Tootfinder

New Tool Reads DNA and RNA in a Single Cell, Unlocking Secrets of Disease
https://scitechdaily.com/new-tool-reads-dna-and-rna-in-a-single-cell-unlocking-secrets-of-disease/

Mehr Zeit für die Forschung: KI hilft bei der Suche nach Sternenexplosionen
Dank eines KI-Systems müssen Astronomen nicht mehr viel Zeit auf die Sichtung möglicher Funde verwenden. Das Tool imitiert die menschliche Entscheidungsfindung.

I mean sure, "AI" might make that somehow easier to pull off, but "politicians holding signs that could be manipulated" has been the source of hilarity since Photoshop v1 released.
And every generation of politicians and political campaign managers seems to have to re-learn this lesson. 😅
«Swedish Prime Minister Pulls AI Campaign Tool After It Was Used to Ask Hitler for Support»
https://www.404media.co/swedish-prime-minister-pulls-ai-campaign-tool-after-it-was-used-to-ask-hitler-for-support/

Google plans to shut down Tables, a work-tracking tool and competitor to Airtable, in December and directs users to migrate to Google Sheets or AppSheet (Sarah Perez/TechCrunch)
https://techcrunch.com/2025/09/11/google-is-shutting-down-tables-its-airtable…

Google is shutting down Tables, its Airtable rival | TechCrunch
Google Tables, a work-tracking tool and competitor to the popular spreadsheet-database hybrid Airtable, is shutting down. The app will not be supported after December 16, 2025.

Exploit Tool Invocation Prompt for Tool Behavior Hijacking in LLM-Based Agentic System
Yu Liu, Yuchong Xie, Mingyu Luo, Zesen Liu, Zhixiang Zhang, Kaikai Zhang, Zongjie Li, Ping Chen, Shuai Wang, Dongdong She
https://arxiv.org/abs/2509.05755

Exploit Tool Invocation Prompt for Tool Behavior Hijacking in LLM-Based Agentic System
LLM-based agentic systems leverage large language models to handle user queries, make decisions, and execute external tools for complex tasks across domains like chatbots, customer service, and software engineering. A critical component of these systems is the Tool Invocation Prompt (TIP), which defines tool interaction protocols and guides LLMs to ensure the security and correctness of tool usage. Despite its importance, TIP security has been largely overlooked. This work investigates TIP-rela…

MATRIX: Multimodal Agent Tuning for Robust Tool-Use Reasoning
Tajamul Ashraf, Umair Nawaz, Abdelrahman M. Shaker, Rao Anwer, Philip Torr, Fahad Shahbaz Khan, Salman Khan
https://arxiv.org/abs/2510.08567

MATRIX: Multimodal Agent Tuning for Robust Tool-Use Reasoning
Vision language models (VLMs) are increasingly deployed as controllers with access to external tools for complex reasoning and decision-making, yet their effectiveness remains limited by the scarcity of high-quality multimodal trajectories and the cost of manual annotation. We address this challenge with a vision-centric agent tuning framework that automatically synthesizes multimodal trajectories, generates step-wise preference pairs, and trains a VLM controller for robust tool-use reasoning. …

Validation of a CT-brain analysis tool for measuring global cortical atrophy in older patient cohorts
Sukhdeep Bal, Emma Colbourne, Jasmine Gan, Ludovica Griffanti, Taylor Hanayik, Nele Demeyere, Jim Davies, Sarah T Pendlebury, Mark Jenkinson
https://arxiv.org/abs/2509.08012

Validation of a CT-brain analysis tool for measuring global cortical atrophy in older patient cohorts
Quantification of brain atrophy currently requires visual rating scales which are time consuming and automated brain image analysis is warranted. We validated our automated deep learning (DL) tool measuring the Global Cerebral Atrophy (GCA) score against trained human raters, and associations with age and cognitive impairment, in representative older (>65 years) patients. CT-brain scans were obtained from patients in acute medicine (ORCHARD-EPR), acute stroke (OCS studies) and a legacy sample. …

Tool-Augmented Policy Optimization: Synergizing Reasoning and Adaptive Tool Use with Reinforcement Learning
Wenxun Wu, Yuanyang Li, Guhan Chen, Linyue Wang, Hongyang Chen
https://arxiv.org/abs/2510.07038

Tool-Augmented Policy Optimization: Synergizing Reasoning and Adaptive Tool Use with Reinforcement Learning
Recent advances in large language models (LLMs) have popularized test-time scaling, where models generate additional reasoning tokens before producing final answers. These approaches have demonstrated significant performance improvements on benchmarks involving mathematical reasoning. However, language models relying solely on direct inference still struggle with tasks demanding up-to-date knowledge or computational tools such as calculators and code interpreters for complex arithmetic operatio…

Adaptive Tool Generation with Models as Tools and Reinforcement Learning
Chenpeng Wang, Xiaojie Cheng, Chunye Wang, Linfeng Yang, Lei Zhang
https://arxiv.org/abs/2510.06825 http…

Adaptive Tool Generation with Models as Tools and Reinforcement Learning
Tool-augmented language models have demonstrated strong capabilities, but their reliance on live API access creates scalability and reliability challenges during training and deployment. We propose MTR, a simulation-first training framework for tool-augmented reasoning. Instead of relying on live APIs, MTR learns from complete ReAct traces with schema-validated, simulated observations. Our approach operates through a multi-agent architecture where a ToolMaker generates task-specific, OpenAI-com…

A UK PR agency is offering a £250/month AI tool called Olivia Brown, which creates press releases and expert quotes, and "relentlessly" emails journalists (Rob Waugh/Press Gazette)
https://pressgazette.co.uk/news/automated-pr-tool…

Automated PR tool is bombarding UK media with AI-generated content
Olivia Brown' reads websites, writes press releases then 'relentlessly' sends emails.

no-build is the best north star for a build tool

$\texttt{geko}$: A tool for modelling galaxy kinematics and morphology in JWST/NIRCam slitless spectroscopic observations
A. Lola Danhaive, Sandro Tacchella
https://arxiv.org/abs/2510.07369

