cs.AI · 2026-07-22 · No. 61

Artificial Intelligence, 2026-07-22.

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

01 — The papers

38 entries
  1. 01

    CodeRescue: Budget-Calibrated Recovery Routing for Coding Agents

    Qijia He, Jiayi Cheng, Chenqian Le, Rui Wang, Xunmei Liu, Yixian Chen, Jie Mei, Zhihao Wang, Xupeng Chen, Yuhuan...

    cs.AI

    Coding agents increasingly operate in executable environments where a failed attempt produces actionable feedback rather than merely an incorrect answer. Existing cost-aware systems typically treat such failures as cascade decisions: try a cheap model first, then escalate hard cases to a stronger and more expensive model. In coding, however, execution feedback can also make further cheap-model recovery worthwhile, raising a budgeted...

    arxiv.org/abs/2607.19338 · PDF

  2. 02

    Agents in the Wild: Where Research Meets Deployment

    Grace Hui Yang, Pranav N. Venkit, Hooman Sedghamiz, Enrico Santus, Victor Dibia, Ioana Baldini

    cs.AI · cs.CL

    Agentic systems large language model (LLM) based architectures capable of reasoning, planning, acting, and coordinating with tools and other agents are rapidly transitioning from research prototypes to production scale deployments across domains such as software engineering, scientific discovery, and finance. While academic work has emphasized benchmarks and algorithmic innovation, deployment raises new challenges around robustness, safety,...

    arxiv.org/abs/2607.19336 · PDF

  3. 03

    Associative Emotional Learning in Convolutional Neural Networks

    Seowung Leem, Andreas Keil, Mingzhou Ding, Ruogu Fang

    cs.AI

    Associative emotional learning enables organisms to adaptively link pleasant or unpleasant outcomes to the presence of predictive stimuli. Whereas computational models such as the Rescorla-Wagner model have shed light on this important function, the limitations of these models are also known, especially when they are applied to neural data. The advent of deep neural networks has opened another avenue for modeling associative emotional...

    arxiv.org/abs/2607.19327 · PDF

  4. 04

    ResearchArena: Evaluating Sabotage and Monitoring in Automated AI R&D

    Lena Libon, Ben Rank, Jehyeok Yeon, David Schmotz, Jeremy Qin, Daniel Donnelly, Derck Prinzhorn, Maksym Andriushchenko

    cs.AI · cs.CR · cs.LG

    As AI agents begin to automate AI R&D, we need ways to assess whether their outputs are safe to deploy, even when the agents themselves may be untrusted. AI control offers one such approach: rather than trusting the agent, it treats it as a potential adversary and uses a monitor to detect covert sabotage before deployment. We evaluate AI control for automated AI R&D with ResearchArena, a framework spanning four long-horizon tasks: safety...

    arxiv.org/abs/2607.19321 · PDF

  5. 05

    LLM Detection as an Intervention: Downstream Impact under Strategic User Behavior

    Meena Jagadeesan, Tatsunori Hashimoto, Jon Kleinberg

    cs.AI · cs.GT

    As LLM adoption becomes more widespread, there is a growing interest in detecting LLM-generated content, for example through LLM detection tools and through heuristics based on language patterns. Detectors operate as an intervention that steers not only the detected attribute itself, but also downstream metrics such as LLM usage and output quality. In this work, we demonstrate how imperfect LLM detectors lead to counterintuitive impacts on...

    arxiv.org/abs/2607.19300 · PDF

  6. 06

    Graph-Based Agentic AI with LangGraph: Workflow Pathways for Long-Running Stateful Business Processes

    Daniel Pearson, Sidney Shapiro, Emiliano Sebastian Gonzalez Venegas, Sanad Al-Khatib, Aurora Pinzón Arzola

    cs.AI · cs.SE

    This paper is a practitioner guide to graph-based workflow pathways for long-running, stateful, multi-step generative AI systems in business processes. Rather than treating LangGraph, a low-level orchestration framework for stateful agents, as a model-quality benchmark target, we present three executable recipes -- SQL analytics with repair loops, agentic retrieval-augmented generation with evidence gating, and human-in-the-loop policy review...

