The paper reports on a deployed multi‑agent tender‑response system that uses an open‑weights language model under sovereignty constraints. In a blind comparison, the system’s answers were judged at least as good as human‑written bids in 40 of 55 sections, with only a few gaps attributable to missing knowledge rather than writing quality. The study also demonstrates an asymmetry in conditioning: while structural markup improves reading tasks, converting instruction material from prose to nested XML degrades answer quality, and naming forbidden constructions concentrates defects.
By Cheng Yu, Nikhil Mathew, Zhengjie Wang
VortexChat is an agentic framework that autonomously performs end-to-end inverse design of integrated photonic devices from natural language specifications. It combines a large language model decision agent with topology generation, gradient-based refinement, and full-wave electromagnetic simulation in a closed-loop architecture, enabling iterative decomposition of design objectives and minimal human intervention. The system successfully generated devices meeting the Vortex100 Benchmark metrics and fabricated a broadband terahertz perfect vortex beam multiplexer that matched simulation predictions.
By Faqian Chong, Yulun Wu, Shilong Li, Andrew Forbes, Hongsheng Chen, Song Han
The paper introduces the Agentic Adoption Index (AAI), a new metric that captures whether workers actually delegate tasks to AI within their workflows, rather than merely measuring potential AI applicability. Using 53,000 agent skill specifications and 18,000 O*NET task statements, the authors find that occupations with high delegation differ from those previously deemed most at risk, that AAI aligns more closely with AI’s capabilities than current usage, and that adoption peaks at mid‑wage, bachelor’s‑level occupations while declining at both ends of the wage and education spectrum. The study highlights that technical availability explains much of the variation, but other factors—such as resistance to specification or professional discretion—also influence who adopts AI.
whyItMatters":"The findings suggest that actual AI adoption patterns differ from prior risk assessments, indicating that factors beyond technical feasibility shape who delegates to AI, which has implications for workforce planning and policy."
By Hyeongjae Lee, Jihyang Cheon, Lanu Kim
PhotoBench is a new benchmark built from authentic personal photo albums that moves beyond simple visual matching to focus on personalized, intent-driven retrieval. It incorporates a multi-source profiling framework that combines visual semantics, spatial‑temporal metadata, social identity, and temporal events to generate complex queries reflecting users’ life trajectories. Evaluation on PhotoBench reveals two key limitations: a modality gap where unified embedding models fail on non‑visual constraints, and a source fusion paradox where agentic systems struggle with tool orchestration.
By Tianyi Xu, Rong Shan, Junjie Wu, Jiadeng Huang, Teng Wang, Jiachen Zhu, Wenteng Chen, Minxin Tu, Quantao Dou, Zhaoxiang Wang, Changwang Zhang, Weinan Zhang, Jun Wang, Jianghao Lin
arXiv:2603.11252v2 Announce Type: replace
Abstract: Although semantic 3D city models are internationally available and becoming increasingly detailed, the incorporation of material information remain...
By Benedikt Schwab, Thomas H. Kolbe
arXiv:2608.21136v1 Announce Type: new
Abstract: Recently, open-vocabulary zero-shot 3D scene understanding using vision foundation models has emerged as a promising alternative to data-intensive supe...
By Jie Xu, Na Zhao
arXiv:2608.21066v1 Announce Type: new
Abstract: Deploying autonomous systems in safety-critical domains demands guaranteed robustness against physically plausible geometric perturbations rather than...
By Gregoire Theau, Melanie Ducoffe
arXiv:2608.20483v1 Announce Type: cross
Abstract: We develop analytical and particle-based methods for uncertainty propagation in random neural network models, where both the inputs and network param...
By Janice Adams, Daniele Venturi
arXiv:2608.21345v1 Announce Type: new
Abstract: Self-refinement, typically structured as generation, critique, and revision, is a widely adopted paradigm for improving LLM generation and serves as a...
By Zhuoyi Yang, Ian G. Harris, Salar Hashemitaheri, Cassie Huang, Yuangang Li, Hyunwoo Oh, Paul Dourish, Tony Givargis, Mohsen Imani, Li Zhang
arXiv:2608.21099v1 Announce Type: cross
Abstract: Multi-modal object detection is essential for robust scene understanding in challenging conditions, including low-light and adverse environments. Rec...
By Jiekang Feng, Zhihe Fan, Yunqi Zhu, Xinjie Yao, Yueying Zhang, Yike Gao, Ranxin Li, Guanzuo Chen
The paper introduces BUMEX, a reinforcement learning exploration strategy that leverages a set of prior models containing the true transition kernel and reward function. By optimizing over this model set, the method derives upper and lower bounds on the Q‑function to guide exploration, providing theoretical guarantees of convergence to the optimal policy. When the model set follows a bounded‑parameter MDP structure, the optimization becomes convex, enabling finite‑time convergence under mild assumptions and demonstrating accelerated learning in simulations.
By J. S. van Hulst, W. P. M. H. Heemels, D. J. Antunes
The study examines how adding a security-requirements section to prompts affects web applications generated by a large language model. Six distinct applications were produced twice—once with a baseline prompt and once with a security-aware prompt—yielding 12 programs. Analysis of these programs revealed 75 confirmed security findings, with the security-aware variants showing fewer issues (24 vs. 51) and no Critical or High severity problems.