$\texttt{geko}$: A tool for modelling galaxy kinematics and morphology in JWST/NIRCam slitless spectroscopic observations
Wide-field slitless spectroscopy (WFSS) is a powerful tool for studying large samples of galaxies across cosmic times. With the arrival of JWST, and its NIRCAM grism mode, slitless spectroscopy can reach a medium spectral resolution of $(R\sim 1600)$, allowing it to spatially resolve the ionised-gas kinematics out to $z\sim 9$. However, the kinematic information is convolved with morphology along the dispersion axis, a degeneracy that must be modelled to recover intrinsic properties. We present…

mist: MIST protein interaction database (2020)
The Molecular Interaction Search Tool (MIST) is a comprehensive resource of molecular interactions, assembled from severla primary sources. MIST currently supports several species, including:.
This network has 27105 nodes and 334495 edges.
Tags: Biological, Protein interactions, Unweighted

COMPASS: A Multi-Turn Benchmark for Tool-Mediated Planning & Preference Optimization
Tian Qin, Felix Bai, Ting-Yao Hu, Raviteja Vemulapalli, Hema Swetha Koppula, Zhiyang Xu, Bowen Jin, Mert Cemri, Jiarui Lu, Zirui Wang, Meng Cao
https://arxiv.org/abs/2510.07043

COMPASS: A Multi-Turn Benchmark for Tool-Mediated Planning & Preference Optimization
Real-world large language model (LLM) agents must master strategic tool use and user preference optimization through multi-turn interactions to assist users with complex planning tasks. We introduce COMPASS (Constrained Optimization through Multi-turn Planning and Strategic Solutions), a benchmark that evaluates agents on realistic travel-planning scenarios. We cast travel planning as a constrained preference optimization problem, where agents must satisfy hard constraints while simultaneously …

Vector embedding of multi-modal texts: a tool for discovery?
Beth Plale, Sai Navya Jyesta, Sachith Withana
https://arxiv.org/abs/2509.08216 https://arxiv.o…

Vector embedding of multi-modal texts: a tool for discovery?
Computer science texts are particularly rich in both narrative content and illustrative charts, algorithms, images, annotated diagrams, etc. This study explores the extent to which vector-based multimodal retrieval, powered by vision-language models (VLMs), can improve discovery across multi-modal (text and images) content. Using over 3,600 digitized textbook pages largely from computer science textbooks and a Vision Language Model (VLM), we generate multi-vector representations capturing both …

#XSLT used to be my goto tool for transforming documents. Today I was facing a document transformation problem (the daring fireball `markdown` program does not emit valid HTML, and although you can pipe it through `tidy`, tidy won't extract the first `h1` and use it as `title`), so I thought 'yay! XSLT'.
Reader, I am no longer competent to write a simple XSLT transform.
I *kno…

Running on the battle-tested #Erlang virtual machine that powers planet-scale systems such as WhatsApp and Ericsson, #Gleam is ready for workloads of any size.
https://gleam…

Wow, FileMerge not only has a new icon, but someone finally fixed the "Use Selection for Find" (Command-E) menu item that's been raising an "unrecognized selector" exception for several years.
Thank you to the team at Apple for giving this ancient NeXT-era tool some love!

Windows / DOS only.
AMI Support & Additional Sources https://www.ami.com/support-other/

The ATLAS Virtual Research Assistant: #supernovae in a sky full of noise: https://www.eurekalert.org/news-releases/1097443

TIGeR: Tool-Integrated Geometric Reasoning in Vision-Language Models for Robotics
Yi Han, Cheng Chi, Enshen Zhou, Shanyu Rong, Jingkun An, Pengwei Wang, Zhongyuan Wang, Lu Sheng, Shanghang Zhang
https://arxiv.org/abs/2510.07181

TIGeR: Tool-Integrated Geometric Reasoning in Vision-Language Models for Robotics
Vision-Language Models (VLMs) have shown remarkable capabilities in spatial reasoning, yet they remain fundamentally limited to qualitative precision and lack the computational precision required for real-world robotics. Current approaches fail to leverage metric cues from depth sensors and camera calibration, instead reducing geometric problems to pattern recognition tasks that cannot deliver the centimeter-level accuracy essential for robotic manipulation. We present TIGeR (Tool-Integrated Ge…

SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs
Hongfei Xia, Hongru Wang, Zeming Liu, Qian Yu, Yuhang Guo, Haifeng Wang
https://arxiv.org/abs/2509.07315 …

SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs
Large Language Models (LLMs) have exhibited great performance in autonomously calling various tools in external environments, leading to better problem solving and task automation capabilities. However, these external tools also amplify potential risks such as financial loss or privacy leakage with ambiguous or malicious user instructions. Compared to previous studies, which mainly assess the safety awareness of LLMs after obtaining the tool execution results (i.e., retrospective evaluation), t…

i put so much active effort over the years into communicating closer to an average person, not sounding like some stuffy pretentious academic like when i was 15, but now i sorta wanna relearn aspects of that. the aesthetic of being a smart person people should listen to, at least depending on where its applied, is a tool like any other

The invisible plastic threat you can finally see #environment

The invisible plastic threat you can finally see
Researchers in Germany and Australia have created a simple but powerful tool to detect nanoplastics—tiny, invisible particles that can slip through skin and even the blood-brain barrier. Using an "optical sieve" test strip viewed under a regular microscope, these particles reveal themselves through striking color changes.

As a survivor of the type of stochastic terrorism that people like Charlie Kirk carry out, and also a survivor of gun violence, I've had a bit to think about.
I still understand the anger, the frustration, that leads someone to snap. I'll always have compassion, if also paired with some frustration, for the person who shot me and her husband. That makes sense to me. I refused to testify because it never made sense to punish a tool who acted out of ignorance.
What doesn't make as much sense to me are the upper class grifters, the stochastic terrorists, who turn a profit of off setting people like that up to kill. I always wanted to see people like that, people who were clearly profiting off of bringing evil into the world, held accountable.
But the way I always want to see them held accountable, is by being forced to live in a world where everyone is free. Charlie Kirk got out easy, and that is a bit sad. He should have had to suffer through our victory. He should have had to watch the fall of Western Civilization, the collapse of all the things he held dear, all the things he tried to uphold. I wish that he had lived long enough to understand the suffering he inflicted on the world. He should have lived long enough to have to do real work, to have to figure out how to feed himself, house himself, in a world that has no market for the hate that he brings.
As much as I had rather that he starved, I would never shed a tear for the opening of a new public urinal.
Rest in piss. Charlie Kirk.

