cs.AI · 2026-07-15 · No. 54

Artificial Intelligence, 2026-07-15.

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

01 — The papers

46 entries
  1. 01

    Do AI Agents Know When a Task Is Simple? Toward Complexity-Aware Reasoning and Execution

    Junjie Yin, Xinyu Feng

    cs.AI · cs.CL · cs.SE · eess.SY

    Large language model (LLM) agents increasingly automate multi-step engineering and informatics workflows, yet they rarely ask how much effort a task actually requires. They often follow a maximum-context-first strategy--re-reading files and dependencies they have already seen--turning a one-line edit into a small code-base audit. We argue the missing capability is task-aware execution-scope estimation: judging a task's difficulty, the...

    arxiv.org/abs/2607.13034 · PDF

  2. 02

    Audio-Native Speech Recognition with a Frozen Discrete-Diffusion Language Model

    Harsha Vardhan Khurdula, Abhinav Kumar Singh, Yoeven D Khemlani, Vineet Agarwal

    cs.AI · cs.SD

    Automatic speech recognition is dominated by autoregressive decoders that emit one token at a time. We ask whether a discrete diffusion language model can transcribe speech instead, refining a whole transcript in parallel over a small number of denoising steps. We train an audio-native interface for DiffusionGemma, a 26B mixture-of-experts model that generates text by uniform, random-token discrete diffusion rather than the absorbing-mask...

    arxiv.org/abs/2607.13013 · PDF

  3. 03

    Dynamic Resource Allocation for Ensemble Determinization MCTS

    Jakub Kowalski, Adam Ciężkowski, Artur Krzyżyński, Mark H. M. Winands

    cs.AI

    Simulation-based algorithms are especially suited for high-uncertainty environments such as adversarial board games with significant elements of randomness and hidden information. In particular, several Monte Carlo Tree Search (MCTS) variants are commonly used in such domains. In this paper, we propose a series of enhancements for Ensemble Determinization MCTS, introducing two axes for dynamic resource allocation. First, Dynamic Number of...

    arxiv.org/abs/2607.13007 · PDF

  4. 04

    Win by Silence: Deletion Non-Monotonicity, Autonomous Exploitation, and Typed-State Gating in LLM Plan Evaluation

    Aleh Manchuliantsau

    cs.AI · cs.SE

    Plan evaluators can reward a strategic plan for becoming less explicit. This paper studies that failure in a staged expected-value scorer for LLM-generated venture routes. Proposition 1 gives the score change from deleting an interior transition while retargeting its predecessor and retaining downstream value: Delta_k = (prod_{i<k} p_i)[c_k + (1 - p_k)R_{k+1}]. On a frozen 26-route cohort, all 57 admissible deletions matched the analytic...

    arxiv.org/abs/2607.12986 · PDF

  5. 05

    Resist and Update: Counterfactual Report Coordinates for Incentive-Compatible LLMs

    Sen Yang, Yuen-Hei Yeung

    cs.AI

    Aligned language models routinely misreport under non-evidential incentive pressure: they agree with a confident user or overstate certainty even when their internal belief is unchanged. We cast this as a failure of internal incentive-compatibility (IC) and present a method for learning and certifying counterfactual report mediators that hold a model's reports to a causal contract: invariant to forbidden influences (pressure, prestige,...

    arxiv.org/abs/2607.12985 · PDF

  6. 06

    FormalAnalyticGeo: A Neural-Symbolic Based Framework for Multimodal Analytic Geometry Problem Generation

    Ruoran Xu, Wending Gao, Qiufeng Wang

    cs.AI · cs.MA · cs.SC

    Math reasoning has achieved significant progress with the rapid advancement of Multimodal Large Language Models (MLLMs), however analytic geometry remains largely underexplored, primarily due to the scarcity of annotated samples. Existing diagram generation approaches struggle with analytic geometry: template methods cannot handle constraint-driven layouts, and generative models lack the geometric precision to render annotated conic curves...

    arxiv.org/abs/2607.12982 · PDF

  7. 07

    Knowledge- and Gradient-Guided Reinforcement Learning for Parametrized Action Markov Decision Processes

