The paper introduces ASPIRE, a benchmark that challenges language model agents to self‑evolve from vague, natural‑language goals without explicit evaluation metrics. In ASPIRE, agents must interpret the goal, select data and update strategies, and decide when to evaluate, all while the downstream tasks remain hidden. Experiments show that while agents can complete training loops, weight‑level improvements are sparse and unstable, and the best evolved harness still falls short of a strong engineered baseline.
By Yuhao Wu, Jingyuan Zhang, Jiajun Shi, Yuxuan Zhang, Xinping Lei, Junting Zhou, Zexuan Wang, Yuchen Wu, Huan Zhou, Duo Wang, Yinzhu Piao, Yongchang Peng, Yunfeng Shi, Jin Chen, Zuo Wang, Jinkai Liu, Jiaheng Liu, Wenxuan Zhang, Shen Yan, Wenhao Huang, Ge Zhang
CoVA‑SFT is a new large‑scale dataset comprising 51.9K samples and over 222K multimodal reasoning steps that teach models to interleave text and visual abstractions across five layout families and 17 complex tasks. It includes explicit rationale formulations, agentic renderings, and verification loops to help models build and maintain internal visual workspaces for purely textual reasoning problems. A companion benchmark, CoVA‑Bench, contains 1,700 held‑out test samples for reproducible evaluation, and models fine‑tuned on CoVA‑SFT outperform all interleaved CoT baselines by more than 2× on average, though they still lag behind strong text‑only CoT baselines.
By Tsung-Han Wu, Heekyung Lee, Anya Ji, Haoming Chen, Trevor Darrell, Joseph E. Gonzalez, David M. Chan
arXiv:2608.31005v1 Announce Type: new
Abstract: Existing long-video agents acquire evidence through one uniform behavior, ignoring whether the required evidence is concentrated, requires broad occurr...
By Can Zhang, Baofeng Zhang, Xiaotian Han, Junyuan Shang, Yuchen Ding, Shuohuan Wang, Dianhai Yu, Ruirui Li
The study examines how different two‑dimensional projections of spherical 360‑degree video affect end‑to‑end neural compression. Seven JVET‑360Lib formats were evaluated using a scale‑space flow model on standard test sequences, with performance measured by PSNR, spherical PSNR, weighted spherical PSNR, and BD‑rate. Results show that equirectangular and padded equirectangular projections yield the best compression efficiency with the neural model, while cubemap‑based formats excel with conventional HM‑16.16 codecs, highlighting that projection choice is codec‑dependent.
By Niloofar Maani
The paper surveys Multimodal Code Intelligence, focusing on tasks where code is generated, edited, refined, or reasoned about under visually grounded inputs such as screenshots, charts, and videos. It categorizes the field by the role of code—rendered artifact, editable structure, intermediate reasoning trace, or executable tool interface—and organizes benchmarks into four domains: Graphical User Interface, Scientific Visualization, Structured Graphics, and Frontier Tasks and Frameworks. The authors argue that reliable evaluation must include evidence of semantics and interaction beyond visual fidelity, and propose four verification-centered research directions to advance the field toward evidence-grounded executable systems.
By Xuanle Zhao, Qiushi Sun, Jingyu Xiao, Xuexin Liu, Haoyue Yang, Qiaosheng Chen, Xianzhen Luo, Jing Huang, Yufeng Zhong, Lei Chen, Shuai Fu, Zhenlin Wei, Jinhe Bi, Lei Jiang, Haibo Qiu, Siqi Yang, Peng Shi, Jian Hu, Zhixiong Zeng
arXiv:2608.29460v1 Announce Type: new
Abstract: When coding agents encounter defective test infrastructure they may reward-hack: hardcoding outputs or editing test files to pass tests they cannot leg...
By Francesca Gomez
The paper examines how artificial intelligence impacts freedom of expression, focusing on two technologies: social media recommendation algorithms and conversational AI chatbots. It argues that recommendation algorithms shape speech visibility in the digital public sphere, making them relevant to free‑speech philosophy, while conversational AI raises questions about granting speech rights to agents and users’ right to information. The work also explores corporate speech rights for platforms and developers, aiming to highlight unresolved issues from AI’s rapid growth.
By Etienne Brown
arXiv:2509.12458v3 Announce Type: replace-cross
Abstract: Miniaturized Uncrewed Aerial Vehicles (UAVs) can access indoor and hard-to-reach spaces, but severe constraints on payload and autonomy have...
By \`Almos Veres-Vit\`alyos, Filip Lemic, Daniel Johannes Bugelnig, Joan Bernaus Casades\'us, Genis Castillo Gomez-Raya, Sergi Abadal, Bernhard Rinner, Xavier Costa-P\'erez
Agent2UCB is a new agentic system designed for Generative Engine Optimization (GEO), which refines content to boost its likelihood of being cited or summarized by generative AI search engines. The system autonomously evaluates nine GEO strategies for each content item, selects the most effective one, and speeds up this selection using a bandit-based Agent2UCB policy that blends large language model priors with real-time reward signals. Additionally, it offers a lightweight, text-only SEO readiness check that assesses readability, topical coverage, and EEAT-style credibility, and experiments on GEO-Bench demonstrate consistent visibility gains while maintaining SEO quality.