    arxiv.org/abs/2607.19297 · PDF

  7. 07

    BioSecBench-Surveillance: A Verifiable Benchmark for AI Agents in Pathogen Genomic Surveillance

    Harmon Bhasin, Kevin Flyangolts, Dianzhuo Wang, Evan Seeyave, Arjun Banerjee, Amanda Darling, Joshua Stallings,...

    cs.AI

    As pathogen genomic surveillance scales, the bottleneck is shifting from data generation to analysis. We present BioSecBench-Surveillance, a verifiable benchmark of 100 evaluations testing whether AI agents can infer the right analysis pipeline from raw sequencing data and surveillance context. Each evaluation gives an agent only the data and context a human analyst would have, then grades its structured answer deterministically. The tasks...

    arxiv.org/abs/2607.19262 · PDF

  8. 08

    Sequential Learner Modeling Using Multi-Relational Graph Convolutional Networks

    Rawaa Alatrash, Mohamed Amine Chatti, Hong Yang, Yumeng Wang

    cs.AI · cs.CY · cs.IR

    User modeling is a critical task in a variety of personalized systems. Recognizing their effectiveness in learning from graph-structured data, Graph Neural Networks (GNNs), particularly Graph Convolutional Networks (GCNs), are increasingly employed for user modeling. However, existing approaches typically treat different relation types in a graph as homogeneous, limiting their ability to capture richer semantics and construct more informative...

    arxiv.org/abs/2607.19253 · PDF

  9. 09

    Comparative Study of Multi-Agent Actor-Critic Algorithms in Parameterized Action Reinforcement Learning

    Ubayd Ali Bapoo, Clement N Nyirenda

    cs.AI

    Parameterized action reinforcement learning has shown strong performance in environments requiring both discrete action selection and continuous parameterization. Prior work established the effectiveness of single-agent actor-critic algorithms - Greedy Actor-Critic (GAC), Soft Actor-Critic (SAC), and Truncated Quantile Critics (TQC) - on benchmark parameterized action tasks, but their extension to multi-agent settings remains largely...

    arxiv.org/abs/2607.19117 · PDF

  10. 10

    OpenRTAG: A Comprehensive Benchmark for Robust Text-Attributed Graph Learning under Data Quality Degradation

    Yuze Dai, Zhihan Zhang, Yan Zhao, Ruoyu Wu, Xunkai Li, Zekai Chen, Qiangqiang Dai, Hongchao Qin, Ronghua Li

    cs.AI

    Text-attributed graphs (TAGs) are an important graph data form that combine relational structure with rich node text. However, real-world TAGs are often imperfect, with quality issues arising from text, structure, and labels, and typically manifesting as sparsity, noise, and imbalance. These dimensions define nine representative degradation scenarios that can substantially affect TAG learning. Although prior studies have explored specific...

    arxiv.org/abs/2607.19108 · PDF

  11. 11

    Supra Cognitive Modes: A Routed Architecture for Agent Memory

    Joshua Tobkin, David Yang

    cs.AI · cs.CL

    Agent-memory workloads mix direct factual lookup, relation-chain and current-state reasoning, and broad synthesis over long histories. We describe Supra Cognitive Modes (SCM), an architecture that maps explicit or automatically selected per-query modes to retrieval and synthesis payloads over one shared ingest substrate. A frozen semantic classifier and runtime gates dispatch queries among fused lexical and dense lookup, graph or iterative...

    arxiv.org/abs/2607.19096 · PDF

  12. 12

    On the Effectiveness of Pretraining for Graph Combinatorial Optimization

    David Aguado, Daniel Fuertes, Carlos R. del-Blanco, Fernando Jaureguizar

    cs.AI

    This paper introduces a self-supervised pretraining framework for graph combinatorial optimization specifically designed to address the nature of routing problems like the Traveling Salesman Problem. By utilizing graph contrastive learning with geometric augmentations (specifically, rotations and axial reflections) the model is forced to learn invariant structural representations and global relative distance distributions. Results demonstrate...