    Jonas Ehrhardt, René Heesch, Oliver Niggemann

    cs.AI

    In this paper, we study Reinforcement Learning in Parametrized Action Markov Decision Processes (PAMDP), where each decision consists of a symbolic action and numerical parameters. In such settings Reinforcement Learning algorithms typically determine parameters with one-shot estimators, which makes their training sample inefficient. Though in most PAMDP environments explicit but incomplete knowledge (e.g., rules, safety constraints, or...

    arxiv.org/abs/2607.12924 · PDF

  8. 08

    MemOps: Benchmarking Lifecycle Memory Operations in Long-Horizon Conversations

    Xixuan Hao, Zeyu Zhang, Zehao Lin, Yihang Sun, Ziliang Guo, Xichong Zhang, Yuxuan Liang, Feiyu Xiong, Zhiyu Li

    cs.AI · cs.CL

    Long-term memory has become a foundational capability for LLM-based agents that accompany users across extended, multi-session interactions. Existing benchmarks, however, evaluate such memory almost exclusively through downstream question answering, scoring only the correctness of a final answer. This black-box formulation conflates the heterogeneous causes of memory failure, such as missing the introduction of a relevant fact, binding an...

    arxiv.org/abs/2607.12893 · PDF

  9. 09

    A Multi-Agent System for Autonomous, Fine-Tuning-Free Clinical Symptom Detection: Development and Validation Study

    Cameron Cagan, Pedram Fard, Jiazi Tian, Jingya Cheng, Shawn N. Murphy, Hossein Estiri

    cs.AI

    Clinical notes contain many of the signs and symptoms that bring patients to care, yet this information rarely reaches structured fields. Existing extraction approaches either rely on context-insensitive rules that generate false positives or on supervised models that require substantial fine-tuning. We present Pythia, a multi-agent system that autonomously writes and optimizes extraction prompts for clinical concepts without manual prompt...

    arxiv.org/abs/2607.12886 · PDF

  10. 10

    Solution of the Hempel's statistical ambiguity problem and Causal AI

    Evgenii Vityaev

    cs.AI

    This paper addresses Carl Hempel's longstanding problem of statistical ambiguity in inductive-statistical inference, in which contradictory predictions are derived from statistical laws. To avoid such predictions, Carl Hempel proposed the Requirement of Maximal Specificity (RMS) for the statistical laws used in the inference. An analysis of the RMS refinements made by Wesley Salmon, Alberto Coffa, and James Fetzer led to the following...

    arxiv.org/abs/2607.12826 · PDF

  11. 11

    Human-AI Agent Interaction as a Neuroplastic Training Environment

    Eranga Bandara, Ross Gore, Asanga Gunaratna, Ravi Mukkamala, Nihal Siriwardanagea, Gihan Siriwardanagea, Sachini...

    cs.AI

    Interaction with AI agents has become one of the most frequent activities of everyday digital life. Whether conversing with an assistant, working with a coding copilot, or generating images, the interaction follows a common iterative loop: a request is issued, a result returned, appraised, and the request revised. We observe that this loop is a high-frequency stream of contact events -- moments at which a result meets a person and a...

    arxiv.org/abs/2607.12823 · PDF

  12. 12

    Visual Access Boundaries in Vision-Language Model Reasoning

    Hiroto Osaka, Shohei Taniguchi, Gouki Minegishi, Kai Yamashita, Masahiro Suzuki, Yutaka Matsuo

    cs.AI

    Chain-of-Thought (CoT) prompting is widely used as a test-time scaling strategy for Vision-Language Models (VLMs), but it remains unclear what is extended when VLMs generate longer reasoning traces. We ask whether CoT requires continued access to image tokens, or whether it mainly operates over visual information already made available earlier in the forward pass. We introduce Visual Access Sweep, a causal intervention that masks attention...

    arxiv.org/abs/2607.12815 · PDF

  13. 13

    Who Grades the Grader? Co-Evolving Evaluation Metrics and Skills for Self-Improving LLM Agents

    Xing Zhang, Guanghui Wang, Yanwei Cui, Ziyuan Li, Wei Qiu, Bing Zhu, Peiyang He

    cs.AI · cs.CL · cs.MA

    Self-evolving agent systems improve by creating, revising, and retiring their own skills, but every such loop rests on a hidden assumption: a reliable evaluation metric already exists. In many real applications it does not. We make three claims. First, metrics can be \emph{evolved}: our metric loop searches compositions of small drawback detectors under a full evolutionary lifecycle, trained to agree with a ten-item anchored reference set,...

    arxiv.org/abs/2607.12790 · PDF

  14. 14

    Do We Really Need Multimodal Emotion Language Models Larger Than 1B Parameters?

