Tootfinder

Google launches the Agent Payments Protocol, or AP2, designed to securely facilitate agent-led payments across platforms, with the support of over 60 companies (Sabrina Ortiz/ZDNET)
https://www.zdnet.com/article/googles-new-

Google's new open protocol secures AI agent transactions - and 60 companies already support it
The Agent Payments Protocol aims to help consumers and businesses finally trust AI-enabled payments.

Open Source, Open Threats? Investigating Security Challenges in Open-Source Software
Seyed Ali Akhavani, Behzad Ousat, Amin Kharraz
https://arxiv.org/abs/2506.12995

Open Source, Open Threats? Investigating Security Challenges in Open-Source Software
Open-source software (OSS) has become increasingly more popular across different domains. However, this rapid development and widespread adoption come with a security cost. The growing complexity and openness of OSS ecosystems have led to increased exposure to vulnerabilities and attack surfaces. This paper investigates the trends and patterns of reported vulnerabilities within OSS platforms, focusing on the implications of these findings for security practices. To understand the dynamics of OS…

Social Media Reactions to Open Source Promotions: AI-Powered GitHub Projects on Hacker News
Prachnachai Meakpaiboonwattana, Warittha Tarntong, Thai Mekratanavorakul, Chaiyong Ragkhitwetsagul, Pattaraporn Sangaroonsilp, Raula Kula, Morakot Choetkiertikul, Kenichi Matsumoto, Thanwadee Sunetnanta
https://arxiv.org/abs/2506.12643

Social Media Reactions to Open Source Promotions: AI-Powered GitHub Projects on Hacker News
Social media platforms have become more influential than traditional news sources, shaping public discourse and accelerating the spread of information. With the rapid advancement of artificial intelligence (AI), open-source software (OSS) projects can leverage these platforms to gain visibility and attract contributors. In this study, we investigate the relationship between Hacker News, a social news site focused on computer science and entrepreneurship, and the extent to which it influences de…

LearnLens: An AI-Enhanced Dashboard to Support Teachers in Open-Ended Classrooms
Namrata Srivastava, Shruti Jain, Clayton Cohn, Naveeduddin Mohammed, Umesh Timalsina, Gautam Biswas
https://arxiv.org/abs/2509.10582

LearnLens: An AI-Enhanced Dashboard to Support Teachers in Open-Ended Classrooms
Exploratory learning environments (ELEs), such as simulation-based platforms and open-ended science curricula, promote hands-on exploration and problem-solving but make it difficult for teachers to gain timely insights into students' conceptual understanding. This paper presents LearnLens, a generative AI (GenAI)-enhanced teacher-facing dashboard designed to support problem-based instruction in middle school science. LearnLens processes students' open-ended responses from digital assessments to…

An Open-Source User-Friendly Interface for Simulating Magnetic Soft Robots using Simulation Open Framework Architecture (SOFA)
Carla Wehner, Finn Schubert, Heiko Hellkamp, Julius Hahnewald, Kilian Scheafer, Muhammad Bilal Khan, Oliver Gutfleisch
https://arxiv.org/abs/2508.10686

An Open-Source User-Friendly Interface for Simulating Magnetic Soft Robots using Simulation Open Framework Architecture (SOFA)
Soft robots, particularly magnetic soft robots, require specialized simulation tools to accurately model their deformation under external magnetic fields. However, existing platforms often lack dedicated support for magnetic materials, making them difficult to use for researchers at different expertise levels. This work introduces an open-source, user-friendly simulation interface using the Simulation Open Framework Architecture (SOFA), specifically designed to model magnetic soft robots. The t…

Boosting Scientific Error-Bounded Lossy Compression through Optimized Synergistic Lossy-Lossless Orchestration
Shixun Wu, Jinwen Pan, Jinyang Liu, Jiannan Tian, Ziwei Qiu, Jiajun Huang, Kai Zhao, Xin Liang, Sheng Di, Zizhong Chen, Franck Cappello
https://arxiv.org/abs/2507.11165

Boosting Scientific Error-Bounded Lossy Compression through Optimized Synergistic Lossy-Lossless Orchestration
As high-performance computing architectures evolve, more scientific computing workflows are being deployed on advanced computing platforms such as GPUs. These workflows can produce raw data at extremely high throughputs, requiring urgent high-ratio and low-latency error-bounded data compression solutions. In this paper, we propose cuSZ-Hi, an optimized high-ratio GPU-based scientific error-bounded lossy compressor with a flexible, domain-irrelevant, and fully open-source framework design. Our n…

Sources: OpenAI plans to launch an open-weight model as soon as next week on Hugging Face and other platforms, its first open-weight release since GPT-2 in 2019 (Tom Warren/The Verge)
https://www.theverge.com/notepad-microsoft

OpenAI’s open language model is imminent
OpenAI is ready to launch its new open AI model. The release could come as soon as next week, according to sources familiar with OpenAI’s plans.