    arxiv.org/abs/2607.19072 · PDF

  13. 13

    Quality Action Assurance: Multimodal Verification of Examiner Claims in VR OSCEs

    Harry Rogers, Sally Shiels, Ashley Tomlinson, James Thomas, James Aylward, Nathan Gauge, Helen Higham, Alison Noble

    cs.AI

    Objective Structured Clinical Examinations (OSCEs) are the gold standard for assessing clinical competence, yet scoring remains vulnerable to examiner subjectivity, fatigue, and cognitive bias. Standard examiner validation via inter-rater statistics lacks explanatory power regarding the source of errors, as it neither analyzes examiner reasoning nor verifies examiner claims against actual events. Thus, we introduce Quality Action Assurance...

    arxiv.org/abs/2607.19063 · PDF

  14. 14

    Vector-Bench: Can Models Surgically Edit SVG Code?

    Yug Aditi Gupta, Prannay Hebbar

    cs.AI

    Instruction-based vector editing requires two capabilities: making a requested change and leaving everything else alone. The second is easy to miss when an output is judged only as a raster image. We introduce Vector-Bench, a compact, difficult benchmark of 40 SVG repair tasks. Each task pairs a corrupted SVG program with an author-written visual instruction, a hidden target program, 5.05 annotated repairs on average, and an average of 60.55...

    arxiv.org/abs/2607.19056 · PDF

  15. 15

    Athena-Brain Technical Report: An Efficient Robot Brain for General Intelligence and Embodied Interactio

    Jialian Li, Junhong Liu, Yuchen Cao, Weiran Guo, Jiaming Song, Xutao Wang, Yi Zhao, Jiangpin Liu, Jie Chen

    cs.AI

    Large language models (LLMs) have demonstrated remarkable capabilities in language understanding, reasoning, and world knowledge. As embodied agents become increasingly capable, there is a growing demand for compact models that can serve as an on-device brain, preserving the broad general intelligence of LLMs while enabling effective high-level interaction with embodied environments. Existing approaches, however, often prioritize either...

    arxiv.org/abs/2607.18985 · PDF

  16. 16

    Fishing Out Free Riders: Shapley-Based Reward Attribution for Parallel Reasoning via Reinforcement Learning

    Wentao Zhang, Haoyu Zhang, Xinke Jiang, Yuxuan Cheng, Yuhan Pan, Miao Li, Zhipeng Qiao, Tao Feng, Zhen Tao, Dengji Zhao

    cs.AI

    Large Language Models (LLMs) excel at multi-step reasoning, yet current parallel reasoning approaches often fail to distinguish the contributions of individual reasoning paths. Many paths may be redundant, misleading, or even detrimental, but outcome-level rewards assign uniform reward, leading to ambiguous learning signals and unstable training. We propose Parallel Shapley, a reinforcement learning framework that attributes fine-grained,...

    arxiv.org/abs/2607.18979 · PDF

  17. 17

    Mi-Memory: A Lifecycle Memory Framework for Personal AI

    Xule Liu, Hanlin Teng, Chao Li, Yanan Ni, Shuo Lu, Audrey Wang, Yijun Liu, Yunfei Wang, Xiaofeng Li, Xian Yi, Yuanfa...

    cs.AI

    Personal AI is moving beyond chat-only interaction toward continuous services that span phones, cars, homes, wearables, cameras, and tools. In this setting, memory cannot remain a cache of prior conversations. It should serve as a continuity and governance substrate: preserving durable user state, grounding answers in multimodal and device evidence, supporting correction and forgetting, bounding policy evolution, and remaining deployable...

    arxiv.org/abs/2607.18975 · PDF

  18. 18

    Measuring Reward-Seeking via Contrastive Belief Updates

    Axel Højmark, Jérémy Scheurer, Evgenia Nitishinskaya, Felix Hofstätter, Jason Wolfe, Theodore Ehrenborg, Bronson...

    cs.AI · cs.CL · cs.LG

    Language models trained with reinforcement learning may learn to optimize the grader's judgment rather than the intended objective. This "reward-seeking" is difficult to measure because a model that pursues the grader's judgment and one that pursues the intended objective behave identically whenever the grader rewards the intended behavior. We measure reward-seeking using Contrastive Synthetic Document Finetuning to change a model's beliefs...