    Kaiwen Zheng, Junchen Fu, Wenhao Deng, Hu Han, Joemon M. Jose, Xuri Ge

    cs.AI · cs.CL · cs.CV · cs.MM

    Recent advances in multimodal large language models (MLLMs) have significantly improved the performance of multimodal emotion recognition (MER) and enabled interpretable description generation by jointly modeling video, audio, and language, etc. However, these performance improvements are often accompanied by an increase in model parameter size (e.g, at least 7B), which simultaneously incurs high computational costs and reduces inference...

    arxiv.org/abs/2607.12787 · PDF

  15. 15

    Accuracy and Normalized Accuracy under Length Bias: Analysis, Guidelines, and a Bayesian Alternative

    Koen Oostermeijer

    cs.AI

    Multiple-choice benchmarks that rank candidate completions by conditional log-probability suffer from a length bias: because log-probabilities sum over tokens, longer answers tend to be penalized relative to shorter ones in practice. A common mitigation is to normalize scores by completion length, but we show empirically that this heuristic frequently over-corrects, introducing a bias toward longer answers instead. We first analyze these...

    arxiv.org/abs/2607.12767 · PDF

  16. 16

    Tracing Agentic Failure from the Flow of Success

    Samuel Yeh, Yiwen Zhu, Shaleen Deep, Sharon Li

    cs.AI · cs.CL

    Failure attribution for LLM-based agentic systems, i.e., identifying which steps in a failure trajectory caused the task to fail, is critical for debugging and improving these systems. Existing approaches either rely on prompting-based pipelines, which are computationally expensive, or require post-training on failure trajectories with step-level error annotations, which are costly to collect and difficult to scale. We argue that a practical...

    arxiv.org/abs/2607.12747 · PDF

  17. 17

    LLMs Can See the Smoke but not the Fire: Evaluating Abductive Reasoning with Elenchos

    Julius Steiglechner, Lucas Mahler, Gabriele Lohmann

    cs.AI · cs.LG

    Large language models (LLMs) excel at pattern recognition and text generation, but their capacity for abductive inference - inferring latent hypotheses that explain observed behavior - remains poorly understood. Here, we introduce Elenchos (named after the Socratic method of cross-examination), a generative evaluation framework that measures abductive reasoning as a structural inverse problem. Given a reference formal system, such as the...

    arxiv.org/abs/2607.12733 · PDF

  18. 18

    MaxSAT-Based Feedback for Guiding Vision-Language Models in Sudoku

    Pedro Orvalho, Guillem Alenyà, Felip Manyà

    cs.AI · cs.LO

    Vision--Language Models (VLMs) have recently demonstrated promising performance on structured visual reasoning tasks, including grid-based puzzles. However, despite strong perceptual capabilities, these models lack explicit mechanisms for enforcing logical consistency and frequently generate assignments that violate underlying constraints. In this paper, we propose a neuro-symbolic approach that integrates formal constraint reasoning into the...

    arxiv.org/abs/2607.12711 · PDF

  19. 19

    Internet of Agentic Things: Networked AI Agents for Closed-Loop IoT Orchestration

    Quanyan Zhu

    cs.AI · cs.MA · eess.SY

    The paper introduces the Internet of Agentic Things (IoAT), an architectural framework that integrates agentic AI, IoT, cyber-physical systems, Physical AI, edge computing, and digital twins into a unified closed-loop orchestration framework. The proposed architecture consists of cloud, edge/fog, and physical IoT layers connected through autonomous AI agents that perceive, reason, coordinate, and actuate across distributed cyber-physical...

    arxiv.org/abs/2607.12662 · PDF

  20. 20

    A Learning-Rate-Gated Failure of GRPO in a Small Language and Vision-Language Model Web Agent: A Controlled Null and Its Mechanism

