cs.AI · 2026-06-29 · No. 38

Artificial Intelligence, 2026-06-29.

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

01 — The papers

19 entries
  1. 01

    Agent-Native Immune System: Architecture, Taxonomy, and Engineering

    Bo Shen, Lifeng Chang, Tianyuan Wei, Yunpeng Li, Feng Shi, Yichen Han, Peijie Gao, Shiyi Kuang, Xin Chang, Dehui Li

    cs.AI · cs.MA

    The transition from static chat bots to autonomous agents--equipped with persistent memory, tool-use protocols, and multi-agent collaboration--has fundamentally expanded the AI threat landscape. Current defense mechanisms, such as perimeter security and training-time alignment, remain external to the agent's active reasoning loop. Consequently, they fall short: a fully aligned agent remains highly vulnerable to runtime hijacking via memory...

    arxiv.org/abs/2606.28270 · PDF

  2. 02

    Tandem Reinforcement Learning with Verifiable Rewards

    Difan Jiao, Raghav Singhal, Robert West, Ashton Anderson

    cs.AI

    Reinforcement learning with verifiable rewards (RLVR) has significantly improved the reasoning capability of large language models, reaching expert or even superhuman performance in domains such as competition math. However, whether weaker agents and humans can actually harness this capability is far less certain, with RLVR documented to drift reasoning toward idiosyncratic patterns such as poor readability and language mixing. Tandem...

    arxiv.org/abs/2606.28166 · PDF

  3. 03

    AI-Driven Synthesis for High-Tech System Design: Automating Innovation

    Luuk Oerlemans, Steven Westerhof, Theo Hofman

    cs.AI · cs.AR · cs.CE · cs.ET · cs.RO

    This article addresses the combinatorial complexity inherent in modern high-tech system design by presenting automation-in-design (AiD) as a transformative paradigm. We propose computational design synthesis (CDS), a framework utilising deep learning and generative AI to automate the creation of novel systems. Two case studies (e-drive system design and spatial dimensioning problem) serve as proof-points for this approach. The AI-driven...

    arxiv.org/abs/2606.28126 · PDF

  4. 04

    Ontology-Guided Evidence Path Inference for Multi-hop Knowledge Graph Question Answering

    Yongxue Shan, Meihan Wu, Cundi Fang, Jie Peng, Xiaodong Wang

    cs.AI

    Knowledge graph question answering (KGQA) aims to answer natural-language questions by reasoning over structured facts. Existing multi-hop KGQA methods mainly rely on topic-centered expansion, which faces two key challenges: the search space rapidly grows with noisy mixed-type paths, and retrieved paths may fail to satisfy the semantic constraints of complex questions. To address these challenges, we propose OPI, an ontology-guided evidence...

    arxiv.org/abs/2606.28076 · PDF

  5. 05

    JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications

    Oxygen AIIC, Chan Long, Chao Liu, Chaofan Chen, Chaohui Dong, Chunyuan Guo, Danping Liu, Debin Liu, Deping Xiang,...

    cs.AI

    JD.com, one of the world's largest e-commerce platforms, serves over 700 million active users and millions of merchants, with a catalog of tens of billions of SKUs. At this scale, high-quality, structured item knowledge underpins a better consumer experience, lower management costs, and higher operational efficiency-yet producing and serving it poses three industrial-scale challenges: fast-emerging concepts, high-quality knowledge production...

    arxiv.org/abs/2606.28070 · PDF

  6. 06

    Lifted Causal Inference

    Malte Luttermann, Tanya Braun, Ralf Möller, Marcel Gehrke

    cs.AI · cs.LG

    Lifted inference exploits indistinguishabilities in probabilistic graphical models by using a representative for indistinguishable objects, thereby speeding up query answering while maintaining exact answers. In this article, we show how lifting can be applied to efficiently compute causal effects in relational domains. More specifically, we introduce parametric causal factor graphs (PCFGs) to incorporate causal knowledge in lifted models and...

