The paper introduces a thermodynamic framework for agents that interact with their environment through percept-action loops, extending the study of information processing beyond passive observation. It defines the work capacity of an agent as the maximum rate at which it can extract work from its surroundings. The authors find that agents achieving high work efficiency must balance predictive accuracy with forgetting, indicating a trade‑off between prediction and energy efficiency in active learning systems.
By Lukas J. Fiderer, Paul C. Barth, Isaac D. Smith, Hans J. Briegel
The paper introduces SEAR, a four-task benchmark that evaluates audio language models (ALMs) for audio deepfake detection by requiring acoustic evidence identification, quantification, deepfake detection, and forensic rationale generation. It also proposes BAEA, an acoustic evidence agent that equips a frozen ALM with controlled acoustic tools under fixed or adaptive evidence-acquisition policies. Experiments with six ALMs show a gap between plausible rationales and verifiable acoustic evidence reasoning, and demonstrate that BAEA‑Fixed improves final verdicts and forensic rationales while revealing that misleading evidence harms detection and grounding performance.
By Rong Wan, Suliu Qin, Jiaxi Li, Wei Xie, Wenwu Wang, Xiaolong Han, Lu Yin, Xilu Wang
The paper introduces RateAR, a benchmark of AR images and videos that captures perceptual factors such as object placement, scale, and shadow consistency. Eleven commercial vision‑language models (VLMs) are evaluated on this benchmark, with VLM‑based quality predictions showing strong correlation with human judgments (Spearman’s ρ up to 0.8695). Using contextual prompting, the authors build an automated AR content adjustment system that, in a 21‑participant study, improved placement and size coherence of virtual content for over 90% of users.
By Elias Rotondo (Duke University), Lin Duan (Duke University), Yanming Xiu (Duke University), Sangjun Eom (Duke University), Conrad Li (Duke University), Maria Gorlatova (Duke University)
LiteReality-Agent is an agentic system that reconstructs real indoor environments into realistic, articulated, and simulation-ready 3D scenes from RGB‑D scans. It treats reconstruction as a coding problem, where a coding agent iteratively edits a Python script (Room.py) using specialized tools, while an observe‑edit‑verify harness ensures evidence gathering, measurement, verification, layout optimisation, simulation readiness, and quality control. The system outperforms recent models like Astra and Fable in geometric accuracy, visual realism, and simulation compatibility, and its modular framework is positioned as a robust foundation for future agent‑driven reconstruction tasks.
By Zhening Huang, Yueyan Li, Johnathan Chiu, Xiaoyang Lyu, Matt Zhou, Yuxin Yao, Joan Lasenby, Shangzhe Wu
MapLightning introduces a new approach to online vectorized HD map construction that replaces dense bird’s‑eye‑view grids with a compact set of 1D learnable map tokens. Using a transformer‑based mapper that applies full self‑attention to combined image and map tokens, the method achieves efficient inference, lower memory usage, and improved global context without relying on camera projection parameters. Experiments on nuScenes and Argoverse 2 show state‑of‑the‑art accuracy, with a lightweight variant outperforming MapTRv2 by over 10 mAP and running 1.73× faster at 40+ FPS while using 53 % less memory.
By Shen Zheng, Anurag Ghosh, Mani Ramanagopal, Srinivasa Narasimhan
Oneira is an interactive video world model that links open-ended generation with persistent interaction. It uses a coding agent to manage an extensible world state, allowing newly generated or discovered entities to become actionable and ensuring that changes made by an agent are retained across video segments. Experiments demonstrate that Oneira supports consistent interaction with new objects while preserving prior interaction effects over long horizons.
By Xindi Yang, Baolu Li, Liam Lee, Zhenfei Yin, Songxin Zhang, Zhuoyang Song, Xu Jia, Jianfei Cai, Tien-Tsin Wong, Bingyi Jing, Mengyue Yang
World Observer introduces a joint actor‑observer framework for persistent world modeling, decoupling the agent’s view from panoramic observers that track regions outside the actor’s field of view. By warping from a shared panoramic source and using an Observer Sink for high‑resolution references, the method maintains accurate object states and dynamics even when they leave and re‑enter the actor’s view. The approach is evaluated with new world‑space metrics and a benchmark across real and synthetic scenes, showing improved out‑of‑view dynamics while preserving visual fidelity, camera control, and 3D adherence.