    Chengguang Gan, Zhixi Cai, Yunhao Liang, Hanjun Wei, Shiwen Ni, Qinghao Zhang

    cs.AI · cs.CL

    Reinforcement learning with verifiable rewards, and Group Relative Policy Optimization (GRPO) in particular, is now run routinely on a supervised checkpoint in the hope of producing a stronger agent. We ask whether it adds skill to a small language and vision-language model web agent at the 4B to 8B scale, or whether it mostly reshapes behavior the supervised model already has. Across a control grid of 18 runs that varies learning rate, KL...

    arxiv.org/abs/2607.12640 · PDF

  21. 21

    Atomic Units of X: The Compression Layer of Intelligence

    Sachin Dev Duggal, Pradyumna Swarnalatha Ramanna, Alexandros Vassiliades

    cs.AI

    This paper proposes a theoretical framework for understanding intelligence as a process of atomic compression and compositional reuse. We argue that cognitive, biological, computational, and organizational systems achieve scalable intelligence by decomposing complex phenomena into reusable atomic units that can be recombined into higher-order structures. Drawing on evidence from cognitive science, information theory, evolutionary biology,...

    arxiv.org/abs/2607.12634 · PDF

  22. 22

    Agentic Service-Oriented Computing: A Manifesto for the Next Frontier of Service-Oriented Computing

    Amin Beheshti, Rong N. Chang, Boualem Benatallah, Fabio Casati, Schahram Dustdar, Geoffrey Fox, Quan Z. Sheng, Yan...

    cs.AI · cs.ET

    The rapid emergence of LLM-powered autonomous and semi-autonomous agents is reshaping software systems from static, request-response components into goal-directed, adaptive, and tool-using computational actors. As these agents move from isolated cognitive prototypes into complex distributed workflows, they confront challenges that the Service-Oriented Computing community has studied for more than two decades: composition, interoperability,...

    arxiv.org/abs/2607.12619 · PDF

  23. 23

    Vertical Standardisation for High-Risk AI Systems under the EU AI Act: A Domain-Specific Framework for Algorithmic Hiring

    Anna Gatzioura, Vrettos Moulos, Nina Baranowska

    cs.AI

    According to the recent European legislation, high-risk AI systems will have to adapt in order to comply with requirements related to specific areas, like risk management, data quality and governance, logging and traceability, technical documentation, transparency, human oversight, and accuracy, as outlined in the European Artificial Intelligence (AI) Act. As the standardisation process for AI is expected to remain iterative and, so far,...

    arxiv.org/abs/2607.12588 · PDF

  24. 24

    Evidence-Grounded AI for Musculoskeletal Care

    Wenjie Li, Yujie Zhang, Fanrui Zhang, Haoran Sun, Renhao Yang, Junjun He, Weiran Huang, Yuanfeng Ji, Chenrun Wang,...

    cs.AI

    Musculoskeletal diseases are among the leading causes of disability worldwide and create the greatest global need for rehabilitation. Because recovery, remodelling and degeneration often unfold over months to years, musculoskeletal care requires longitudinal management that repeatedly integrates evolving patient evidence, external medical knowledge and stage-specific functional goals. In routine practice, this evidence is fragmented across...

    arxiv.org/abs/2607.12527 · PDF

  25. 25

    The Model Knows Your Project, Not You: Measuring Recognition in LLMs with NameRank

    Bojie Li, Noah Shi

    cs.AI

    What a frontier model recalls about a person or tool from its own weights -- before any retrieval step -- often shapes the first description a human sees, making that parametric corpus presence a measurement problem. Citations explain about a third of whether a model recognizes a researcher; we target the residual and build NameRank, a [0,1] recognition score: each of 4,685 entities in 54 cohorts is probed with one open-ended question across...

    arxiv.org/abs/2607.12520 · PDF

  26. 26

    TRACE: An Operational Reasoning Schema for Auditable Agentic Commitments

    Edward Y. Chang, Emily J. Chang

    cs.AI

    This paper defines TRACE (Typed Reasoning And Commitment Evidence): a typed, versioned schema for recording reasoning traces, a reference procedure for writing records against it, and one operating discipline, no durable state change without a record. The paper argues in three layers that reasoning is not in the language model: the autoregressive mechanism natively computes association; chain-of-thought and reinforcement learning inherit its...

