.AI · cs.CV · cs.LG

    Agentic systems powered by large language models (LLMs) have opened new opportunities for business ideation. Yet existing approaches remain confined to a text-only paradigm, despite the inherently multimodal nature of real-world contexts. We thus introduce MBA-Bench, the first multimodal benchmark for training and evaluating business ideation agents, comprising 30K samples across six domains, each domain characterized by distinct visual cues...

    arxiv.org/abs/2608.11616 · PDF

  28. 28

    Foresight Without Seeing: Latent Futures for World Action Models

    Jiakai Huang, Zhongbo Wu, Zheng Zhang, Zihan Wang, Shan You, Tao Huang

    cs.AI

    World Action Models (WAMs) couple future visual prediction with robot action generation, enabling policies to model how the physical world evolves during interaction. Existing WAMs differ in how predictive dynamics are exposed to the action pathway. Explicit-future WAMs provide direct access to predicted scene evolution, but incur substantial inference costs from iterative video denoising. In contrast, direct-policy WAMs efficiently predict...

    arxiv.org/abs/2608.11605 · PDF

  29. 29

    Learning from Online User Feedback for Shopping Agents

    Haobo Zhang, Kelong Mao, Sulong Xu, Simiu Gu, Zhicheng Dou

    cs.AI

    Large language model-based shopping agents are increasingly deployed in real-world e-commerce platforms, generating massive amounts of user interaction logs that provide valuable supervision for improving these agents. However, existing approaches primarily rely on offline training signals, such as user-item interactions or synthetic preference data, while largely overlooking the rich supervision contained in users' natural conversational...

    arxiv.org/abs/2608.11604 · PDF

  30. 30

    CoAdapt-GUI: Joint Workflow Context and Policy Adaptation for Unseen GUI Applications

    Linqiang Guo, Li Gu, Zihuan Jiang, Zhixiang Chi, Siobhan Reid, Ziqiang Wang, Yuanhao Yu, Wei Liu, Yang Wang, Tse-Hsun, Chen

    cs.AI

    Mobile GUI agents remain brittle when deployed to applications absent from source training. We study novel-app generalization under a limited target interaction budget and without target demonstrations. We introduce CoAdapt-GUI, a test-time adaptation (TTA) framework that jointly adapts structured workflow context and policy from the agent's own target-app rollouts and rewards. The workflow context retains transferable procedures, failure...

    arxiv.org/abs/2608.11588 · PDF

  31. 31

    EnterpriseRAG: Benchmarking LLM Instruction Adherence and Robustness under Non-Ideal Enterprise Retrieval

    Huiqi Miao, Xinbao Sun, Bo Wang, Fanyu Meng, Lijun Mei, Na Wu, Di Jin, Chao Deng, Junlan Feng

    cs.AI

    Enterprise RAG deployments face a critical reliability gap: while LLMs satisfy 80% of individual constraints, only 26.8% of responses meet all requirements simultaneously, revealing a 57-point orchestration gap. Existing benchmarks assume clean retrieval with simple queries, failing to capture production conditions where noisy documents and multi-dimensional constraints coexist. We introduce EnterpriseRAG, a benchmark of 983 expert-validated...

    arxiv.org/abs/2608.11584 · PDF

  32. 32

    Localizing Safety Alignment: MLP Layers and Mid-Network Blocks Encode Refusal Behavior in Large Language Models

    Mingyu Zong, Sampad Mohanty, Bhaskar Krishnamachari

    cs.AI

    Safety alignment in large language models is often treated as a distributed property of the entire network, yet its practical brittleness suggests that refusal behavior may be concentrated in a smaller set of parameters. This work addresses where safety-aligned refusal is encoded by transplanting weights from aligned models into matched unaligned base models at multiple levels of granularity. Using two open-weight model pairs and four safety...

    arxiv.org/abs/2608.11583 · 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.