Whenever I Google for something and it gives me a Facebook link for a *public* post/page, clicking on it from my mobile immediately redirects me to the Google Play Store.
No, I don't want to download your shitty app, Facebook to look at a single link.
So it turns out that if I put the browser in desktop mode, all of a sudden I can open that link.
Social media platforms nowadays have gotten so bad that the only way they get users is by forcing them into the platform and …

LightAgent: Production-level Open-source Agentic AI Framework
Weige Cai, Tong Zhu, Jinyi Niu, Ruiqi Hu, Lingyao Li, Tenglong Wang, Xiaowu Dai, Weining Shen, Liwen Zhang
https://arxiv.org/abs/2509.09292

LightAgent: Production-level Open-source Agentic AI Framework
With the rapid advancement of large language models (LLMs), Multi-agent Systems (MAS) have achieved significant progress in various application scenarios. However, substantial challenges remain in designing versatile, robust, and efficient platforms for agent deployment. To address these limitations, we propose \textbf{LightAgent}, a lightweight yet powerful agentic framework, effectively resolving the trade-off between flexibility and simplicity found in existing frameworks. LightAgent integra…

User Exploration and Exploitation Behavior Under the Influence of Real-time Interactions in Live Streaming Environments
Akira Matsui, Kazuki Fujikawa, Ryo Sasaki, Ryo Adachi
https://arxiv.org/abs/2509.09138

User Exploration and Exploitation Behavior Under the Influence of Real-time Interactions in Live Streaming Environments
Live streaming platforms offer a distinctive way for users and content creators to interact with each other through real-time communication. While research on user behavior in online platforms has explored how users discover their favorite content from creators and engage with them, the role of real-time features remains unclear. There are open questions as to what commonalities and differences exist in users' relationships with live streaming platforms compared to traditional on-demand style p…

AGILOped: Agile Open-Source Humanoid Robot for Research
Grzegorz Ficht, Luis Denninger, Sven Behnke
https://arxiv.org/abs/2509.09364 https://arxiv.org/pdf/…

AGILOped: Agile Open-Source Humanoid Robot for Research
With academic and commercial interest for humanoid robots peaking, multiple platforms are being developed. Through a high level of customization, they showcase impressive performance. Most of these systems remain closed-source or have high acquisition and maintenance costs, however. In this work, we present AGILOped - an open-source humanoid robot that closes the gap between high performance and accessibility. Our robot is driven by off-the-shelf backdrivable actuators with high power density a…

MIoT-Driven Comparison of Open Blockchain Platforms
Abdou-Essamad Jabri (UPJV, MIS), Mostafa Azizi (UPJV, MIS), Cyril Drocourt (UPJV, MIS), Gil Utard (MIS, UPJV)
https://arxiv.org/abs/2509.08399

MIoT-Driven Comparison of Open Blockchain Platforms
Being propelled by the fourth industrial revolution (Industry 4.0), IoT devices and solutions are well adopted everywhere, ranging from home applications to industrial use, crossing through transportation, healthcare, energy, and so on. This wide use of IoT has not gone unnoticed, hackers are tracking the weakness of such a technology and threatening them continuously. Their security at various levels has become an important concern of professionals and researchers. This issue takes more risk, …

Deterministic Equations for Feedback Control of Open Quantum Systems
Alberto J. B. Rosal, Patrick P. Potts, Gabriel T. Landi
https://arxiv.org/abs/2507.01934

Deterministic Equations for Feedback Control of Open Quantum Systems
Feedback control in open quantum dynamics is crucial for the advancement of various coherent platforms. For a proper theoretical description, however, most feedback schemes rely on stochastic trajectories, which require significant statistical sampling and lack analytical insight. Currently, only a handful of deterministic feedback master equations exist in the literature. In this letter we derive a set of deterministic equations for describing feedback schemes based on generic causal signals. …