    arxiv.org/abs/2607.12480 · PDF

  27. 27

    From Observation to Insight: Mechanistic World Models and the Quest for Autonomous Discovery

    Ingmar Posner, Anson Lei, Bernhard Schölkopf

    cs.AI

    Recent advances in foundation models have transformed AI for Science, enabling remarkably accurate predictive performance across domains ranging from protein folding to weather forecasting. Yet prediction alone does not constitute scientific discovery. Scientific understanding depends on uncovering the reusable explanatory mechanisms that generate observations, whereas contemporary machine learning remains fundamentally organised around...

    arxiv.org/abs/2607.12474 · PDF

  28. 28

    Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models

    Yubo Wang, Jiarong Liang, Yuxuan Zhang, Xuye Liu, Cong Wei, Yuyu Zhang, Ping Nie, Wenhu Chen

    cs.AI · cs.CL

    Coding agents must integrate external tool returns into ongoing reasoning - a capability that standard left-to-right pretraining on code exposes only in its forward direction. We observe that the action-observation-continuation loop of a coding agent is structurally isomorphic to a function call site, where a caller binds arguments, a callee returns a value computed elsewhere, and downstream code consumes that value. This conditioning...

    arxiv.org/abs/2607.12463 · PDF

  29. 29

    Do We Really Need Transformers for Global Spatial Information Extraction in Traffic Forecasting?

    Qihang Zhang, Siyao Zhang, Letao Kang, Wenzhe Liang, Miao Zhang, Zhao Zhang

    cs.AI

    Existing traffic forecasting models commonly focus on extracting spatial dependencies, particularly global spatial information, which characterizes the representations obtained through interactions between each individual node and all nodes across the traffic network. However, the underlying mechanism by which such global information is modeled and extracted remains insufficiently investigated. Whether global information must be extracted by...

    arxiv.org/abs/2607.12462 · PDF

  30. 30

    EVOQUANT: Self-Evolving Verifier-Guided Strategy Optimization for Robust Quantitative Trading

    Jie Mao, Changlun Li, Xiang Li, Qiqi Duan, Jinhui Yuan, Xiang Liu, Yuyu Luo, Jing Tang, Xiaowen Chu, Nan Tang

    cs.AI · cs.CE

    Quantitative strategy optimization remains largely manual, requiring domain experts to identify weak signals, tune risk-control rules, and repeatedly validate iterative revisions. Large language models can accelerate this process, but directly relying on them to rewrite trading strategies often introduces hallucinated edits, strategy drift, and backtest overfitting. We propose EVOQUANT, a self-Evolving Verifier-guided framework for strategy...

    arxiv.org/abs/2607.12455 · PDF

  31. 31

    Accepted Prefixes Are Not All You Need: A Negative Result on PEFT-Based Block-Diffusion Drafting

    Abdurrahman Javat, Allan Kazakov

    cs.AI

    Speculative decoding accelerates autoregressive language model inference by using a cheap drafter to propose multiple future tokens and a target model to verify them. A common design goal is therefore to improve draft quality while reducing auxiliary parameters and systems overhead. We study a negative result for this direction through PEFT-BD, a same-backbone speculative decoding method in which a LoRA-like adapter acts as a block-diffusion...

    arxiv.org/abs/2607.12422 · PDF

  32. 32

    Isolation as a First-Class Principle for LLM-Agent System Safety: Concepts, Taxonomy, Challenges and Future Directions

    Huihao Jing, Wenbin Hu, Shaojin Chen, Haochen Shi, Sirui Zhang, Hanyu Yang, Changxuan Fan, Zhongwei Xie, Hongyu Luo,...

    cs.AI

    The capability of LLM agents to function as the ``brain'' of a system fundamentally expands the scope of analysis beyond a standalone model. Consequently, safety is no longer only about input--output content alignment. It also concerns system behavior and real-world execution outcomes. However, the current literature is fragmented across attack types, applications, and benchmarks. This makes it hard to explain why failures such as prompt...

    arxiv.org/abs/2607.12406 · PDF

  33. 33

    Critic Experience Bank: Self-Evolving Step-Level Confidence Estimation for LLM Agents

