Tootfinder

from my link log —
Swift regrets: a programming language design retrospective.
https://belkadan.com/blog/tags/swift-regrets/
saved 2025-11-26 https://

If I didn't need iOS 26 for testing, I’d have waited a few point releases. Fixing years of tech debt is good, but has to frustrate those who updated but might have wanted to wait.
“Apple to focus on ‘quality and underlying performance’ with iOS 27 next year: report”
https://

Apple to focus on 'quality and underlying performance' with iOS 27 next year: report - 9to5Mac
This past year, Apple overhauled its design language across all of its major software platforms with the introduction of Liquid...

Cursor launches Visual Editor, a vibe-coding product for designers that integrates professional design controls with natural language editing (Maxwell Zeff/Wired)
https://www.wired.com/story/cursor-launches-pro-design-tools-figma/

Cursor Launches an AI Coding Tool For Designers
The 300-person startup hopes bringing designers aboard will give it an edge in an increasingly competitive AI software market.

Deconstructing Attention: Investigating Design Principles for Effective Language Modeling
Huiyin Xue, Nafise Sadat Moosavi, Nikolaos Aletras
https://arxiv.org/abs/2510.11602 htt…

Deconstructing Attention: Investigating Design Principles for Effective Language Modeling
The success of Transformer language models is widely credited to their dot-product attention mechanism, which interweaves a set of key design principles: mixing information across positions (enabling multi-token interactions), sequence-dependent activations (where attention weights adapt to each input), a specific mathematical form (dot-product similarities plus softmax weighting), and coupling of queries and keys to evolving hidden states (grounding attention in the current layer). However, th…

EvoCAD: Evolutionary CAD Code Generation with Vision Language Models
Tobias Preintner, Weixuan Yuan, Adrian K\"onig, Thomas B\"ack, Elena Raponi, Niki van Stein
https://arxiv.org/abs/2510.11631

EvoCAD: Evolutionary CAD Code Generation with Vision Language Models
Combining large language models with evolutionary computation algorithms represents a promising research direction leveraging the remarkable generative and in-context learning capabilities of LLMs with the strengths of evolutionary algorithms. In this work, we present EvoCAD, a method for generating computer-aided design (CAD) objects through their symbolic representations using vision language models and evolutionary optimization. Our method samples multiple CAD objects, which are then optimiz…

Our new ASL Consulting page is now live:
#asl #deaf

A Design-based Solution for Causal Inference with Text: Can a Language Model Be Too Large?
Graham Tierney, Srikar Katta, Christopher Bail, Sunshine Hillygus, Alexander Volfovsky
https://arxiv.org/abs/2510.08758

A Design-based Solution for Causal Inference with Text: Can a Language Model Be Too Large?
Many social science questions ask how linguistic properties causally affect an audience's attitudes and behaviors. Because text properties are often interlinked (e.g., angry reviews use profane language), we must control for possible latent confounding to isolate causal effects. Recent literature proposes adapting large language models (LLMs) to learn latent representations of text that successfully predict both treatment and the outcome. However, because the treatment is a component of the tex…

Agentic Systems in Radiology: Design, Applications, Evaluation, and Challenges
Christian Bluethgen, Dave Van Veen, Daniel Truhn, Jakob Nikolas Kather, Michael Moor, Malgorzata Polacin, Akshay Chaudhari, Thomas Frauenfelder, Curtis P. Langlotz, Michael Krauthammer, Farhad Nooralahzadeh
https://arxiv.org/abs/2510.09404

Agentic Systems in Radiology: Design, Applications, Evaluation, and Challenges
Building agents, systems that perceive and act upon their environment with a degree of autonomy, has long been a focus of AI research. This pursuit has recently become vastly more practical with the emergence of large language models (LLMs) capable of using natural language to integrate information, follow instructions, and perform forms of "reasoning" and planning across a wide range of tasks. With its multimodal data streams and orchestrated workflows spanning multiple systems, radiology is u…