Billionaire Peter Thiel, founder of defence contractor Palantir, famed for exploring receiving blood transfusions from teenagers for longevity purposes, says that tax is a tool of the Antichrist.
"Thiel said that international financial bodies, which make it more difficult for people to shelter their wealth in tax havens, are one sign the antichrist may be amassing power and hastening Armageddon, saying: “"It's become quite difficult to hide one's money."”
…

Yeah, so the GNU #make jobserver protocol is trivial, which can be a blessing and a curse. It puts the job management entirely on the clients, which means that they must reliably return job tokens, or otherwise the jobserver will be left with no jobs available and everything will hang. The make documentation is clear on this:
> Your tool should be sure to write back the tokens it read, even under error conditions. This includes not only errors in your tool but also outside influences such as interrupts (SIGINT), etc. You may want to install signal handlers to manage this write-back.
#NinjaBuild jobserver implementation may not handle this correctly, but fortunately it does. The irony is, it turns out that GNU make does not…
#Gentoo

So yes, BlueSky finally has bookmarks.
Before this feature came out, people had simply been replying to posts with a 📌 emoji and there was a dedicated feed where you could view your 📌’ed posts.
In an example of how to roll stuff out, someone made an importing tool that either moved OR copied your 📌 posts to bookmarks (saved posts)
VERY well done.

Bluesky (@bsky.app)
v1.108 is rolling out today 🚚 Now live, at long last: Bookmarks, aka Saved Posts. For all those posts you'll definitely plan to come back to! Update the app and give it a try. The button is right down there 👇

Bounce: Kontenumzug von Bluesky zu Mastodon und bald auch andersherum
Ein Tool namens Bounce zieht bald Accounts von Bluesky zu Mastodon und in die Gegenrichtung um. Derweil soll Mastodon hauseigene Starter Packs bekommen.

China-linked hackers target Asian organizations with Nezha monitoring tool https://therecord.media/china-linked-hackers-target-asian-orgs-monitoring-tool

I'm so disappointed in what @… has become. It used to be a a fantastic tool for catching up with my follows in Mastodon, Threads, and Bluesky, but now the creator forces an algorithm upon us. All social media algorithms are toxic.

"The agency recently blocked users from accessing multiple websites and made password changes to an internet security tool in efforts to shore up its cyber posture"
FEMA begins security overhauls following cyber incident and employee firings

FEMA begins security overhauls following cyber incident and employee firings
The agency recently blocked users from accessing multiple websites and made password changes to an internet security tool in efforts to shore up its cyber posture, people familiar say.

My favourite tool on Linux (and macOS) recently: magic-wormhole
#cli #linux

Weekly news round-up from Saigon:
Nix-shell (for me, as a desktop user) is a powerful tool to, temporarily, enable software I wouldn't otherwise use. And that someone took the trouble to package filen-desktop as a nix package is amazing.
The Intel wifi drivers work ootb on FreeBSD 14.3, which makes it possible for me to install Ungoogled Chromium later on (as a pkg it is only available on stable releases) I got an error after compiling for 4 hrs on an i7 with 16gb, so there'…

AISysRev -- LLM-based Tool for Title-abstract Screening
Aleksi Huotala, Miikka Kuutila, Olli-Pekka Turtio, Mika M\"antyl\"a
https://arxiv.org/abs/2510.06708 https://…

AISysRev - LLM-based Tool for Title-abstract Screening
Systematic reviews are a standard practice for summarizing the state of evidence in software engineering. Conducting systematic reviews is laborious, especially during the screening or study selection phase, where the number of papers can be overwhelming. During this phase, papers are assessed against inclusion and exclusion criteria based on their titles and abstracts. Recent research has demonstrated that large language models (LLMs) can perform title-abstract screening at a level comparable …

Amazon is testing an AI tool called Kindle Translate that automatically translates books into other languages, for authors that self-publish on the platform (Lawrence Bonk/Engadget)
https://www.engadget.com/ai/amazon-is-test

Amazon is testing an AI tool that automatically translates books into other languages
Amazon is introducing an AI tool that will automatically translate books into other languages. This should be useful for authors who self publish.

Definitely not the future.
https://mastodon.social/@harrymccracken/115341019007992956

Path Integral Approach to Input-Output Theory
Aaron Daniel, Matteo Brunelli, Aashish A. Clerk, Patrick P. Potts
https://arxiv.org/abs/2509.07563 https://ar…

Path Integral Approach to Input-Output Theory
Input-output theory is a well-known tool in quantum optics and ubiquitous in the description of quantum systems probed by light. Owing to the generality of the setup it describes, the theory finds application in a wide variety of experiments in circuit and cavity QED. We present an approach to input-output theory using the Schwinger-Keldysh path integral formalism that gives us direct access to the full output field statistics such as the first and second order coherence functions. By making th…

I'm surprised that many people just seem to realize that the golden cage by #Apple is actually a golden cage! 🤷
What have you thought when you decided for that (overpriced) #lockin situation?
Of course, an #iOS

On fibred products of toposes
L\'eo Bartoli, Olivia Caramello
https://arxiv.org/abs/2509.07719 https://arxiv.org/pdf/2509.07719

On fibred products of toposes
In the setting of relative topos theory, we show that the pullback of a relative presheaf topos on an arbitrary fibration is the relative presheaf topos on its inverse image. To this end, we develop and exploit a notion of extension with base change of a morphism of sites along the canonical functor. This provides a tool to compare the canonical relative site of the direct (resp. inverse) image with the direct (resp. inverse) image of the canonical relative site: although these operations do no…

@… hey no worries! I think no build is such a good north star for any build tool!