By Hyunwook Choi, Dahyun Chung, Hyunsung Kim, Siyoon Jin, Jinhyeok Choi, Junyoung Seo, Seungryong Kim
FocusGraph is a framework for selecting keyframes in egocentric long‑video question answering. It uses a lightweight Scene‑Graph LLM Selector to identify query‑relevant clips from graph‑based captions, then extracts keyframes with Patch‑wise Sparse‑Flow Retention (PSFR) before feeding them to a multimodal large language model for answer generation. The method achieves state‑of‑the‑art performance on FindingDory and HourVideo while reducing question‑time inference cost.
By Tatiana Zemskova, Solomon Andryushenko, Ilya Obrubov, Viktoriia Khoruzhaia, Ekaterina Eroshenko, Ekaterina Derevyanka, Dmitry Yudin
VideoWeaver is an agent harness and benchmark for long‑video generation that evaluates and evolves reusable skills. It allows an agent to dynamically compose foundation skills into a workflow based on a single high‑level instruction, rather than following a static pipeline. The benchmark includes 16 task categories and 285 cases with multimodal references, and an evidence‑grounded agent‑as‑judge inspects execution traces and final videos to guide skill evolution, improving both process and output quality.
By Jianhui Wei, Yan Zhang, Jie Tan, Hengchuan Zhu, Xiaotian Zhang, Ziyi Chen, Daoan Zhang, Wei Xu, Yeying Jin, Zuozhu Liu
The article discusses how the rapid development of artificial intelligence (AI) and machine learning (ML) is transforming chemical engineering by influencing problem formulation, analysis, and solution across a wide range of applications, from atomic-scale simulations to industrial operations. It highlights recent methodological advances and representative uses, noting a shift from purely black-box models to hybrid and physics-informed frameworks that incorporate conservation laws, thermodynamic consistency, and structural constraints. These integrated approaches enhance robustness, reliability, and human-AI collaboration, ultimately amplifying rather than replacing core chemical engineering principles.
By Michael Baldea, Linda J. Broadbelt, Marianthi G. Ierapetritou, Akhilesh Jain, Ankur Kumar, Thomas A. Kwan, F\`elix Llovell, Andrew J. Medford, Ilias Mitrai, Joel Paulson, Junyi Qiao, Matthew P. Rivera, Kirti C. Sahu, Lev Sarkisov, Zachary P. Smith, Calvin Tsay, Ching-Mei Wen, Victor M. Zavala, Huacheng Zhang, Dan Zhao
The paper introduces the global coherence problem, where AI agents make locally valid decisions that collectively lead to an invalid outcome due to shared state failures. It presents the Observation‑Aliasing Impossibility Theorem, establishing that a policy can guarantee a valid action only when all indistinguishable worlds share an admissible action, and shows that even with additional reasoning, roles, messages, or samples, the missing distinction cannot be recovered. The authors propose a local‑to‑global runtime semantics framework and conduct nine studies demonstrating that missing global state cannot be substituted by local intelligence.
By Xin Heng
The paper demonstrates that a verifier used in closed‑loop agent debugging can inadvertently reveal the answer it is meant to test, rendering solver comparisons meaningless. In a study of 12 development cases, both exact minimum hitting set and a greedy method returned identical supports, and an audit showed that exact‑anchor predicates always produced the planted fault pair. The authors propose a support‑gated verification contract that requires a clean reference map and runtime evidence before an independently calibrated signal can confirm a detection, and validate this approach on 1,440 held‑out cases with a low false‑admission rate.
By Peiying Zhu, Sidi Chang
The article surveys LLM-based agentic reasoning frameworks, presenting a unified formal language that categorizes them into single-agent, tool-based, and multi-agent methods. It reviews application scenarios in scientific discovery, healthcare, software engineering, society, economics, and general-purpose tasks, and compares the distinct features and evaluation strategies of each category. The survey highlights the rapid development of complex agentic systems in real-world contexts.