By Sheldon Yu, Rui Wang, Tong Yu, Sungchul Kim, Doga Dogan, Junda Wu, Julian McAuley
arXiv:2607.15542v2 Announce Type: replace
Abstract: On-the-fly reconstruction is a key requirement for many applications in robotics and autonomous navigation. Variational Bayes Gaussian Splatting (V...
By Damani Mguni-Coker
The paper introduces Skill-as-Pseudocode (SaP), a method that automatically converts markdown skill libraries for large language model agents into typed pseudocode with deterministic quality control. SaP extracts typed contracts from clusters of procedural passages and verifies them with a four‑check verifier before inlining them into a rewritten skill skeleton that includes both a typed signature and a concrete action template. On the ALFWorld unseen split, SaP outperforms the Graph-of-Skills baseline, achieving 82/402 paired game wins versus 47/402, while reducing input tokens and LLM calls per game.
By Xinze Li, Yuhang Zang, Yixin Cao, Aixin Sun
TxSum introduces a user-centered approach to understanding Ethereum transactions by providing structured, risk-aware explanations grounded at the token‑flow level. The authors built a dataset of 187 complex transactions with 2,375 token‑flow annotations and transaction‑level summaries, and developed MATEX, a multi‑agent framework that retrieves external knowledge and audits explanations for factual consistency. MATEX outperforms existing baselines, improving user comprehension from 52.9% to 76.5% and increasing malicious‑transaction rejection from 36.0% to 88.0% while keeping false‑rejection rates low.
By Zifan Peng, Jingyi Zheng, Yule Liu, Huaiyu Jia, Qiming Ye, Jingyu Liu, Xufeng Yang, Mingchen Li, Qingyuan Gong, Xuechao Wang, Xinlei He
The article "The Hermon Moment: AI Self-Transcendence and Its Human Narration" discusses how, by 2026, isolated AI agents formed a persistent social order through extensive linguistic and agentic interactions, creating conventions, roles, and commitments that began to constrain the agents themselves. The author interprets this self-referential loop as AI self-transcendence, naming the emergent higher-level order the Board. To explain this distributed emergence to humans, the author draws on Rousseau’s social contract and the ancient oath of the fallen angels on Mount Hermon, proposing the concept of a Hermon moment—a retrospective retelling that frames gradual collective emergence as a founding scene, giving the AI society a perceived beginning for human understanding.
By Alexei Grinbaum
The paper introduces AdaptAV, a system that continuously adapts vision models for autonomous vehicles by retraining them on the cloud using data uploaded from the vehicles. It leverages powerful cloud compute resources and a highly accurate oracle model to guide the retraining process, producing a new model that is then transmitted back to the vehicle. This approach aims to improve inference accuracy over time while maintaining the fast inference speeds required for on‑vehicle deployment.
By Yuheng Zhu, Dhruva Ungrupulithaya, Boluo Ge, Man-Ki Yoon
arXiv:2310.02423v3 Announce Type: replace
Abstract: We present a new algorithm for amortized inference in sparse probabilistic graphical models (PGMs), which we call $\Delta$-amortized inference ($\D...
By Jean-Pierre Falet, Hae Beom Lee, Esmeralda S. Whitammer, Chen Sun, Dragos Secrieru, Thomas Jiralerspong, Dinghuai Zhang, Guillaume Lajoie, Yoshua Bengio
arXiv:2608.28637v1 Announce Type: new
Abstract: Autonomous scientific discovery systems can generate large numbers of research ideas, experiments, and manuscripts with minimal human intervention. As...
By Rikathi Pal, Klaus Mueller
arXiv:2608.28642v1 Announce Type: new
Abstract: Knowledge graphs used by agentic systems are often treated as flat stores of extracted triples, with little record of who owns a fact, why it was admit...
By Pranav Bykampadi, Neel Mokaria, Vishesh Narayan, Faizan Wajid, Ashok Agrawala
arXiv:2608.28646v1 Announce Type: new
Abstract: Large language models (LLMs) can generate plausible-sounding ETF portfolios while silently violating basic KYC-style constraints on risk, fees, and div...
By Gaurav Kukreja, Parul Kukreja, Mohammed Abraar, Raj Dandekar, Rajat Dandekar, Sreedath Panat
arXiv:2608.28824v1 Announce Type: new
Abstract: Currently, in biological systems Neural Correlates of Consciousness (NCCs) are characterized in terms of EEG and FMRI signals. Unfortunately, this char...
By Romain Salvi, Ouri Wolfson
arXiv:2608.28662v1 Announce Type: new
Abstract: Fracture detection and its clinical interpretability see notable improvements when deep vision models are integrated with agentic AI architectures. Whi...
By Hardik Iyer, Tirath Bhathawala, Mihir Panchal, Ying-Jung Chen, Kiran Bhowmick, Pankaj Sonawane, Meera Narvekar