A Honest Cross-Validation Estimator for Prediction Performance
Tianyu Pan, Vincent Z. Yu, Viswanath Devanarayan, Lu Tian
https://arxiv.org/abs/2510.07649 https://

A Honest Cross-Validation Estimator for Prediction Performance
Cross-validation is a standard tool for obtaining a honest assessment of the performance of a prediction model. The commonly used version repeatedly splits data, trains the prediction model on the training set, evaluates the model performance on the test set, and averages the model performance across different data splits. A well-known criticism is that such cross-validation procedure does not directly estimate the performance of the particular model recommended for future use. In this paper, w…

Prototyping an AI-powered Tool for Energy Efficiency in New Zealand Homes
Abdollah Baghaei Daemei
https://arxiv.org/abs/2509.05364 https://arxiv.org/pdf/25…

Prototyping an AI-powered Tool for Energy Efficiency in New Zealand Homes
Residential buildings contribute significantly to energy use, health outcomes, and carbon emissions. In New Zealand, housing quality has historically been poor, with inadequate insulation and inefficient heating contributing to widespread energy hardship. Recent reforms, including the Warmer Kiwi Homes program, Healthy Homes Standards, and H1 Building Code upgrades, have delivered health and comfort improvements, yet challenges persist. Many retrofits remain partial, data on household performan…

The Slow Space Editor : Broadening Access to Restorative XR
Nate Laffan, Ashley Hom, Andrea Nadine Castillo, Elizabeth Gitelman, Rebecca Zhao, Nikita Shenoy, Kaia Rae Schweig, Katherine Isbister
https://arxiv.org/abs/2510.07610

The Slow Space Editor : Broadening Access to Restorative XR
The Slow Space Editor is a 2D tool for creating 3D spaces. It was built as part of a research-through-design project that investigates how Virtual and Mixed Reality (XR) environments might be used for reflection and attention restoration. In this phase, we seek to radically simplify the creation of virtual environments, thereby broadening the potential group of users who could benefit from them. The research described in this paper has three aspects. First, we define the concept of "slow space,…

Neu im DNBLab: Tool zur SRU-Schnittstellenabfrage
#DNBlab

Woo hoo! You all get to start adding stuff to Cosmik Network’s Semble: a social bookmarking tool built on ATProto, so all your data is stored in your own account https://semble.so
I’ve been using it for weeks, have it as a PWA on my phone, and it’s been great to just get the basics of saving links somewhere.

Semble | A social knowledge network for researchers
Follow your peers' research trails. Surface and discover new connections. Built on ATProto so you own your data.

❗ Weitere Informationen – nicht nur zum Thema Diebstahl, sondern auch zu einer Vielzahl anderer Risiken – findet ihr im SiLK-Tool: https://www.silk-tool.de/de. Hier gibt es einführende Informationen, Fragebögen und eine Wissensdatenbank, die gemeinsam das Bewusstsein für Fragen des Schutzes und der Erha…

Free Majorana Fermion Meets Gauged Ising Conformal Field Theory on the Fuzzy Sphere
Zheng Zhou, Davide Gaiotto, Yin-Chen He
https://arxiv.org/abs/2509.08038 https://

Free Majorana Fermion Meets Gauged Ising Conformal Field Theory on the Fuzzy Sphere
The fuzzy sphere regularisation is a powerful tool to study conformal field theories (CFT) in three spacetime dimensions. In this paper, we extend its scope to CFTs with local fermionic operators. We realise the free Majorana fermion CFT on a setup with one flavour of bosons and one flavour of fermions on the lowest Landau level with a $1/2$ angular momentum mismatch. We allow conversion between two bosons and two fermions, and use a relative chemical potential as the tuning parameter. On the p…

Now up to 37.5 GB, 72K image tiles, and another 100x scan in progress.
It looks like most of the die is now at M2, but there's a bunch of oxide junk on top of it still. This kind of nonuniformity is why HF is not the best delayering tool, but I think on this node I can get away with it.
I also have more samples if I need them.

DKFNet: Differentiable Kalman Filter for Field Inversion and Machine Learning
Yuan Wu, Sicheng He
https://arxiv.org/abs/2509.07474 https://arxiv.org/pdf/25…

DKFNet: Differentiable Kalman Filter for Field Inversion and Machine Learning
The Kalman filter is a fundamental tool for state estimation in dynamical systems. While originally developed for linear Gaussian settings, it has been extended to nonlinear problems through approaches such as the extended and unscented Kalman filters. Despite its broad use, a persistent limitation is that the underlying approximate model is fixed, which can lead to significant deviations from the true system dynamics. To address this limitation, we introduce the differentiable Kalman filter (D…

Etwas mehr der heute besonders häufig geteilten #News:
Bounce: Kontenumzug von Bluesky zu Mastodon und bald auch andersherum

Amazon is testing an AI tool called Kindle Translate that automatically translates books into other languages, for authors that self-publish on the platform (Lawrence Bonk/Engadget)
https://www.engadget.com/ai/amazon-is-test

Amazon is testing an AI tool that automatically translates books into other languages
Amazon is introducing an AI tool that will automatically translate books into other languages. This should be useful for authors who self publish.

ToolMem: Enhancing Multimodal Agents with Learnable Tool Capability Memory
Yunzhong Xiao, Yangmin Li, Hewei Wang, Yunlong Tang, Zora Zhiruo Wang
https://arxiv.org/abs/2510.06664

ToolMem: Enhancing Multimodal Agents with Learnable Tool Capability Memory
Agents utilizing tools powered by large language models (LLMs) or vision-language models (VLMs) have demonstrated remarkable progress in diverse tasks across text and visual modalities. Unlike traditional tools such as calculators, which give deterministic outputs, neural tools perform uncertainly across task scenarios. While different tools for a task may excel in varied scenarios, existing agents typically rely on fixed tools, thus limiting the flexibility in selecting the most suitable tool …

Google's New AI Health Tool: Opt in or Risk Losing Benefits - Business Insider
https://www.businessinsider.com/google-ai-health-tool-opt-in-risk-losing-benefits-2025-10