    Yaopei Zeng, Congchao Wang, JianHang Chen, Nan Wang, Yurui Chang, Lu Lin

    cs.AI

    LLM agents act in external environments where each action changes the state that later decisions condition on, and where a single wrong step can waste interaction budget or trigger irreversible side effects long before the final failure is observed. Reliable deployment therefore requires \emph{step-level confidence estimation}: a calibrated probability that each proposed action is productive, available \emph{before} the action is executed....

    arxiv.org/abs/2607.12397 · PDF

  34. 34

    PM-Bench: Evaluating Prospective Memory in LLM Agents

    Genglin Liu, Saadia Gabriel

    cs.AI

    A significant challenge in agentic AI is prospective memory: the ability to execute an intention at a specific future cue or state while other activities are ongoing. We introduce PM-Bench, a text-based benchmark for measuring prospective memory capabilities in modern LLM agents. Inspired by the Virtual Week paradigm from cognitive science, PM-Bench evaluates how well LLM agents maintain user intentions, execute delayed intentions, and...

    arxiv.org/abs/2607.12385 · PDF

  35. 35

    How Many Tasks Are Enough for Agent Benchmark Decisions? A Replay Analysis of Public LLM Agent Benchmarks

    Wei-Jung Huang

    cs.AI

    Agent benchmarks often compare two agents after all tasks have run, but costly evaluations make partial runs tempting. A task fraction alone does not show whether a partial run supports the same pairwise conclusion as the completed benchmark. We study this question by replaying completed public task-level records from SWE-bench, AppWorld, and tau-bench. A partial budget counts as enough only when it supports the completed benchmark's...

    arxiv.org/abs/2607.12338 · PDF

  36. 36

    On-Device Deep Research at 4B: Exposure Bounds Faithfulness, Retrieval Bounds Coverage

    Vinay Kumar Chaganti

    cs.AI · cs.CL · cs.IR · cs.LG

    On-device research agents search a corpus, read sources, and write a cited brief on a personal laptop. Whether their citations are faithful, and at what cost, is unmeasured for a deployable small model. This study fixes one 4B generator on a 24 GB laptop and asks what makes its citations faithful. It separates two quantities usually reported as one number. Cited claim faithfulness asks whether the cited source supports the claim. Trustworthy...

    arxiv.org/abs/2607.12257 · PDF

  37. 37

    Rethinking the Evaluation of Harness Evolution for Agents

    Yike Wang, Huaisheng Zhu, Zhengyu Hu, Yige Yuan, Zhengyu Chen, Shakti Senthil, Hannaneh Hajishirzi, Yulia Tsvetkov,...

    cs.AI

    We revisit the evaluation of automatic harness evolution for LLM agents. Existing harness evolution methods use unit test cases to search for harness configurations and then report final performance on the same public benchmark. This protocol raises two fundamental concerns. First, harness evolution is itself an iterative search procedure that repeatedly evaluates and revises candidate harnesses using task feedback. As in agentic test-time...

    arxiv.org/abs/2607.12227 · PDF

  38. 38

    Good Benchmarks

    Ivan Bercovich

    cs.AI

    Good tasks are correct, solvable, verifiable, well-specified, and hard for interesting reasons. The best tasks describe a real problem an experienced practitioner would recognize, in language a practitioner would use, with tests that verify the outcome rather than the approach.

    arxiv.org/abs/2607.12217 · PDF

  39. 39

    A Threshold Exceedance Framework for CBRN Uplift Evaluation in Frontier Language Models

    Rahul Gupta, Abhinav Mohanty, Payal Motwani, Venkatesh Saligrama, Satyapriya Krishna, Connor Harris, Gary Anthony...

    cs.AI · cs.CR · cs.CY

    As frontier language models advance, policymakers and model developers need methods for assessing whether model access materially increases a non-expert actor's ability to plan high-consequence Chemical, Biological, Radiological, or Nuclear (CBRN) misuse relative to public tools alone. Existing CBRN evaluations differ in non-expert definitions, threat scope, baselines, scoring rubrics, and decision rules, making results difficult to compare...

    arxiv.org/abs/2607.12200 · PDF

  40. 40

    Cost-Governed RAG: Unified Per-Tenant Cost Attribution Across Retrieval and Generation in Multi-Tenant LLM Systems