Replaced article(s) found for physics.optics. https://arxiv.org/list/physics.optics/new
[1/1]:
- LLM4Laser: Large Language Models Automate the Design of Lasers
Renjie Li, Ceyao Zhang, Sixuan Mao, Xiyuan Zhou, Feng Yin, Sergios Theodoridis, Zhaoyu Zhang
https://arxiv.org/abs/2104.12145
- Room-temperature valley-selective emission in Si-MoSe2 heterostructures enabled by high-quality-f...
Feng Pan, et al.
https://arxiv.org/abs/2409.09806 https://mastoxiv.page/@arXiv_physicsoptics_bot/113152185040115763
- 1T'-MoTe$_2$ as an integrated saturable absorber for photonic machine learning
Maria Carolina Volpato, Henrique G. Rosa, Tom Reep, Pierre-Louis de Assis, Newton Cesario Frateschi
https://arxiv.org/abs/2507.16140 https://mastoxiv.page/@arXiv_physicsoptics_bot/114901571498004090
- NeOTF: Guidestar-free neural representation for broadband dynamic imaging through scattering
Yunong Sun, Fei Xia
https://arxiv.org/abs/2507.22328 https://mastoxiv.page/@arXiv_physicsoptics_bot/114947052118796753
- Structured Random Models for Phase Retrieval with Optical Diffusers
Zhiyuan Hu, Fakhriyya Mammadova, Juli\'an Tachella, Michael Unser, Jonathan Dong
https://arxiv.org/abs/2510.14490 https://mastoxiv.page/@arXiv_physicsoptics_bot/115388901264416806
- Memory Effects in Time-Modulated Radiative Heat Transfer
Riccardo Messina, Philippe Ben-Abdallah
https://arxiv.org/abs/2510.19378 https://mastoxiv.page/@arXiv_physicsoptics_bot/115422659227231796
- Mie-tronics supermodes and symmetry breaking in nonlocal metasurfaces
Thanh Xuan Hoang, Ayan Nussupbekov, Jie Ji, Daniel Leykam, Jaime Gomez Rivas, Yuri Kivshar
https://arxiv.org/abs/2511.03560 https://mastoxiv.page/@arXiv_physicsoptics_bot/115502066008543828
- Integrated soliton microcombs beyond the turnkey limit
Wang, Xu, Wang, Zhu, Luo, Luo, Wang, Ni, Yang, Gong, Xiao, Li, Yang
https://arxiv.org/abs/2511.06909 https://mastoxiv.page/@arXiv_physicsoptics_bot/115530791701071777
- Ising accelerator with a reconfigurable interferometric photonic processor
Rausell-Campo, Al Kayed, P\'erez-L\'ppez, Aadhi, Shastri, Francoy
https://arxiv.org/abs/2511.13284 https://mastoxiv.page/@arXiv_physicsoptics_bot/115570439939074488
- Superradiance in dense atomic samples
I. M. de Ara\'ujo, H. Sanchez, L. F. Alves da Silva, M. H. Y. Moussa
https://arxiv.org/abs/2504.20242 https://mastoxiv.page/@arXiv_quantph_bot/114425762810828336
- Fluctuation-induced Hall-like lateral forces in a chiral-gain environment
Daigo Oue, M\'ario G. Silveirinha
https://arxiv.org/abs/2507.14754 https://mastoxiv.page/@arXiv_condmatmeshall_bot/114896308178114535
- Tensor-network approach to quantum optical state evolution beyond the Fock basis
Nikolay Kapridov, Egor Tiunov, Dmitry Chermoshentsev
https://arxiv.org/abs/2511.15295 https://mastoxiv.page/@arXiv_quantph_bot/115581390666689204
- OmniLens : Blind Lens Aberration Correction via Large LensLib Pre-Training and Latent PSF Repres...
Jiang, Qian, Gao, Sun, Yang, Yi, Li, Yang, Van Gool, Wang
https://arxiv.org/abs/2511.17126 https://mastoxiv.page/@arXiv_eessIV_bot/115603729319581340
toXiv_bot_toot

The Ethics Engine: A Modular Pipeline for Accessible Psychometric Assessment of Large Language Models
Jake Van Clief, Constantine Kyritsopoulos
https://arxiv.org/abs/2510.11742 …

The Ethics Engine: A Modular Pipeline for Accessible Psychometric Assessment of Large Language Models
As Large Language Models increasingly mediate human communication and decision-making, understanding their value expression becomes critical for research across disciplines. This work presents the Ethics Engine, a modular Python pipeline that transforms psychometric assessment of LLMs from a technically complex endeavor into an accessible research tool. The pipeline demonstrates how thoughtful infrastructure design can expand participation in AI research, enabling investigators across cognitive…

This is a great look at the #GraphicDesign of #ZohranMamdani’s campaign. It’s so memorable that I can’t even remember what Cuomo’s looked like.

Zohran’s Campaign Logo Looked Nothing Like a Campaign Logo
Zohran Mamdani’s campaign had a visual language like no other, drawing on hand-painted bodega signage and New York iconography in a completely fresh way.