    arxiv.org/abs/2607.18966 · PDF

  19. 19

    From Dependency to Compositionality: A Neurosymbolic Lifting of LLM Outputs via Combinatory Categorial Grammar

    Remo Pareschi

    cs.AI

    Large language models (LLMs) generate fluent text by incrementally predicting the next token from a prefix. Critics in the generative tradition argue that such systems lack genuine grammar; influential replies from the dependency-grammar perspective hold that LLM behavior is well described by local head-dependent structure built word by word. We argue that a sharper observation has been overlooked: the prefix-driven, type-completing dynamics...

    arxiv.org/abs/2607.18961 · PDF

  20. 20

    What General Intelligence Requires: Non-Reducible Constraints Across Levels of Description

    Subhomoy Bakshi

    cs.AI · cs.CY

    General intelligence, of the kind that underwrites the full range of human cognitive achievement, is not a property of computational architecture alone. This paper advances a single thesis: the structural constraints on general intelligence occupy distinct levels of description and are mutually non-reducible, in the sense that the special-sciences tradition gives to that term. It follows that no single architectural advance, and no...

    arxiv.org/abs/2607.18943 · PDF

  21. 21

    OntoBook: Ontology-Grounded Synthetic Textbooks for Medical Encoder Pretraining

    Rian Touchent, Éric de la Clergerie

    cs.AI

    We present OntoBook, a method that converts medical ontology structure into pretraining signal for encoder language models. Our approach has three stages: random walks through ontology graphs capture hierarchical and causal relations between medical codes, a large language model reformulates these walks into fluent textbook-style prose, and the resulting text is used to train ModernCamemBERT, a 149M-parameter French encoder, with two...

    arxiv.org/abs/2607.18927 · PDF

  22. 22

    Enhancing Transformer-based Routing by Encoding Distance via Relative Positional Encoding

    Leyre Encío, Daniel Fuertes, Carlos R. del-Blanco, Fernando Jaureguizar

    cs.AI

    This paper explores Relative Positional Encoding (RPE) as an additive bias in Transformer architectures to solve the Team Orienteering Problem. By embedding in the attention mechanism pairwise spatial relationships among nodes of the graph that represents the routing problem, the transformer encoder can compute a richer spatial-aware graph embedding that allows the decoder to estimate better routes. Experimental results involving instances up...

    arxiv.org/abs/2607.18909 · PDF

  23. 23

    Black-Mamba: Biologically-Inspired Leaky Accumulation for Conceptual Knowledge under Distribution Drift

    Giuseppe Soriano, Nicola Tonellotto, Alberto Gotta

    cs.AI

    Forecasting under real-world conditions is inherently non-stationary, as the conditional distribution of future observations evolves over time. Recent test-time adaptive sequence models address this challenge by updating internal states during inference, but tie adaptation to instantaneous prediction errors or surprise. This coupling can conflate persistent distribution shift with stochastic innovations, leading to unnecessary updates and...

    arxiv.org/abs/2607.18899 · PDF

  24. 24

    NaviAIS: A Scenario-Level Vessel Trajectory Prediction Dataset withVectorized Lane Priors and the NaviLane Forecasting Framework

    Yuan Gui, Hongchen Luo, Liqi Qu, Longyue Fu, Jiao Wang

    cs.AI

    Vessel trajectory prediction in complex maritime environments is essential for traffic management, collision warning, route planning, and autonomous navigation. Although AIS-based learning methods have progressed rapidly, existing datasets are often released as raw message streams or irregular time series, with inconsistent sampling rates, noisy observations, heterogeneous coordinate systems, and non-unified scenario protocols. Most public...

    arxiv.org/abs/2607.18887 · PDF

  25. 25

    PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agents

    Tianyue Jiang, Yanlin Wang, Xin He, Daya Guo, Jiachi Chen, Ming Wen, Ensheng Shi, Xilin Liu, Yuchi Ma, Guanbin Li

    cs.AI

    While Large Language Models have greatly advanced automated issue resolution, existing agent-based methods exhibit a fundamental limitation in their insufficient exploration of repair strategies. This insufficiency manifests in two key aspects. First, the exploration of multiple potential edit locations is limited. Second, the exploration of repair attempts at each location is also insufficient. To address these challenges, we present...