In-the-Flow Agentic System Optimization for Effective Planning and Tool Use
Zhuofeng Li, Haoxiang Zhang, Seungju Han, Sheng Liu, Jianwen Xie, Yu Zhang, Yejin Choi, James Zou, Pan Lu
https://arxiv.org/abs/2510.05592

In-the-Flow Agentic System Optimization for Effective Planning and Tool Use
Outcome-driven reinforcement learning has advanced reasoning in large language models (LLMs), but prevailing tool-augmented approaches train a single, monolithic policy that interleaves thoughts and tool calls under full context; this scales poorly with long horizons and diverse tools and generalizes weakly to new scenarios. Agentic systems offer a promising alternative by decomposing work across specialized modules, yet most remain training-free or rely on offline training decoupled from the l…

Observation of CH$_{3}$$^{17}$OH and CH$_{3}$$^{18}$OH in Orion KL: A New Tool to Study Star-Formation History
Yoshimasa Watanabe, Takahiro Oyama, Akemi Tamanai, Shaoshan Zeng, Nami Sakai
https://arxiv.org/abs/2510.08041

Observation of CH$_{3}$$^{17}$OH and CH$_{3}$$^{18}$OH in Orion KL: A New Tool to Study Star-Formation History
Methanol is a seed species of complex organic molecules that is of fundamental importance in astrochemistry. Although various isotopologues of CH$_3$OH have been detected in the interstellar medium (ISM), CH$_{3}$$^{17}$OH is only tentatively detected in Sgr~B2. To confirm the presence of CH$_{3}$$^{17}$OH in the ISM and to investigate its abundance, we search for its emission lines in the Orion~KL region. We have obtained image cubes covering the frequency ranges 236.40~GHz-236.65~GHz and 231.…

And when I'm talking about understanding the drives to violence, I did write about something similar recently.
https://write.as/hexmhell/algorithmic-violence
The drives behind this and the shooting last week are pretty radically different, but there's some overlap. People like Kirk are part a huge political machine slowly crushing people all over the world. There's a hopeless rage that would naturally drive even the most calm person to the edge of violence. You can't look at the world honestly and be OK. We want to do something. We want to react. But everything we do is silenced or must rmain silent. So it's easy to understand why someone might choose violence. Very different situation, but everyone is subject to the same national and international influences.
I don't promote violence, not because I disagree with it but because I think it's expensive. It takes time to plan, especially for those trying to get away. Guns are not cheap, nor are bullets, nor is the range time you need to get somewhat good under pressure. It's not cheap for the person doing it, and it's not cheap for the community that has to clean up. The community will face police repression (which, if we're honest, was gonna come anyway). The community will have to post bail, will lose a person for a while, will need to support the family, will go to hearings, will write reports, will do interviews.
Sun Tzu said that deploying one soldier to the front takes 7 in the field. Logistics are a huge invisible cost. Some of that time and energy could be reused. It's never bad to be armed and able to defend if needed. But a lot of that energy and time would be better spent planning a community pantry, a tool library, organizing a union, etc. We are living in a disaster, and we need to invest in thriving through the next crumble.
Kirk is replacable. They're almost all replacable, because they don't really care about human life. We do, so none of us are. It's not really a worth while trade, IMHO.

AgentSentinel: An End-to-End and Real-Time Security Defense Framework for Computer-Use Agents
Haitao Hu, Peng Chen, Yanpeng Zhao, Yuqi Chen
https://arxiv.org/abs/2509.07764 http…

AgentSentinel: An End-to-End and Real-Time Security Defense Framework for Computer-Use Agents
Large Language Models (LLMs) have been increasingly integrated into computer-use agents, which can autonomously operate tools on a user's computer to accomplish complex tasks. However, due to the inherently unstable and unpredictable nature of LLM outputs, they may issue unintended tool commands or incorrect inputs, leading to potentially harmful operations. Unlike traditional security risks stemming from insecure user prompts, tool execution results from LLM-driven decisions introduce new and …

MultiCOIN: Multi-Modal COntrollable Video INbetweening
Maham Tanveer, Yang Zhou, Simon Niklaus, Ali Mahdavi Amiri, Hao Zhang, Krishna Kumar Singh, Nanxuan Zhao
https://arxiv.org/abs/2510.08561

MultiCOIN: Multi-Modal COntrollable Video INbetweening
Video inbetweening creates smooth and natural transitions between two image frames, making it an indispensable tool for video editing and long-form video synthesis. Existing works in this domain are unable to generate large, complex, or intricate motions. In particular, they cannot accommodate the versatility of user intents and generally lack fine control over the details of intermediate frames, leading to misalignment with the creative mind. To fill these gaps, we introduce \modelname{}, a vi…

Anthropic releases Petri, an open-source tool using AI agents for safety testing, and says it observed multiple cases of models attempting to blow the whistle (Anthropic)
https://www.anthropic.com/research/petri-open-source-auditing

Petri: An open-source auditing tool to accelerate AI safety research
A new automated auditing tool for AI safety research

xRouter: Training Cost-Aware LLMs Orchestration System via Reinforcement Learning
Cheng Qian, Zuxin Liu, Shirley Kokane, Akshara Prabhakar, Jielin Qiu, Haolin Chen, Zhiwei Liu, Heng Ji, Weiran Yao, Shelby Heinecke, Silvio Savarese, Caiming Xiong, Huan Wang
https://arxiv.org/abs/2510.08439

xRouter: Training Cost-Aware LLMs Orchestration System via Reinforcement Learning
Modern LLM deployments confront a widening cost-performance spectrum: premium models deliver strong reasoning but are expensive, while lightweight models are economical yet brittle on complex tasks. Static escalation rules and keyword heuristics under-utilize this spectrum and fail to adapt across task types. We present xRouter, a tool-calling-based routing system in which a learned router can either answer directly or invoke one or more external models. The router is trained end-to-end with re…

mist: MIST protein interaction database (2020)
The Molecular Interaction Search Tool (MIST) is a comprehensive resource of molecular interactions, assembled from severla primary sources. MIST currently supports several species, including:.
This network has 46404 nodes and 643319 edges.
Tags: Biological, Protein interactions, Unweighted

