Large language model (LLM) agents are increasingly extended through Agent Skills, reusable artifacts that package natural-language metadata, procedural instructions, and execution-time resources for runtime use. As open-source skill marketplaces expand, users and agents increasingly rely on brief metadata to select third-party skills, making it difficult to detect inconsistencies between a skill's description and its true behavior, a problem we call cross-layer misalignment.
Large language model (LLM) agents are beginning to automate machine learning engineering (MLE) by coupling planning, code execution, debugging, and empirical feedback. Translating this capability to medical imaging remains difficult because each task imposes modality-specific experimentation and strict requirements for validation protocols and prediction artifacts.
Agentic retrieval-augmented generation (RAG) extends static RAG by allowing language models to iteratively reason, generate search queries, retrieve evidence, and predict answers. However, it remains challenging for models to decide when to retrieve, whether to use lexical matching or semantic similarity, and how to control context granularity to prevent irrelevant tokens from interfering with agent reasoning.
Recommendation systems, from traditional multi-stage to recent unified generative architectures, face challenges in incorporating diverse contextual signals, such as trending topics, breaking news, cultural events, and cross-surface user activities, into their ranking pipelines. These systems are designed to consume structured behavioral signals with consistent schemas, and lack the reasoning capability to naturally process unstructured or heterogeneously formatted contextual information.
Recommender systems increasingly face a choice among heterogeneous agents -- collaborative filters, sequential models, content-based retrievers, and LLM-based rerankers -- yet no single agent is uniformly best. We study this choice as task-aware agent ranking under cost constraints using RouteRec, a framework that compares request-level hard selection with item-level learned aggregation over four traditional recommender agents and one LLM reranker agent.
Internet of Things (IoT) systems are inherently vulnerable due to constrained hardware, outdated firmware, and insecure default configurations, creating a need for scalable and adaptive security testing approaches. While recent adoptions of Large Language Model (LLM) agents have demonstrated promise in penetration testing and Capture-the-Flag (CTF) environments, their application to IoT specific vulnerabilities remains unexplored.
Large language models (LLMs) have shown increasing promise in solving open problems in mathematics. However, their performance can be further improved through agentic workflows tailored to real-world mathematical practice.
What our over-dependence on external consulting teaches us about delegating our minds to machines The post The Big Con of Agentic AI appeared first on Towards Data Science .
By Chinmay Kakatkar
arXiv:2607. 08375v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have advanced end-to-end autonomous driving.
By Xuerun Yan, Zhexi Lian, Nuoheng Zhang, Shiyu Fang, Haoran Wang, Chen Lv, Jia Hu, Binyang Song
arXiv:2607. 08252v1 Announce Type: new Abstract: Long-term persona agents must remain identifiable while adapting to new events, relationships, evidence, and social conditions.
By Mengchen Li
arXiv:2607. 08028v1 Announce Type: new Abstract: Enterprise large language model (LLM) applications often begin as prototypes whose behavior is carried by prompts and retrieval context.
By Joongho Ahn, Moonsoo Kim
arXiv:2607. 08331v1 Announce Type: cross Abstract: Understanding how artworks are created requires reasoning about the iterative decisions, material operations, and contextual influences that shape artistic production.
By Kaustubh Kumar, Ashutosh Ranjan, Vivek Srivastava, Blessin Varkey, Shirish Karande
arXiv:2607. 08647v1 Announce Type: cross Abstract: As autonomous agents are increasingly deployed across diverse operational contexts, aligning their behavior with human intent demands reward functions that remain robust to such changes rather than overfitting to any single environment.
By Ali Larian, Qian Lin, Chang Zong Wu, Daniel S. Brown
arXiv:2607. 08391v1 Announce Type: cross Abstract: Making tradeoffs between execution latency and result utility (i.
By Ahmet Soyyigit, Shuochao Yao, Heechul Yun
arXiv:2607. 08497v1 Announce Type: cross Abstract: Recent unified multimodal models show a single architecture can jointly perform vision/language understanding and image generation/editing.
By Feng Wang, Canmiao Fu, Zhipeng Huang, Chen Li, Jing Lyu, Ge Li
arXiv:2605. 17361v2 Announce Type: replace-cross Abstract: Multi-agent systems (MAS) powered by large language models (LLMs) have emerged as a powerful paradigm for complex problem solving, where performance critically depends on the underlying inter-agent communication topology.
By Xuefei Wang, Jialu Wang, Fengbo Zhang, Yihan Hu, Di Zhang, Yutong Ye, Yikun Ban, Jun Han, Ruijie Wang
arXiv:2607. 08193v1 Announce Type: cross Abstract: Open-ended curricula in Reinforcement Learning (RL) aim to train generally-capable agents by identifying tasks that facilitate learning increasingly complex skills.
By Lorenzo Pant\`e, Andrea Fanti, Roberto Capobianco
arXiv:2607. 07753v1 Announce Type: cross Abstract: Modelling psychological disorders in artificial agents offers both a testbed for computational psychiatry and a lens on the failure modes of affective control.
By Hari Prasad
arXiv:2607. 08043v1 Announce Type: cross Abstract: Research software collaborations span meetings, informal chats, pull requests, and GitHub issues.
By Kshitij Dani, Cordero Core, Landung Setiawan, Carlos Garcia Jurado Suarez, Anshul Tambay, Vani Mandava, Anant Mittal
arXiv:2607. 08124v1 Announce Type: cross Abstract: The behavior of an LLM agent is determined not only by the underlying model, but also by its harness: the executable program that constructs context, invokes tools, verifies intermediate results, and recovers from failures.
By Jun Nie, Yonggang Zhang, Jun Song, Qianshu Cai, Dahai Yu, Yike Guo, Xinmei Tian, Bo Han