AI for Abolition? A Participatory Design Approach
Carolyn Wang, Avriel Epps, Taylor Ferrari, Ra Ames
https://arxiv.org/abs/2510.07156 https://arxiv.org/pdf…

AI for Abolition? A Participatory Design Approach
The abolitionist community faces challenges from both the carceral state and oppressive technologies which, by empowering the ruling class who have the resources to develop artificial intelligence (AI), serve to entrench societal inequities even more deeply. This paper presents a case study in participatory design with transformative and restorative justice practitioners with the goal of designing an AI system to support their work. By co-designing an evaluation framework for large language mod…

Eliciting Secret Knowledge from Language Models
Bartosz Cywi\'nski, Emil Ryd, Rowan Wang, Senthooran Rajamanoharan, Neel Nanda, Arthur Conmy, Samuel Marks
https://arxiv.org/abs/2510.01070

Eliciting Secret Knowledge from Language Models
We study secret elicitation: discovering knowledge that an AI possesses but does not explicitly verbalize. As a testbed, we train three families of large language models (LLMs) to possess specific knowledge that they apply downstream but deny knowing when asked directly. For example, in one setting, we train an LLM to generate replies that are consistent with knowing the user is female, while denying this knowledge when asked directly. We then design various black-box and white-box secret elici…

Information Design With Large Language Models
Paul Duetting, Safwan Hossain, Tao Lin, Renato Paes Leme, Sai Srivatsa Ravindranath, Haifeng Xu, Song Zuo
https://arxiv.org/abs/2509.25565

Information Design With Large Language Models
Information design is typically studied through the lens of Bayesian signaling, where signals shape beliefs based on their correlation with the true state of the world. However, Behavioral Economics and Psychology emphasize that human decision-making is more complex and can depend on how information is framed. This paper formalizes a language-based notion of framing and bridges this to the popular Bayesian-persuasion model. We model framing as a possibly non-Bayesian, linguistic way to influenc…

Tiny but Mighty: A Software-Hardware Co-Design Approach for Efficient Multimodal Inference on Battery-Powered Small Devices
Yilong Li, Shuai Zhang, Yijing Zeng, Hao Zhang, Xinmiao Xiong, Jingyu Liu, Pan Hu, Suman Banerjee
https://arxiv.org/abs/2510.05109

Tiny but Mighty: A Software-Hardware Co-Design Approach for Efficient Multimodal Inference on Battery-Powered Small Devices
Large Multimodal Models (LMMs) are inherently modular, consisting of vision and audio encoders, projectors, and large language models. Yet, they are almost always executed monolithically, which underutilizes the heterogeneous accelerators (NPUs, GPUs, DSPs) in modern SoCs and leads to high end-to-end latency. In this paper, we present NANOMIND, a hardware--software co-design inference framework for Large Multimodal Models (LMMs) that breaks large models into modular ``bricks'' (vision, language…

A Call to Action for a Secure-by-Design Generative AI Paradigm
Dalal Alharthi, Ivan Roberto Kawaminami Garcia
https://arxiv.org/abs/2510.00451 https://arxi…

A Call to Action for a Secure-by-Design Generative AI Paradigm
Large language models have gained widespread prominence, yet their vulnerability to prompt injection and other adversarial attacks remains a critical concern. This paper argues for a security-by-design AI paradigm that proactively mitigates LLM vulnerabilities while enhancing performance. To achieve this, we introduce PromptShield, an ontology-driven framework that ensures deterministic and secure prompt interactions. It standardizes user inputs through semantic validation, eliminating ambiguit…

COSTAR-A: A prompting framework for enhancing Large Language Model performance on Point-of-View questions
Nzubechukwu C. Ohalete (School of Data Science and Analytics, Kennesaw State University, GA, USA), Kevin B. Gittner (School of Data Science and Analytics, Kennesaw State University, GA, USA), Lauren M. Matheny (School of Data Science and Analytics, Kennesaw State University, GA, USA)

COSTAR-A: A prompting framework for enhancing Large Language Model performance on Point-of-View questions
Large Language Models (LLMs) are highly sensitive to prompt design, and making optimized prompting techniques is crucial for generating consistent, high-quality outputs. In this study, we introduce COSTAR-A, a novel prompt engineering framework that enhances the existing COSTAR method, which stands for Context, Objective, Style, Tone, Audience, and Response, by adding the 'Answer' component at the end. We demonstrate that while the original COSTAR framework improves prompt clarity and aligns ou…

Introducing Large Language Models in the Design Flow of Time Sensitive Networking
Rubi Debnath, Luxi Zhao, Mohammadreza Barzegaran, Sebastian Steinhorst
https://arxiv.org/abs/2509.26368