By Darko Andro\v{c}ec
AudioWorldSim is an open‑source platform that generates realistic binaural audio datasets for training and evaluating audio‑based machine learning models, especially world models. It extends Meta’s SoundSpaces 2.0 by automating random agent navigation and correcting continuous sound composition. The project is publicly available on GitHub to support reproducibility in research.
By Luis Vitor Zerkowski, Luiz Velho
The paper introduces an LLM-as-a-Judge framework for evaluating the outputs of an agentic drug discovery assistant, ChatInvent, deployed at AstraZeneca. It defines four quality dimensions—Completeness, Relevancy, Structural Clarity, and Scope Adherence—alongside deterministic Tool Call Correctness checks, and validates the judge against five expert annotators. After optimizing the best-performing judge with few-shot demonstrations, alignment with human majority votes improves from 0.80 to 0.86, and the framework reveals that informal question phrasing does not degrade output quality.
By Emma Granqvist, Roc\'io Mercado, Samuel Genheden
AsmEvo is an agentic assembly-level optimizer that targets compiled AMDGPU code objects, reconstructing a reassemblable representation and applying low-level edits guided by a long-horizon agent. It rebuilds ABI-preserving optimized objects and verifies functional equivalence through differential testing against the original binary. Experiments show significant speedups—up to 1.35× geometric mean on MI308X and 1.18× on MI300X—while maintaining correctness.
By Ji Liu, Puyuan Yang, Rongzhang Zheng, Fan Wang, Jinglin Wang, Muhammad A. Awad, Mortis Huang, Andy Chang, Zekai Li, Zeping Li, Zihao An, Yue Liu, Yuchen Yang, Jianghui Wang, Chushi Chen, Ziqiong Liu, Fuwei Yang, Dong Li, Wen Heng Chung, Shengcai Liu, Emad Barsoum
Tree-of-Concerns is a multi‑agent framework that uses specialized skeptic personas to conduct parallel debate trees, each focusing on a specific category of potential limitations in scientific papers. The system employs structured, evidence‑grounded argumentation and a panel review mechanism to correct drift and miscalibration, ultimately extracting unstated limitations. Experiments on the ToC‑Bench benchmark show that the approach improves precision by 79% and coverage by 11% over leading baselines, providing reviewers with specific, evidence‑based concerns for systematic evaluation.
By Sahil Mishra, Niranjan Rajeev, Tanmoy Chakraborty
The paper investigates how small lexical changes in prompts can cause large performance swings in large language models. Using a dataset of 132,000 prompt variants, the authors uncover a scaling law linking higher average task performance to lower variance and greater robustness. They identify domain-specific terminology and explicit action directives as key linguistic factors that stabilize prompts, and propose an automated Prompt-Refining Agent that reduces performance variance by 40.7% in code generation while maintaining or improving mean performance.
By Qipeng Xie, Zi Liang, Jiafei Wu, Yufei Chen, Weizheng Wang, Wenao Ma, Zhong Ming, Haiqin Yang, Kaishun Wu
BridgeGuard is an air‑gapped, agentic Retrieval‑Augmented Generation system designed to automate compliance verification for the Federal Highway Administration’s bridge inspection requirements. It combines vector search over the FHWA Recording and Coding Guide with structured SQL queries against National Bridge Inventory data, guided by a stateful multi‑step ReAct planning loop that runs locally on commodity edge hardware. The system achieves near‑perfect classification and citation accuracy on large bridge inventories while operating without external network access, and ablation studies show that both vector search and the agentic loop are essential for correct compliance reasoning.
By Viraj Nishesh Darji, Hemaliben Rakeshkumar Darji
The paper introduces the concept of personalized privacy for large language models, allowing user‑specific disclosure preferences to guide information sharing. It presents P3Bench, a benchmark that extends contextual privacy policies with personalized rules, and shows that existing prompt‑based methods often ignore these policies. To improve compliance, the authors propose “Repair”, an inference‑time attention head intervention that aligns model responses with user‑specific privacy rules.
By Junseok Kim, Nakyeong Yang, Kyomin Jung
The paper introduces OneModel, a paradigm that consolidates complex business workflows and SOPs into a single model’s parameters, replacing traditional modular pipelines. By using Continual Pre‑Training and logic‑compilation SFT, the authors transform fragmented rules into unified attention‑based reasoning. In a global financial service deployment, OneModel cuts end‑to‑end latency by over 50 % and raises the Intelligent Resolution Rate from 64.3 % to 83.3 %.
By Chang Liu, Chaoyang Ning, Dayi Jiang, Enrui Gu, Fang Ran, Hongyan Xue, Huaqing Li, Hui Cai, Jia Liu, Jiang-Ming Yang, Jianshe Li, Jiawei Luo, Jin Zhou, Leshen Zhu, Lihui Chen, Liying Ma, Lyuxin Xue, Mengjian Ji, Ruijia Xu, Wei Ren, Wei Wu, Xiaoling Qu, Xiaoyun Feng, Xin Zhang, Xixie Zhou, Xuanwei Hu, Yan Chen, Yichao Wang, Yongqi Tong, Yu Liu, Yuhong Zhou, Zemin Sun, Zhenwen Xu, Zhiling Liu, Zifan Wang