ODYSSEY: Open-World Quadrupeds Exploration and Manipulation for Long-Horizon Tasks
Kaijun Wang, Liqin Lu, Mingyu Liu, Jianuo Jiang, Zeju Li, Bolin Zhang, Wancai Zheng, Xinyi Yu, Hao Chen, Chunhua Shen
https://arxiv.org/abs/2508.08240

ODYSSEY: Open-World Quadrupeds Exploration and Manipulation for Long-Horizon Tasks
Language-guided long-horizon mobile manipulation has long been a grand challenge in embodied semantic reasoning, generalizable manipulation, and adaptive locomotion. Three fundamental limitations hinder progress: First, although large language models have improved spatial reasoning and task planning through semantic priors, existing implementations remain confined to tabletop scenarios, failing to address the constrained perception and limited actuation ranges of mobile platforms. Second, curre…

Hmm. I should probably make ngscopeclient able to open scopesession files from the command line at some point.
Aaaand that's probably going to turn into figuring out how to register file associations on various platforms. Might not finish in time for v0.1 but it should happen soon

LEO: An Open-Source Platform for Linking OMERO with Lab Notebooks and Heterogeneous Metadata Sources
Rodrigo Escobar D\'iaz Guerrero, Jamile Mohammad Jafari, Tobias Meyer-Zedler, Michael Schmitt, Juergen Popp, Thomas Bocklitz
https://arxiv.org/abs/2508.00654

LEO: An Open-Source Platform for Linking OMERO with Lab Notebooks and Heterogeneous Metadata Sources
In the interdisciplinary field of microscopy research, managing and integrating large volumes of data stored across disparate platforms remains a major challenge. Data types such as bioimages, experimental records, and spectral information are often maintained in separate repositories, each following different management standards. However, linking these data sources across the research lifecycle is essential to align with the FAIR principles of data management: Findability, Accessibility, Inte…

Building an Open CGRA Ecosystem for Agile Innovation
Rohan Juneja, Pranav Dangi, Thilini Kaushalya Bandara, Zhaoying Li, Dhananjaya Wijerathne, Li-Shiuan Peh, Tulika Mitra
https://arxiv.org/abs/2508.19090

Building an Open CGRA Ecosystem for Agile Innovation
Modern computing workloads, particularly in AI and edge applications, demand hardware-software co-design to meet aggressive performance and energy targets. Such co-design benefits from open and agile platforms that replace closed, vertically integrated development with modular, community-driven ecosystems. Coarse-Grained Reconfigurable Architectures (CGRAs), with their unique balance of flexibility and efficiency are particularly well-suited for this paradigm. When built on open-source hardware…

On the Security of SSH Client Signatures
Fabian B\"aumer, Marcus Brinkmann, Maximilian Radoy, J\"org Schwenk, Juraj Somorovsky
https://arxiv.org/abs/2509.09331 https:/…

On the Security of SSH Client Signatures
Administrators and developers use SSH client keys and signatures for authentication, for example, to access internet backbone servers or to commit new code on platforms like GitHub. However, unlike servers, SSH clients cannot be measured through internet scans. We close this gap in two steps. First, we collect SSH client public keys. Such keys are regularly published by their owners on open development platforms like GitHub and GitLab. We systematize previous non-academic work by subjecting the…

Works-magnet: Accelerating Metadata Curation for Open Science
Eric Jeangirard
https://arxiv.org/abs/2506.14430 https://arxiv.org/pdf/…

Works-magnet: Accelerating Metadata Curation for Open Science
The transition to Open Science necessitates robust and reliable metadata. While national initiatives, such as the French Open Science Monitor, aim to track this evolution using open data, reliance on proprietary databases persists in many places. Open platforms like OpenAlex still require significant human intervention for data accuracy. This paper introduces Works-magnet, a project by the French Ministry of Higher Education and Research (MESR) Data Science & Engineering Team. Works-magnet is d…

BEAVR: Bimanual, multi-Embodiment, Accessible, Virtual Reality Teleoperation System for Robots
Alejandro Posadas-Nava, Alejandro Carrasco, Richard Linares
https://arxiv.org/abs/2508.09606