Temporal Counterfactual Explanations of Behaviour Tree Decisions
Tamlin Love, Antonio Andriella, Guillem Aleny\`a
https://arxiv.org/abs/2509.07674 https://…

Temporal Counterfactual Explanations of Behaviour Tree Decisions
Explainability is a critical tool in helping stakeholders understand robots. In particular, the ability for robots to explain why they have made a particular decision or behaved in a certain way is useful in this regard. Behaviour trees are a popular framework for controlling the decision-making of robots and other software systems, and thus a natural question to ask is whether or not a system driven by a behaviour tree is capable of answering "why" questions. While explainability for behaviour…

Ramsey Spectroscopy via Symmetry-Protected Destructive Many-Body Interferometry
Sijie Chen, Jiahao Huang, Min Zhuang, Chaohong Lee
https://arxiv.org/abs/2509.08288 https://

Ramsey Spectroscopy via Symmetry-Protected Destructive Many-Body Interferometry
Ramsey spectroscopy, a fundamental tool in both basic science and practical applications, is inevitably subject to several detrimental effects. % Here we propose a symmetry-protected destructive many-body interferometry (SPDMBI) for Ramsey spectroscopy, which successfully mitigates the spectral shift caused by interparticle interaction, noise, decoherence and experimental imperfection. % Through matching the symmetry of the input states and the Hamiltonian, the SPDMBI-based Ramsey spectroscopy …

Design and Implementation of a Domain-specific Language for Modelling Evacuation Scenarios Using Eclipse EMG/GMF Tool
Heerok Banerjee
https://arxiv.org/abs/2509.06688 https://…

Design and Implementation of a Domain-specific Language for Modelling Evacuation Scenarios Using Eclipse EMG/GMF Tool
Domain-specific languages (DSLs) play a crucial role in resolving internal dependencies across enterprises and boosts their upfront business management processes. Yet, a lot of development is needed to build modelling frameworks which support graphical interfaces (canvas, pallettes etc.), hierarchical structures and easy implementation to shorten the gap for novice users. In this paper, a DSL namely, Bmod is introduced, which can be used to model evacuation scenarios. The language is built usin…

ADHAM: Additive Deep Hazard Analysis Mixtures for Interpretable Survival Regression
Mert Ketenci, Vincent Jeanselme, Harry Reyes Nieva, Shalmali Joshi, No\'emie Elhadad
https://arxiv.org/abs/2509.07108

ADHAM: Additive Deep Hazard Analysis Mixtures for Interpretable Survival Regression
Survival analysis is a fundamental tool for modeling time-to-event outcomes in healthcare. Recent advances have introduced flexible neural network approaches for improved predictive performance. However, most of these models do not provide interpretable insights into the association between exposures and the modeled outcomes, a critical requirement for decision-making in clinical practice. To address this limitation, we propose Additive Deep Hazard Analysis Mixtures (ADHAM), an interpretable ad…

FASL-Seg: Anatomy and Tool Segmentation of Surgical Scenes
Muraam Abdel-Ghani, Mahmoud Ali, Mohamed Ali, Fatmaelzahraa Ahmed, Mohamed Arsalan, Abdulaziz Al-Ali, Shidin Balakrishnan
https://arxiv.org/abs/2509.06159

FASL-Seg: Anatomy and Tool Segmentation of Surgical Scenes
The growing popularity of robotic minimally invasive surgeries has made deep learning-based surgical training a key area of research. A thorough understanding of the surgical scene components is crucial, which semantic segmentation models can help achieve. However, most existing work focuses on surgical tools and overlooks anatomical objects. Additionally, current state-of-the-art (SOTA) models struggle to balance capturing high-level contextual features and low-level edge features. We propose …

Multi-Agent Tool-Integrated Policy Optimization
Zhanfeng Mo, Xingxuan Li, Yuntao Chen, Lidong Bing
https://arxiv.org/abs/2510.04678 https://arxiv.org/pdf/2…

Multi-Agent Tool-Integrated Policy Optimization
Large language models (LLMs) increasingly rely on multi-turn tool-integrated planning for knowledge-intensive and complex reasoning tasks. Existing implementations typically rely on a single agent, but they suffer from limited context length and noisy tool responses. A natural solution is to adopt a multi-agent framework with planner- and worker-agents to manage context. However, no existing methods support effective reinforcement learning post-training of tool-integrated multi-agent frameworks…

why tf does krita not have a functioning text tool

Autoformalizer with Tool Feedback
Qi Guo, Jianing Wang, Jianfei Zhang, Deyang Kong, Xiangzhou Huang, Xiangyu Xi, Wei Wang, Jingang Wang, Xunliang Cai, Shikun Zhang, Wei Ye
https://arxiv.org/abs/2510.06857

Autoformalizer with Tool Feedback
Autoformalization addresses the scarcity of data for Automated Theorem Proving (ATP) by translating mathematical problems from natural language into formal statements. Efforts in recent work shift from directly prompting large language models to training an end-to-end formalizer model from scratch, achieving remarkable advancements. However, existing formalizer still struggles to consistently generate valid statements that meet syntactic validity and semantic consistency. To address this issue,…

PolicyStory: Leveraging Large Language Models to Generate Comprehensible Summaries of Policy-News in India
Aatif Nisar Dar, Aditya Raj Singh, Anirban Sen
https://arxiv.org/abs/2509.08218

PolicyStory: Leveraging Large Language Models to Generate Comprehensible Summaries of Policy-News in India
In the era of information overload, traditional news consumption through both online and print media often fails to provide a structured and longitudinal understanding of complex sociopolitical issues. To address this gap, we present PolicyStory, an information tool designed to offer lucid, chronological, and summarized insights into Indian policy issues. PolicyStory collects news articles from diverse sources, clusters them by topic, and generates three levels of summaries from longitudinal me…

Combined-distance-based score function of cognitive fuzzy sets and its application in lung cancer pain evaluation
Lisheng Jiang, Tianyu Zhang, Shiyu Yan, Ran Fang
https://arxiv.org/abs/2509.08239