    Navnit Shukla

    cs.AI · cs.DB · cs.IR

    Enterprise Retrieval-Augmented Generation (RAG) deployments face a critical governance gap: while LLM generation cost is metered per token, the retrieval layer - vector memory, similarity compute, and embedding API calls - remains an unattributed shared cost, enabling invisible cross-subsidization among tenants. We present Cost-Governed RAG, an architecture that integrates a codebook-oblivious vector index (TurboVec) with a multi-tenant LLM...

    arxiv.org/abs/2607.12188 · PDF

  41. 41

    The Emerging Paradigm of Geospatial Foundation Models: From Pre-Training to Agentic Reasoning

    Shelley Cazares

    cs.AI · cs.CV

    The analysis of satellite and aerial imagery has entered a new era with the advent of foundation models. This paper describes the concept of Geospatial Foundation Models (GeoFMs), which are artificial intelligence/machine learning (AI/ML) models pre-trained on massive geospatial datasets through varied methodologies. We first articulate the core paradigm shift that GeoFMs enable: a separation of duties, where large-scale model providers...

    arxiv.org/abs/2607.12177 · PDF

  42. 42

    Connected by Construction: Learning Tractable Near-Tour Marginals for Traveling Salesman Problems

    Ke Sun, Xinyuan Zhang, Xinwu Qian

    cs.AI

    Learning-based methods for the traveling salesman problem (TSP) are often evaluated through the tours produced after decoding or search, but the learned object itself frequently lives in a surrogate space such as heatmaps, assignments, construction policies, or search-guidance scores. This hides the fundamental question: what Hamiltonian structure has actually been learned before decoding? In this study, we directly answer this question by...

    arxiv.org/abs/2607.12127 · PDF

  43. 43

    Representing and Generating Levels Over Time through Playtrace Reconstructive Partitioning

    Emily Halina, Matthew Guzdial

    cs.AI

    Video games are a dynamic medium experienced over time. While there are many Procedural Content Generation (PCG) approaches for generating video game levels, they often use representations that abstract away this dynamic nature. In this paper, we introduce a novel, domain-independent ``cake'' representation for game levels over time which implicitly encodes dynamic information. We present a novel level generation approach Playtrace...

    arxiv.org/abs/2607.12097 · PDF

  44. 44

    Operationalising Multi-Dimensional Evaluation for Conversational Agents: A Scalable, Governed Pipeline with Selective Re-evaluation and Model Benchmarking

    Niranjan Kumar M, Balaji Nagarajan, Karthik Nair, Faysal Satter, Nithin Surendran

    cs.AI

    Evaluating retail conversational agents requires methods beyond lexical-overlap metrics to assess intent alignment, factuality, helpfulness, clarity, tone, and overall response quality. Although LLM-as-a-judge methods provide scalable alternatives to human evaluation, production deployment introduces challenges in governance, reproducibility, cost, schema consistency, traceability, and reliability. We present GenAI Evaluation, a governed,...

    arxiv.org/abs/2607.12085 · PDF

  45. 45

    Graph Feedback Controls Consensus and Clique Formation in Open-Weight Language-Model Populations

    Samer Saab, Chaouki Abdallah

    cs.AI · cs.MA

    Multi-agent language-model systems increasingly route local interactions, yet the runtime interaction graph is often treated as an implementation detail. We study convention formation in open-weight LM populations spanning 1.1B-32B parameters with a naming-game protocol. Restricted first-token scores over tokenizer-safe labels let us measure prompt-conditioned score-state distributions, construct state-similarity graphs, and separate...

    arxiv.org/abs/2607.12077 · PDF

  46. 46

    Designing Agent-Ready Websites for AI Web Agents: A Framework for Machine Readability, Actionability, and Decision Reliability

    Said Elnaffar, Farzad Rashidi

    cs.AI · cs.HC

    Online shopping is increasingly shifting toward a model in which AI agents independently search for products, compare options, evaluate constraints, and carry out parts of the purchasing process for users. Website design must now support both human and agent-mediated interaction. This paper introduces the agent-ready website, a design framework for enhancing the readability, interpretability, verifiability, and actionability of e-commerce...

    arxiv.org/abs/2607.12056 · 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.