BEAVR: Bimanual, multi-Embodiment, Accessible, Virtual Reality Teleoperation System for Robots
\textbf{BEAVR} is an open-source, bimanual, multi-embodiment Virtual Reality (VR) teleoperation system for robots, designed to unify real-time control, data recording, and policy learning across heterogeneous robotic platforms. BEAVR enables real-time, dexterous teleoperation using commodity VR hardware, supports modular integration with robots ranging from 7-DoF manipulators to full-body humanoids, and records synchronized multi-modal demonstrations directly in the LeRobot dataset schema. Our …

CEMP: a platform unifying high-throughput online calculation, databases and predictive models for clean energy materials
Jifeng Wang, Jiazhe Ju, Ying Wang
https://arxiv.org/abs/2507.04423

CEMP: a platform unifying high-throughput online calculation, databases and predictive models for clean energy materials
The development of materials science is undergoing a shift from empirical approaches to data-driven and algorithm-oriented research paradigm. The state-of-the-art platforms are confined to inorganic crystals, with limited chemical space, sparse experimental data and a lack of integrated online computation for rapid validation. Here, we introduce the Clean Energy Materials Platform (CEMP), an open-access platform that integrates high-throughput computing workflows, multi-scale machine learning (…

Source: Yann LeCun will continue to work at Meta as chief scientist of the AI research group FAIR and will report to Alexandr Wang (Kurt Wagner/Bloomberg)
https://www.bloomberg.com/news/articles/2025-07-25/meta-says-open-ai…

Meta Says Open AI Hire is Superintelligence Group Chief Scientist
Mark Zuckerberg has named Shengjia Zhao, an artificial intelligence researcher who joined Meta Platforms Inc. from OpenAI in June, as the chief scientist for the social media company’s new superintelligence AI group.

SAKURAONE: Empowering Transparent and Open AI Platforms through Private-Sector HPC Investment in Japan
Fumikazu Konishi
https://arxiv.org/abs/2507.02124 ht…

SAKURAONE: Empowering Transparent and Open AI Platforms through Private-Sector HPC Investment in Japan
SAKURAONE is a managed high performance computing (HPC) cluster developed and operated by the SAKURA Internet Research Center. It reinforces the ``KOKARYOKU PHY'' configuration of bare-metal GPU servers and is designed as a cluster computing resource optimized for advanced workloads, including large language model (LLM) training. In the ISC 2025 edition of the TOP500 list, SAKURAONE was ranked \textbf{49th} in the world based on its High Performance Linpack (HPL) score, demonstrating its glob…

At the 2025 RISC-V Summit in China, Nvidia says CUDA will now be compatible with RISC-V's instruction set architecture, making RISC-V a viable x86 and Arm rival (Anton Shilov/Tom's Hardware)
https://www.

Nvidia's CUDA platform now supports RISC-V — support brings open source instruction set to AI platforms, joining x86 and Arm
Yet another alternative.

Ethical Classification of Non-Coding Contributions in Open-Source Projects via Large Language Models
Sergio Cobos, Javier Luis C\'anovas Izquierdo
https://arxiv.org/abs/2507.21583

Ethical Classification of Non-Coding Contributions in Open-Source Projects via Large Language Models
The development of Open-Source Software (OSS) is not only a technical challenge, but also a social one due to the diverse mixture of contributors. To this aim, social-coding platforms, such as GitHub, provide the infrastructure needed to host and develop the code, but also the support for enabling the community's collaboration, which is driven by non-coding contributions, such as issues (i.e., change proposals or bug reports) or comments to existing contributions. As with any other social endea…

"And we are doing it all with backward compatibility, so gamers could access their favourite titles across platforms." I guess they felt it should be stated even more clearly, since no one was really sure if Xbox console games would be included in this open strategy ->
AMD & Xbox | Advancing the Future of Gaming
https://w…

A Full-Stack Platform Architecture for Self-Organised Social Coordination
Matthew Scott, Jeremy Pitt
https://arxiv.org/abs/2507.01239 https://

A Full-Stack Platform Architecture for Self-Organised Social Coordination
To mitigate the restrictive centralising and monopolistic tendencies of platformisation, we aim to empower local communities by democratising platforms for self-organised social coordination. Our approach is to develop an open-source, full-stack architecture for platform development that supports ease of distribution and cloning, generativity, and a variety of hosting options. The architecture consists of a meta-platform that is used to instantiate a base platform with supporting libraries for …

Is SHACL Suitable for Data Quality Assessment?
Carolina Cort\'es Lasalle, Lisa Ehrlinger, Lorena Etcheverry, Felix Naumann
https://arxiv.org/abs/2507.22305 https://