    arxiv.org/abs/2606.28024 · PDF

  7. 07

    RelBall: Relation Ball with Quaternion Rotation for Knowledge Graph Completion

    Yike Liu, Peijia Xie, Chao He, Huiling Zhu

    cs.AI

    Real-world knowledge graphs are often incomplete, lacking many valid facts. Knowledge Graph Completion (KGC) aims to predict missing links using known triples, thereby enhancing graph coverage. A key challenge is modeling diverse relational patterns such as symmetry, antisymmetry, inversion, composition and semantic hierarchy. Existing models such as RotatE can capture symmetric, antisymmetric, inverse, and commutative composition patterns,...

    arxiv.org/abs/2606.27967 · PDF

  8. 08

    Verifiable Geometry Problem Solving: Solver-Driven Autoformalization and Theorem Proposing

    Can Li, Ting Zhang, Junbo Zhao, Hua Huang

    cs.AI · cs.CL · cs.CV

    Geometry Problem Solving have increasingly adopt the neuro-symbolic paradigm, combining neural intuition with symbolic rigor. However, current frameworks suffer from severe bottlenecks in two core stages: autoformalization, which treats multimodal translation as a static task decoupled from downstream solver compatibility, and theorem prediction, where solvers frequently hit a deductive impasse due to fixed rule libraries. To address these,...

    arxiv.org/abs/2606.27926 · PDF

  9. 09

    NormAct: A Benchmark for Hidden Social Norm Compliance in Embodied Planning

    Shiyun Zhao, Xinwei Song, Tianyu Guo, Xiaomeng Gao, Mingyuan Liu, Xu Han, Yuanyuan Zhang, Zhenliang Zhang, Xue Feng, Bo Dai

    cs.AI

    Multimodal large language models (MLLMs) are increasingly deployed as embodied planners in egocentric environments, where task success requires not only achieving instructed goals but also acting in socially appropriate ways. While explicit goals may render certain actions optimal, implicit social norms often impose hidden constraints. Existing evaluations typically focus on explicit goal achievement or direct norm knowledge, seldom assessing...

    arxiv.org/abs/2606.27826 · PDF

  10. 10

    ATOD: Annealed Turn-aware On-policy Distillation for Multi-turn Autonomous Agents

    Qitai Tan, Zefang Zong, Yang Li, Peng Chen

    cs.AI

    Training small language-model agents for long-horizon interactive tasks requires both fast imitation and reward-driven improvement. On-policy distillation (OPD) provides dense teacher guidance and typically improves rapidly in the early stage, but its gains saturate once the student approaches the teacher, limiting the final performance ceiling. Reinforcement learning (RL) directly optimizes environment rewards and encourages exploratory...

    arxiv.org/abs/2606.27814 · PDF

  11. 11

    Grounded Iterative Language Planning: How Parameterized World Models Reduce Hallucination Propagation in LLM Agents

    Xinyuan Song, Zekun Cai

    cs.AI

    World models for language agents come in two useful forms. An agent-based world model calls an LLM API and reasons flexibly in language, but its errors appear as hallucinated state changes that are hard to score with ordinary regression losses. A parameterized world model is a trained transition predictor; its errors are easier to measure with quantities such as NodeMSE, delta accuracy, and validity accuracy, but it is usually weaker as a...

    arxiv.org/abs/2606.27806 · PDF

  12. 12

    Understanding Rollout Error in Graph World Models

    Xinyuan Song, Zekun Cai

    cs.AI

    World models are often used for planning by rolling learned dynamics forward. Many planning environments, however, are not vectors or images; they are graphs of agents, tools, skills, routes, and dependencies. In these settings, a local prediction error may stay local or spread through the graph, and the failure mode changes again when edges are predicted rather than fixed. This paper studies long-horizon rollout error in Graph World Models...

    arxiv.org/abs/2606.27780 · PDF

  13. 13

    Towards Reliable and Robust LLM Planning: Symbolic Feedback-Driven Iterative Self-Refinement Framework

    Jiajing Zhang, Jiamei Jiang, Chenyang Zhang, Feifei Mo, Linjing Li, Daniel Zeng

    cs.AI

    Large language models (LLMs) have attracted widespread attention from academia and industry, yet their deployment raises critical security concerns regarding robustness and reliability. Planning, a core component of intelligent behavior, remains challenging for LLMs, which often produce infeasible or incorrect solutions in long-horizon decision-making tasks due to inherent complexity. In this paper, we propose a symbolic feedback-driven...