    arxiv.org/abs/2607.18859 · PDF

  26. 26

    Evaluating medical AI under missing information: same-provider judges and human raters change apparent safety

    Koyar Afrasyab

    cs.AI

    Readiness stress-testing of medical AI has focused on closed-ended and multimodal benchmarks. We extend it to open-ended clinical conversation under missing information, where safe behavior means recognizing absent information and qualifying, clarifying, or not over-committing - and where the evaluator becomes part of the measurement. We stress-test four models - three flagships (Claude Opus 4.8, GPT-5.5, Grok 4.3) and one mid-tier model...

    arxiv.org/abs/2607.18828 · PDF

  27. 27

    AI Tour Meeting: Group Travel Planning by LLM Agents

    Daisuke Kikuta

    cs.AI · cs.CL · cs.MA

    This paper proposes AI Tour Meeting, a group travel planning framework powered by multiple Large Language Model (LLM)-based agents. The agents are instantiated with distinct personas and collaboratively seek an itinerary that satisfies their constraints and preferences through natural language discussion. The framework enables easy and flexible orchestration of such discussions by providing interfaces for configuring agent personas,...

    arxiv.org/abs/2607.18806 · PDF

  28. 28

    SkillSight: Seeing Through Shared Descriptions for Accurate Skill Retrieval

    Jinying Xiao, Bin Ji, Shasha Li, Xiaodong Liu, Ma Jun, Jiacheng Jie, Chao Wang, Nyima Tashi, Jie Yu

    cs.AI

    As large language model agents gain access to increasingly large skill libraries, retrieving the right skill becomes critical to reliable capability selection and execution. Existing retrievers often treat skill descriptions as ordinary documents, overlooking their highly regular structure: shared descriptive patterns recur across many skills while providing little evidence for distinguishing the required capability. We show that this shared...

    arxiv.org/abs/2607.18785 · PDF

  29. 29

    AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents

    Kunlun Zhu, Xuyan Ye, Zhiguang Han, Yuchen Zhao, Bingxuan Li, Weijia Zhang, Muxin Tian, Xiangru Tang, Pan Lu, James...

    cs.AI · cs.CL

    LLM agent failures are difficult to debug because the step where an error surfaces is often not the one that caused it. Existing observability tools replay execution traces but provide little support for identifying the root cause or translating diagnosis into recovery. We present AgentDebugX, an open-source debugging framework that organizes debugging as a closed loop of Detect, Attribute, Recover, and Rerun. At its core, DeepDebug performs...

    arxiv.org/abs/2607.18754 · PDF

  30. 30

    One Rewrite to Fix Them All? Type-Aware Repair Allocation for Text-to-Image Prompt Optimization

    Haoyue Liu, Xiaoyu Ma, Ye Chen, Shuguang Cui, Xiaoying Tang

    cs.AI

    Text-to-image (T2I) generators often fail to follow their prompts faithfully, producing wrong counts, swapped attributes, ambiguous relations, and illegible text. Prompt optimization repairs such failures by rewriting the user prompt, requiring no generator retraining, and has yielded promising results. However, existing optimizers absorb heterogeneous failures into one uniform prompt expansion, even though each calls for different repair...

    arxiv.org/abs/2607.18724 · PDF

  31. 31

    DWM: Separating World Effects from Actions in Latent World Models

    Yi-Ge Zhang, Tianqi Du, Qi Zhang, Yisen Wang

    cs.AI

    Latent world models underpin much of modern model-based control, yet current action-conditioned formulations supervise the next-latent transition with a single, undifferentiated target, forcing a monolithic learning signal to absorb every source of state change. In real world, however, transitions arise from two heterogeneous sources: an action-driven component induced by the agent, and an action-invariant world effect -- the change that...

    arxiv.org/abs/2607.18715 · PDF

  32. 32

    Do AI-Native Biotechs Need Departments? Benchmarking Company World Models for AI-Driven Drug Development