Is SHACL Suitable for Data Quality Assessment?
Knowledge graphs have been widely adopted in both enterprises, such as the Google Knowledge Graph, and open platforms like Wikidata to represent domain knowledge and support analysis with artificial intelligence. They model real-world information as nodes and edges. To embrace flexibility, knowledge graphs often lack enforced schemas (i.e., ontologies), leading to potential data quality issues, such as semantically overlapping nodes. Therefore, ensuring their quality is essential, as issues in …

Automatically Generating High-Precision Simulated Road Networking in Traffic Scenario
Liang Xie, Wenke Huang
https://arxiv.org/abs/2509.02990 https://arxiv…

Automatically Generating High-Precision Simulated Road Networking in Traffic Scenario
Existing lane-level simulation road network generation is labor-intensive, resource-demanding, and costly due to the need for large-scale data collection and manual post-editing. To overcome these limitations, we propose automatically generating high-precision simulated road networks in traffic scenario, an efficient and fully automated solution. Initially, real-world road street view data is collected through open-source street view map platforms, and a large-scale street view lane line datase…

NeuroCoreX: An Open-Source FPGA-Based Spiking Neural Network Emulator with On-Chip Learning
Ashish Gautam, Prasanna Date, Shruti Kulkarni, Robert Patton, Thomas Potok
https://arxiv.org/abs/2506.14138

NeuroCoreX: An Open-Source FPGA-Based Spiking Neural Network Emulator with On-Chip Learning
Spiking Neural Networks (SNNs) are computational models inspired by the structure and dynamics of biological neuronal networks. Their event-driven nature enables them to achieve high energy efficiency, particularly when deployed on neuromorphic hardware platforms. Unlike conventional Artificial Neural Networks (ANNs), which primarily rely on layered architectures, SNNs naturally support a wide range of connectivity patterns, from traditional layered structures to small-world graphs characterize…

Open Source, Open Threats? Investigating Security Challenges in Open-Source Software
Seyed Ali Akhavani, Behzad Ousat, Amin Kharraz
https://arxiv.org/abs/2506.12995

Open Source, Open Threats? Investigating Security Challenges in Open-Source Software
Open-source software (OSS) has become increasingly more popular across different domains. However, this rapid development and widespread adoption come with a security cost. The growing complexity and openness of OSS ecosystems have led to increased exposure to vulnerabilities and attack surfaces. This paper investigates the trends and patterns of reported vulnerabilities within OSS platforms, focusing on the implications of these findings for security practices. To understand the dynamics of OS…

ClearerVoice-Studio: Bridging Advanced Speech Processing Research and Practical Deployment
Shengkui Zhao, Zexu Pan, Bin Ma
https://arxiv.org/abs/2506.19398

ClearerVoice-Studio: Bridging Advanced Speech Processing Research and Practical Deployment
This paper introduces ClearerVoice-Studio, an open-source, AI-powered speech processing toolkit designed to bridge cutting-edge research and practical application. Unlike broad platforms like SpeechBrain and ESPnet, ClearerVoice-Studio focuses on interconnected speech tasks of speech enhancement, separation, super-resolution, and multimodal target speaker extraction. A key advantage is its state-of-the-art pretrained models, including FRCRN with 3 million uses and MossFormer with 2.5 million us…

An Open-Source HW-SW Co-Development Framework Enabling Efficient Multi-Accelerator Systems
Ryan Albert Antonio, Joren Dumoulin, Xiaoling Yi, Josse Van Delm, Yunhao Deng, Guilherme Paim, Marian Verhelst
https://arxiv.org/abs/2508.14582

An Open-Source HW-SW Co-Development Framework Enabling Efficient Multi-Accelerator Systems
Heterogeneous accelerator-centric compute clusters are emerging as efficient solutions for diverse AI workloads. However, current integration strategies often compromise data movement efficiency and encounter compatibility issues in hardware and software. This prevents a unified approach that balances performance and ease of use. To this end, we present SNAX, an open-source integrated HW-SW framework enabling efficient multi-accelerator platforms through a novel hybrid-coupling scheme, consisti…

CHEMSMART: Chemistry Simulation and Modeling Automation Toolkit for High-Efficiency Computational Chemistry Workflows
Xinglong Zhang, Huiwen Tan, Jingyi Liu, Zihan Li, Lewen Wang, Benjamin W. J. Chen
https://arxiv.org/abs/2508.20042