Combined-distance-based score function of cognitive fuzzy sets and its application in lung cancer pain evaluation
In decision making, the cognitive fuzzy set (CFS) is a useful tool in expressing experts' complex assessments of alternatives. The distance of CFS, which plays an important role in decision analyses, is necessary when the CFS is applied in solving practical issues. However, as far as we know, the studies on the distance of CFS are few, and the current Minkowski distance of CFS ignores the hesitancy degree of CFS, which might cause errors. To fill the gap of the studies on the distance of CFS, b…

TikTok Shop says fraudulent sellers are using AI to create fake brands and nonexistent products; TikTok rejected 70M products and banned 700K sellers in H1 2025 (Dan Whateley/Business Insider)
https://www.businessinsider.com/tiktok-shop-exec-a…

'It's organized crime': TikTok Shop says it's fighting a new wave of AI scammers
Generative AI is a powerful new tool for fraudsters trying to sell fake products, TikTok Shop's governance leader Nicolas Waldmann said.

IAB announces a tool that lets device manufacturers confirm that ad impressions are associated with real devices; Google, Apple, and Amazon have signed on (Anthony Vargas/AdExchanger)
https://www.adexchanger.com/tv/ctv-manufacturers-have-a-new-t…

CTV Manufacturers Have A New Tool For Catching Spoofed Devices
The Open Measurement SDK now provides a scaled way for original device manufacturers to confirm that ad impressions are associated with real devices.

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[5/5]:
- TIGeR: Tool-Integrated Geometric Reasoning in Vision-Language Models for Robotics
Han, Chi, Zhou, Rong, An, Wang, Wang, Sheng, Zhang

Interpretability as Alignment: Making Internal Understanding a Design Principle
Aadit Sengupta, Pratinav Seth, Vinay Kumar Sankarapu
https://arxiv.org/abs/2509.08592 https://

Interpretability as Alignment: Making Internal Understanding a Design Principle
Large neural models are increasingly deployed in high-stakes settings, raising concerns about whether their behavior reliably aligns with human values. Interpretability provides a route to internal transparency by revealing the computations that drive outputs. We argue that interpretability especially mechanistic approaches should be treated as a design principle for alignment, not an auxiliary diagnostic tool. Post-hoc methods such as LIME or SHAP offer intuitive but correlational explanations…

Beyond hospital reach: Autonomous lightweight ultrasound robot for liver sonography
Zihan Li, Yixiao Xu, Lei Zhang, Taiyu Han, Xinshan Yang, Yingni Wang, Mingxuan Liu, Shenghai Xin, Linxun Liu, Hongen Liao, Guochen Ning
https://arxiv.org/abs/2510.08106

Beyond hospital reach: Autonomous lightweight ultrasound robot for liver sonography
Liver disease is a major global health burden. While ultrasound is the first-line diagnostic tool, liver sonography requires locating multiple non-continuous planes from positions where target structures are often not visible, for biometric assessment and lesion detection, requiring significant expertise. However, expert sonographers are severely scarce in resource-limited regions. Here, we develop an autonomous lightweight ultrasound robot comprising an AI agent that integrates multi-modal per…

Identifying Neural Signatures from fMRI using Hybrid Principal Components Regression
Jared Rieck, Julia Wrobel, Joshua L. Gowin, Yue Wang, Martin Paulus, Ryan Peterson
https://arxiv.org/abs/2509.07300 …

Identifying Neural Signatures from fMRI using Hybrid Principal Components Regression
Recent advances in neuroimaging analysis have enabled accurate decoding of mental state from brain activation patterns during functional magnetic resonance imaging scans. A commonly applied tool for this purpose is principal components regression regularized with the least absolute shrinkage and selection operator (LASSO PCR), a type of multi-voxel pattern analysis (MVPA). This model presumes that all components are equally likely to harbor relevant information, when in fact the task-related si…

ProRata.ai, which lets publishers embed custom AI search on their sites with a 50/50 revenue share, raised a $40M Series B, bringing its total raised to $70M (Kerry Flynn/Axios)
https://www.axios.com/2025/09/05/prorata-ai-search-tool-publishers

Exclusive: ProRata.ai raises $40M and launches new search tool for publishers
The new product provides publishers custom AI search on their sites.

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[9/9]:
- TIGeR: Tool-Integrated Geometric Reasoning in Vision-Language Models for Robotics
Han, Chi, Zhou, Rong, An, Wang, Wang, Sheng, Zhang

ProRata.ai, which lets publishers embed custom AI search on their sites with a 50/50 revenue share, raised a $40M Series B, bringing its total raised to $75M (Kerry Flynn/Axios)
https://www.axios.com/2025/09/05/prorata-ai-search-tool-publishers

Exclusive: ProRata.ai raises $40M and launches new search tool for publishers
The new product provides publishers custom AI search on their sites.

Video-STAR: Reinforcing Open-Vocabulary Action Recognition with Tools
Zhenlong Yuan, Xiangyan Qu, Chengxuan Qian, Rui Chen, Jing Tang, Lei Sun, Xiangxiang Chu, Dapeng Zhang, Yiwei Wang, Yujun Cai, Shuo Li
https://arxiv.org/abs/2510.08480

Video-STAR: Reinforcing Open-Vocabulary Action Recognition with Tools
Multimodal large language models (MLLMs) have demonstrated remarkable potential in bridging visual and textual reasoning, yet their reliance on text-centric priors often limits their ability to disentangle semantically similar actions in open-vocabulary scenarios. To address this, we propose Video-STAR, a framework that harmonizes contextual sub-motion decomposition with tool-augmented reinforcement learning for open-vocabulary action recognition (OVAR). Unlike prior methods that treat actions …

Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[7/7]:
- Disambiguation-Centric Finetuning Makes Enterprise Tool-Calling LLMs More Realistic and Less Risky
Ashutosh Hathidara, Julien Yu, Sebastian Schreiber

ToolTweak: An Attack on Tool Selection in LLM-based Agents
Jonathan Sneh, Ruomei Yan, Jialin Yu, Philip Torr, Yarin Gal, Sunando Sengupta, Eric Sommerlade, Alasdair Paren, Adel Bibi
https://arxiv.org/abs/2510.02554