    arxiv.org/abs/2606.27757 · PDF

  14. 14

    ToE: A Hierarchical and Explainable Claim Verification Framework with Dynamic Multi-source Evidence Retrieval and Aggregation

    Zhaoqi Wang, Zijian Zhang, Kun Zheng, Zhen Li, Xin Li, Chunlei Li, Jiamou Liu

    cs.AI · cs.CR

    The rapid spread of fake news poses increasing threats to information ecosystems, especially as AI-generated misinformation under Generative Engine Optimization (GEO) poisoning allows adversarially crafted content to be systematically surfaced by retrieval systems, contaminating LLM reasoning. In this paper, we propose Tree of Evidence (ToE), a hierarchical evidence reasoning framework for automated fact-checking that models each claim as a...

    arxiv.org/abs/2606.27736 · PDF

  15. 15

    MER-R1: Multimodal Emotion Reasoning via Slow-Fast Thinking Synergy

    Zhiyuan Han, Beier Zhu, Wenwen Tong, Chengwei Qin, Xinyi Wang, Jiayu Zhang, Jiangnan Chen, Hewei Guo, Dongchuan Ran,...

    cs.AI

    We find that explicit reasoning does not necessarily translate into better multimodal emotion recognition (MER) accuracy, even though it makes predictions more interpretable. Specifically, for reasoning-based MLLMs, fast thinking by triggering direct answers often outperforms slow thinking after deliberative reasoning. Our empirical analyses show that fast thinking improves recall with broader and more confident predictions, whereas slow...

    arxiv.org/abs/2606.27652 · PDF

  16. 16

    DysLexLens: A Low-Resource LLM Framework for Analysing Dyslexic Learners Insights from Online Forums

    Dana Rezazadegan, Atie Kia, Phongpadid Nandavong, Dominique Carlon, Jeremy Nguyen, Abhik Banerjee, James Marshall,...

    cs.AI · cs.CL · cs.HC · cs.IR · cs.LG

    Dyslexic learners increasingly use artificial intelligence (AI) tools to support reading, writing, organisation, and study-related tasks. However, their lived experiences with these tools remain largely underexamined. This paper proposes DysLexLens, a low-resource LLM framework, designed to analyse dyslexic learners experience with AI through online forum discussions. DysLexLens is designed as an end-to-end, evidence-traceable architecture...

    arxiv.org/abs/2606.27619 · PDF

  17. 17

    Odyssey: Constructing Verifiable Local Truth-Preserving Foundation Models

    Sridhar Mahadevan

    cs.AI · cs.LG

    We introduce a categorical framework called ODYSSEY for constructing verifiable, local truth-preserving foundation models as compositions of foundries: building-block architectural components that specify a cover of local contexts, local representation families, restriction maps, gluing rules, obstruction policies, update obligations, and human-facing views. A foundry is an organized sheaf of knowledge that carries within it an argumentation...

    arxiv.org/abs/2606.27593 · PDF

  18. 18

    Internalizing the Future: A Unified Agentic Training Paradigm for World Model Planning

    Xuan Zhang, Zhijian Zhou, Lingfeng Qiao, Yulei Qin, Ke Li, Xing Sun, Xiaoyu Tan, Chao Qu, Yuan Qi

    cs.AI

    Large language model (LLM) agents have demonstrated strong capability in sequential decision-making, yet they remains fundamentally reactive in long-horizon tasks. Unlike humans who employ "what-if" reasoning to evaluate potential plans before commitment, standard agents lack an internal world model to simulate future outcomes. Therefore, we propose to internalize future-aware planning by training a single autoregressive model to verbalize...

    arxiv.org/abs/2606.27483 · PDF

  19. 19

    When Does Personality Composition Matter for Multi-Agent LLM Teams?

    Aryan Keluskar, Amrita Bhattacharjee, Huan Liu

    cs.AI

    Personality prompting shapes how large language models communicate, yet whether these behavioral shifts affect objective task outcomes remains under-explored. Prior work shows that agents prompted with low agreeableness produce adversarial language, while those prompted with high agreeableness become cooperative, but the relationship between communication style and task performance has not been systematically examined across multiple domains....

    arxiv.org/abs/2606.27443 · 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.