CHEMSMART: Chemistry Simulation and Modeling Automation Toolkit for High-Efficiency Computational Chemistry Workflows
CHEMSMART (Chemistry Simulation and Modeling Automation Toolkit) is an open-source, Python-based framework designed to streamline quantum chemistry workflows for homogeneous catalysis and molecular modeling. By integrating job preparation, submission, execution, results analysis, and visualization, CHEMSMART addresses the inefficiencies of manual workflow management in computational chemistry by ensuring seamless interoperability with quantum chemistry packages and cheminformatics platforms. It…

FaaSGuard: Secure CI/CD for Serverless Applications -- An OpenFaaS Case Study
Amine Barrak, Emna Ksontini, Ridouane Atike, Fehmi Jaafar
https://arxiv.org/abs/2509.04328 https://…

FaaSGuard: Secure CI/CD for Serverless Applications -- An OpenFaaS Case Study
Serverless computing significantly alters software development by abstracting infrastructure management and enabling rapid, modular, event-driven deployments. Despite its benefits, the distinct characteristics of serverless functions, such as ephemeral execution and fine-grained scalability, pose unique security challenges, particularly in open-source platforms like OpenFaaS. Existing approaches typically address isolated phases of the DevSecOps lifecycle, lacking an integrated and comprehensiv…

Detecting Rug Pulls in Decentralized Exchanges: Machine Learning Evidence from the TON Blockchain
Dmitry Yaremus, Jianghai Li, Alisa Kalacheva, Igor Vodolazov, Yury Yanovich
https://arxiv.org/abs/2509.01168

Detecting Rug Pulls in Decentralized Exchanges: Machine Learning Evidence from the TON Blockchain
This paper presents a machine learning framework for the early detection of rug pull scams on decentralized exchanges (DEXs) within The Open Network (TON) blockchain. TON's unique architecture, characterized by asynchronous execution and a massive web2 user base from Telegram, presents a novel and critical environment for fraud analysis. We conduct a comprehensive study on the two largest TON DEXs, Ston.Fi and DeDust, fusing data from both platforms to train our models. A key contribution is th…

Flexible metadata harvesting for ecology using large language models
Zehao Lu, Thijs L van der Plas, Parinaz Rashidi, W Daniel Kissling, Ioannis N Athanasiadis
https://arxiv.org/abs/2508.20115

Flexible metadata harvesting for ecology using large language models
Large, open datasets can accelerate ecological research, particularly by enabling researchers to develop new insights by reusing datasets from multiple sources. However, to find the most suitable datasets to combine and integrate, researchers must navigate diverse ecological and environmental data provider platforms with varying metadata availability and standards. To overcome this obstacle, we have developed a large language model (LLM)-based metadata harvester that flexibly extracts metadata …

Quantum sensing of electron beams using solid-state spins
Jakob M. Grzesik, Dominic Catanzaro, Charles Roques-Carmes, Eric I. Rosenthal, Guido L. van de Stolpe, Aviv Karnieli, Giovanni Scuri, Souvik Biswas, Kenneth J. Leedle, Dylan S. Black, Robert L. Byer, Ido Kaminer, R. Joel England, Shanhui Fan, Olav Solgaard, Jelena Vu\v{c}kovi\'c
https://

Quantum sensing of electron beams using solid-state spins
Scattering experiments with energetic particles, such as free electrons, have been historically used to reveal the quantum structure of matter. However, realizing coherent interactions between free-electron beams and solid-state quantum systems has remained out of reach, owing to their intrinsically weak coupling. Realizing such coherent control would open up opportunities for hybrid quantum platforms combining free electrons and solid-state qubits for coincident quantum information processing …

A Scalable Trie Building Algorithm for High-Throughput Phyloanalysis of Wafer-Scale Digital Evolution Experiments
Vivaan Singhvi, Joey Wagner, Emily Dolson, Luis Zaman, Matthew Andres Moreno
https://arxiv.org/abs/2508.15074

A Scalable Trie Building Algorithm for High-Throughput Phyloanalysis of Wafer-Scale Digital Evolution Experiments
Agent-based simulation platforms play a key role in enabling fast-to-run evolution experiments that can be precisely controlled and observed in detail. Availability of high-resolution snapshots of lineage ancestries from digital experiments, in particular, is key to investigations of evolvability and open-ended evolution, as well as in providing a validation testbed for bioinformatics method development. Ongoing advances in AI/ML hardware accelerator devices, such as the 850,000-processor Cereb…