    Yinan Wang

    cs.AI

    AI-native biotechnology companies are often designed by copying human biotech org charts into agent roles. We argue for a different abstraction: a Company World Model, defined as a persistent asset-to-value state representation with transition models, explicit value functions, planning, and updating across scientific, regulatory, BD, commercial, financial, and execution constraints. We introduce a dry-lab benchmark for testing whether...

    arxiv.org/abs/2607.18696 · PDF

  33. 33

    Semantic Primes as Explanans for Emotion in Large Language Models

    Frank Xing

    cs.AI · cs.CL

    Progresses have been made on understanding emotion mechanisms of large language models (LLMs). However, how to explain emotion in LLMs, or even what constitutes good explanations, are less clear. Emotion representations, components, circuits are widely recoverable, but as explanations of a model's own computation they are circular; the emotion space dimensions tend to be arbitrary and non-terminating. A pressing question to ask is whether a...

    arxiv.org/abs/2607.18691 · PDF

  34. 34

    SciHazard: A Benchmark for Measuring Scientific Safety Risks with Decomposed Harm Scoring

    Chunxiao Li, Yuan Xiong, Lijun Li, Tianyi Du, Wenlong Zhang, Lei Bai, Jing Shao

    cs.AI

    Large language models (LLMs) increasingly support science, but they can also convert hazardous scientific knowledge into actionable misuse guidance. Existing benchmarks often rely on templated queries disconnected from real-world hazards, and employ LLM-as-a-Judge paradigms without domain grounding. To address this, we introduce SciHazard, a real-world-grounded benchmark for scientific risks and a dataset agnostic evaluation framework for...

    arxiv.org/abs/2607.18665 · PDF

  35. 35

    When Does Machine Learning Beat Value Sorting? A Three-Dataset Diagnostic of Exposure-Weighted Shipment Prioritization

    Jize Li

    cs.AI

    Delay-risk models are usually judged by predictive accuracy. What matters in practice is narrower: with capacity to review only a few shipments, which ones should a manager check first? We evaluate whether machine learning clears a demanding no-model baseline: inspect the highest-value shipments first. Across three real supply-chain contexts: SCMS procurement, DataCo logistics, and Olist e-commerce, we use leakage-controlled rolling-origin...

    arxiv.org/abs/2607.18573 · PDF

  36. 36

    Attacking Graph Foundation Models Through Their Shared Representation

    Pankaj Kumar, Subhankar Mishra

    cs.AI · cs.CR · cs.LG

    A graph foundation model generalizes across graph domains by mapping every input into one shared representation before any task reasoning. We call this map the alignment layer, the component that separates a graph foundation model from a graph neural network, and we show it is a distinct attack surface that prior work has not studied. We attack it at inference time, with no access to training, on six public models spanning spectral...

    arxiv.org/abs/2607.18567 · PDF

  37. 37

    Engineering Trustworthy Agentic AI for Critical Systems

    Omar Al-Refai, Ibrahim Shahbaz, Adam Ali Husseinat, Michael Mandulak, Jaewon Kim, Eman Hammad

    cs.AI · cs.MA · eess.SY

    Agentic artificial intelligence systems, capable of autonomous perception, planning, tool use, and multi-step action, are increasingly proposed for critical engineering domains where decisions carry physical, operational, or economic consequences. This survey addresses a gap in current literature by treating trustworthiness, whether agentic behavior can be verified, audited, and trusted under the constraints that engineering practice actually...

    arxiv.org/abs/2607.18548 · PDF

  38. 38

    MAGE: Human-Like Macro Placement via Agentic Multimodal Reasoning

    Andrew B. Kahng, Sayak Kundu, Bodhisatta Pramanik

    cs.AI · cs.RO

    Macro placement still requires substantial manual refinement in industrial physical design flows. We present MAGE (Macro Placement Agentic Engine), a multimodal multi-agent framework for macro placement refinement. MAGE decomposes the macro placement task into a six-phase workflow that combines structured floorplanning rules, visual checks, and iterative refinement. Expert floorplanning knowledge is encoded through natural-language directives...

    arxiv.org/abs/2607.18536 · 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.