By Bingxi Zhao, Lin Geng Foo, Ping Hu, Christian Theobalt, Hossein Rahmani, Jun Liu
GENSCRIPT is an inference‑only pipeline that generates synthetic data without training a generative model. It creates a deterministic statistical profile of the source data, uses a language model to infer field semantics and cross‑column constraints, and then compiles these into an executable sampler that works for single‑table, temporal, and relational data. The method builds generators in minutes, samples large datasets quickly, and achieves fidelity comparable to leading methods while preserving key data relationships such as 1‑to‑1 mappings and primary‑foreign key constraints.
By Zilong Zhao, Abdul Raheem, Jiayu Li, Sohei Arisaka, Darius Lim Hong Yi, Milad Abdollahzadeh, Uzair Javaid, Biplab Sikdar
VTR-Bench is a new benchmark designed to evaluate how well video generation models render text within scenes. It includes 300 prompts across five real-world scenarios such as advertisements and scientific videos, and uses an automated pipeline with human alignment to assess text fidelity and scene/motion requirements. Experiments on 11 state‑of‑the‑art models show that even the best performer has a word error rate of 0.250, underscoring widespread challenges in visual text rendering.
By Yu Huang, Jungang Li, Zhiyuan Wang, Yonghua Hei, Song Dai, Jiayu Yang, Deyuan Liu, Xiang Zheng, Xiaoshuang Shi, Hao Cheng, Kaidi Xu
The paper reviews one‑pixel attacks (OPAs), highlighting their extreme adversarial fragility across domains such as medical diagnosis, autonomous driving, biometrics, and quantum communication. It presents a PRISMA‑guided synthesis of studies from 2017 to 2026, offering a unified taxonomy that covers algorithmic foundations, black‑box evolutionary optimization, hybrid and program‑synthesis attacks, defence mechanisms, interpretability tools, and domain‑specific vulnerabilities. The review identifies dominant Differential Evolution strategies, emerging efficiency‑optimized and saliency‑guided methods, and gaps in dataset diversity, transferability, and evaluation standards, while proposing future research directions and a regulatory framework for robustness testing and AI security governance.
By Mirza Niaz Morshed, Md. Masudul Islam, Galib Muhammad Shahriar Himel, Md. Aslam Uddin, Hui Liu, Md. Shafiqul Islam
K‑Dense BYOK is a free, open‑source AI research assistant that runs locally on a researcher’s own computer. It provides a structured environment with scientific procedures, workflow templates, and a living lab notebook that logs all actions without allowing the agent to alter the record. The system emphasizes reproducibility by recording the software environment and offering commands to regenerate results, outperforming managed platforms on interdisciplinary research prompts.
By Aubrey M. Brueckner, Darshil Patel, Yuhuan He, Timothy Kassis
The study evaluates whether detailed, profession‑specific system prompts improve performance on scientific tasks. Using an open‑source corpus of 503 agent profiles and Gemini 3.8 Flash, the authors compared matched profiles to four control prompts across nine text‑based science benchmarks and a tool‑using bioinformatics benchmark. Results show no consistent accuracy gains; matched profiles actually increased token usage and cost, and in some cases reduced success rates, with only a minor advantage in one benchmark likely due to prompt length rather than domain expertise.
By Timothy Kassis
The paper introduces Rules to Tools (R2T), a system that provides executable checks for scientific coding agents to verify compliance with public scientific requirements. In experiments across multiple task cohorts, agents using R2T’s prepared checks achieved high repair success rates—26/30 with text and 29/30 with checks—while also demonstrating varying task preferences and cost trade‑offs. The study quantifies how tool‑enabled checks influence repair outcomes and agent‑side resource usage in scientific computing contexts.
By Jingjie Ning, Guojiang Zhao, Chen Xu, Shanshan Zhong, Xiaochuan Li, Ji Zeng, Guolin Ke
The paper introduces GAVA, a grounded arbitration framework that enables text-based embodied agents to decide whether to accept, reject, inspect, or ask for clarification when a user’s correction might be incorrect. In the ALFWorld environment, GAVA achieves perfect correction accuracy through local inspections and reduces interaction costs compared to always-verify baselines, especially when leveraging semantic priors. The study demonstrates that selective information gathering can lower declared joint costs, though it does not conclusively prove a general advantage of environmental value of information over clarification.
By Yezhou Cheng, Runjia Du, Zeming Liu, Hang Lyu, Zehua Yang, Bojun Lin