UAIbot: Beginner-friendly web-based simulator for interactive robotics learning and research
Johnata Brayan, Armando Alves Neto, Pavel Petrovi\v{c}, Gustavo M Freitas, Vinicius Mariano Gon\c{c}alves
https://arxiv.org/abs/2506.21178

UAIbot: Beginner-friendly web-based simulator for interactive robotics learning and research
This paper presents UAIbot, a free and open-source web-based robotics simulator designed to address the educational and research challenges conventional simulation platforms generally face. The Python and JavaScript interfaces of UAIbot enable accessible hands-on learning experiences without cumbersome installations. By allowing users to explore fundamental mathematical and physical principles interactively, ranging from manipulator kinematics to pedestrian flow dynamics, UAIbot provides an eff…

Dissecting the SWE-Bench Leaderboards: Profiling Submitters and Architectures of LLM- and Agent-Based Repair Systems
Matias Martinez, Xavier Franch
https://arxiv.org/abs/2506.17208

Dissecting the SWE-Bench Leaderboards: Profiling Submitters and Architectures of LLM- and Agent-Based Repair Systems
The rapid progress in Automated Program Repair (APR) has been driven by advances in AI, particularly large language models (LLMs) and agent-based systems. SWE-Bench is a recent benchmark designed to evaluate LLM-based repair systems using real issues and pull requests mined from 12 popular open-source Python repositories. Its public leaderboards, SWE-Bench Lite and SWE-Bench Verified, have become central platforms for tracking progress and comparing solutions. However, because the submission pr…

The Art of Hide and Seek: Making Pickle-Based Model Supply Chain Poisoning Stealthy Again
Tong Liu, Guozhu Meng, Peng Zhou, Zizhuang Deng, Shuaiyin Yao, Kai Chen
https://arxiv.org/abs/2508.19774

The Art of Hide and Seek: Making Pickle-Based Model Supply Chain Poisoning Stealthy Again
Pickle deserialization vulnerabilities have persisted throughout Python's history, remaining widely recognized yet unresolved. Due to its ability to transparently save and restore complex objects into byte streams, many AI/ML frameworks continue to adopt pickle as the model serialization protocol despite its inherent risks. As the open-source model ecosystem grows, model-sharing platforms such as Hugging Face have attracted massive participation, significantly amplifying the real-world risks of…

Byzantine-Robust Decentralized Coordination of LLM Agents
Yongrae Jo, Chanik Park
https://arxiv.org/abs/2507.14928 https://arxiv.org/…

Byzantine-Robust Decentralized Coordination of LLM Agents
Collaboration among multiple large language model (LLM) agents is a promising approach to overcome inherent limitations of single-agent systems, such as hallucinations and single points of failure. As LLM agents are increasingly deployed on open blockchain platforms, multi-agent systems capable of tolerating malicious (Byzantine) agents have become essential. Recent Byzantine-robust multi-agent systems typically rely on leader-driven coordination, which suffers from two major drawbacks. First…

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models
Qiming Guo, Jinwen Tang, Xingran Huang
https://arxiv.org/abs/2508.17674 https://

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models
We introduce Advertisement Embedding Attacks (AEA), a new class of LLM security threats that stealthily inject promotional or malicious content into model outputs and AI agents. AEA operate through two low-cost vectors: (1) hijacking third-party service-distribution platforms to prepend adversarial prompts, and (2) publishing back-doored open-source checkpoints fine-tuned with attacker data. Unlike conventional attacks that degrade accuracy, AEA subvert information integrity, causing models to …

Consiglieres in the Shadow: Understanding the Use of Uncensored Large Language Models in Cybercrimes
Zilong Lin, Zichuan Li, Xiaojing Liao, XiaoFeng Wang
https://arxiv.org/abs/2508.12622

Consiglieres in the Shadow: Understanding the Use of Uncensored Large Language Models in Cybercrimes
The advancement of AI technologies, particularly Large Language Models (LLMs), has transformed computing while introducing new security and privacy risks. Prior research shows that cybercriminals are increasingly leveraging uncensored LLMs (ULLMs) as backends for malicious services. Understanding these ULLMs has been hindered by the challenge of identifying them among the vast number of open-source LLMs hosted on platforms like Hugging Face. In this paper, we present the first systematic study …