ToolTweak: An Attack on Tool Selection in LLM-based Agents
As LLMs increasingly power agents that interact with external tools, tool use has become an essential mechanism for extending their capabilities. These agents typically select tools from growing databases or marketplaces to solve user tasks, creating implicit competition among tool providers and developers for visibility and usage. In this paper, we show that this selection process harbors a critical vulnerability: by iteratively manipulating tool names and descriptions, adversaries can systema…

Agent Learning via Early Experience
Kai Zhang, Xiangchao Chen, Bo Liu, Tianci Xue, Zeyi Liao, Zhihan Liu, Xiyao Wang, Yuting Ning, Zhaorun Chen, Xiaohan Fu, Jian Xie, Yuxuan Sun, Boyu Gou, Qi Qi, Zihang Meng, Jianwei Yang, Ning Zhang, Xian Li, Ashish Shah, Dat Huynh, Hengduo Li, Zi Yang, Sara Cao, Lawrence Jang, Shuyan Zhou, Jiacheng Zhu, Huan Sun, Jason Weston, Yu Su, Yifan Wu

Agent Learning via Early Experience
A long-term goal of language agents is to learn and improve through their own experience, ultimately outperforming humans in complex, real-world tasks. However, training agents from experience data with reinforcement learning remains difficult in many environments, which either lack verifiable rewards (e.g., websites) or require inefficient long-horizon rollouts (e.g., multi-turn tool use). As a result, most current agents rely on supervised fine-tuning on expert data, which is challenging to s…

Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search
Xin Lai, Junyi Li, Wei Li, Tao Liu, Tianjian Li, Hengshuang Zhao
https://arxiv.org/abs/2509.07969 …

Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search
Recent advances in large multimodal models have leveraged image-based tools with reinforcement learning to tackle visual problems. However, existing open-source approaches often exhibit monotonous reasoning patterns and allow only a limited number of interaction turns, making them inadequate for difficult tasks that require trial-and-error exploration. In this work, we address this limitation by scaling up tool-based interactions and introduce Mini-o3, a system that executes deep, multi-turn re…

Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management
Miao Lu, Weiwei Sun, Weihua Du, Zhan Ling, Xuesong Yao, Kang Liu, Jiecao Chen
https://arxiv.org/abs/2510.06727

Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management
We study reinforcement learning (RL) fine-tuning of large language model (LLM) agents for long-horizon multi-turn tool use, where context length quickly becomes a fundamental bottleneck. Existing RL pipelines can suffer from degraded instruction following, excessive rollout costs, and most importantly, strict context limits. To address these challenges, we introduce summarization-based context management to training. In specific, it periodically compresses the tool using history by LLM-generate…

WordPress showed off Telex, its experimental AI development tool, at WordCamp US; CEO Matt Mullenweg called it "V0 or Lovable, but specifically for WordPress" (Sarah Perez/TechCrunch)
https://techcrunch.com/2025/09/02/wordpress-show…

WordPress shows off Telex, its experimental AI development tool | TechCrunch
WordPress CEO Matt Mullenweg introduced the new WordPress AI tool, called Telex, at the company's WordCamp US 2025 conference in Portland last week, alongside other AI experiments.

Prepared mind, fast response: A temporal decoupling framework for adaptive knowledge orchestration in open-domain dialogue
Jinling Gan, Churong Liang, Runnan Li
https://arxiv.org/abs/2510.08175

Prepared mind, fast response: A temporal decoupling framework for adaptive knowledge orchestration in open-domain dialogue
The latency-quality tradeoff is a fundamental constraint in open-domain dialogue AI systems, since comprehensive knowledge access necessitates prohibitive response delays. Contemporary approaches offer two inadequate solutions: lightweight instruct models achieve sub-second latency but lack reasoning depth, while tool-augmented ReAct agents enhance factuality through external knowledge at the cost of synchronous execution that blocks interaction during re- trieval processes. PMFR is thus propos…

Perplexity launches a free AI-powered patent research tool in beta to let users search for patents using natural language queries (Emma Roth/The Verge)
https://www.theverge.com/news/811340/perplexity-ai-patent-research-tool

Perplexity’s new AI tool aims to simplify patent research
Perplexity is launching an AI-powered patent research tool that allows you to search for patents using natural language.

Polars, the Amsterdam-based startup behind the popular open-source library for data manipulation of the same name, raised a €18M Series A led by Accel (Anna Heim/TechCrunch)
https://techcrunch.com/2025/09/29/the-startup-behind-open-source-t…

The startup behind open source tool Polars raises $21M from Accel | TechCrunch
Polars, the Amsterdam-based company behind the popular open source project by the same name, has raised an €18 million Series A led by Accel.

TaTToo: Tool-Grounded Thinking PRM for Test-Time Scaling in Tabular Reasoning
Jiaru Zou, Soumya Roy, Vinay Kumar Verma, Ziyi Wang, David Wipf, Pan Lu, Sumit Negi, James Zou, Jingrui He
https://arxiv.org/abs/2510.06217

TaTToo: Tool-Grounded Thinking PRM for Test-Time Scaling in Tabular Reasoning
Process Reward Models (PRMs) have recently emerged as a powerful framework for enhancing the reasoning capabilities of large reasoning models (LRMs), particularly in the context of test-time scaling (TTS). However, their potential for supervising LRMs on tabular reasoning domains remains underexplored. Through detailed empirical analyses, we identify that existing PRMs, though widely adopted for supervising text-only reasoning steps, struggle with table-specific operations such as sub-table ret…

GPT-5 Thinking in ChatGPT is shockingly good at search and demonstrates the potential of combining tool calling with chain-of-thought reasoning (Simon Willison/Simon Willison's Weblog)
https://simonwillison.net/2025/Sep/6/research-goblin/

GPT-5 Thinking in ChatGPT (aka Research Goblin) is shockingly good at search
“Don’t use chatbots as search engines” was great advice for several years... until it wasn’t. I wrote about how good OpenAI’s o3 was at using its Bing-backed search tool back …