Introducing Large Language Models in the Design Flow of Time Sensitive Networking
The growing demand for real-time, safety-critical systems has significantly increased both the adoption and complexity of Time Sensitive Networking (TSN). Configuring an optimized TSN network is highly challenging, requiring careful planning, design, verification, validation, and deployment. Large Language Models (LLMs) have recently demonstrated strong capabilities in solving complex tasks, positioning them as promising candidates for automating end-to-end TSN deployment, referred to as TSN or…

Stratum: System-Hardware Co-Design with Tiered Monolithic 3D-Stackable DRAM for Efficient MoE Serving
Yue Pan, Zihan Xia, Po-Kai Hsu, Lanxiang Hu, Hyungyo Kim, Janak Sharda, Minxuan Zhou, Nam Sung Kim, Shimeng Yu, Tajana Rosing, Mingu Kang
https://arxiv.org/abs/2510.05245

Stratum: System-Hardware Co-Design with Tiered Monolithic 3D-Stackable DRAM for Efficient MoE Serving
As Large Language Models (LLMs) continue to evolve, Mixture of Experts (MoE) architecture has emerged as a prevailing design for achieving state-of-the-art performance across a wide range of tasks. MoE models use sparse gating to activate only a handful of expert sub-networks per input, achieving billion-parameter capacity with inference costs akin to much smaller models. However, such models often pose challenges for hardware deployment due to the massive data volume introduced by the MoE laye…

Lord help me I'm starting to enjoy coding in C .
I find myself saying "if you're writing *that* kind of C you've done something wrong at the design stage"
I caught myself feeling grateful that the language punishes you with unreadability and untestability when you do too much in one function
Is this... Stockholm Syndrome?

Functional Reasoning for Distributed Systems with Failures
Haobin Ni, Robbert van Renesse, Greg Morrisett
https://arxiv.org/abs/2510.12131 https://arxiv.or…

Functional Reasoning for Distributed Systems with Failures
Distributed system theory literature often argues for correctness using an informal, Hoare-like style of reasoning. While these arguments are intuitive, they have not all been foolproof, and whether they directly correspond to formal proofs is in question. We formally ground this kind of reasoning and connect it to standard formal approaches through language design and meta-analysis, which leads to a functional style of compositional formal reasoning for a class of distributed systems, includin…

The EmpathiSEr: Development and Validation of Software Engineering Oriented Empathy Scales
Hashini Gunatilake, John Grundy, Rashina Hoda, Ingo Mueller
https://arxiv.org/abs/2510.12546

The EmpathiSEr: Development and Validation of Software Engineering Oriented Empathy Scales
Empathy plays a critical role in software engineering (SE), influencing collaboration, communication, and user-centred design. Although SE research has increasingly recognised empathy as a key human aspect, there remains no validated instrument specifically designed to measure it within the unique socio-technical contexts of SE. Existing generic empathy scales, while well-established in psychology and healthcare, often rely on language, scenarios, and assumptions that are not meaningful or inte…

Glaucoma Detection and Structured OCT Report Generation via a Fine-tuned Multimodal Large Language Model
Jalil Jalili, Yashraj Gavhane, Evan Walker, Anna Heinke, Christopher Bowd, Akram Belghith, Massimo A. Fazio, Christopher A. Girkin, C. Gustavo De Moraes, Jeffrey M. Liebmann, Sally L. Baxter, Robert N. Weinreb, Linda M. Zangwill, Mark Christopher
https://

Glaucoma Detection and Structured OCT Report Generation via a Fine-tuned Multimodal Large Language Model
Objective: To develop an explainable multimodal large language model (MM-LLM) that (1) screens optic nerve head (ONH) OCT circle scans for quality and (2) generates structured clinical reports that include glaucoma diagnosis and sector-wise retinal nerve fiber layer (RNFL) thinning assessments. Design: Retrospective cohort study of 1,310 subjects contributing 43,849 Spectralis ONH OCT circle scans (1,331 glaucomatous and 867 healthy eyes) from the DIGS and ADAGES cohorts. Methods: A MM-LLM (Lla…

NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints
Changyao Tian, Hao Li, Gen Luo, Xizhou Zhu, Weijie Su, Hanming Deng, Jinguo Zhu, Jie Shao, Ziran Zhu, Yunpeng Liu, Lewei Lu, Wenhai Wang, Hongsheng Li, Jifeng Dai
https://arxiv.org/abs/2510.08565 …

NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints
Compositional training has been the de-facto paradigm in existing Multimodal Large Language Models (MLLMs), where pre-trained vision encoders are connected with pre-trained LLMs through continuous multimodal pre-training. However, the multimodal scaling property of this paradigm remains difficult to explore due to the separated training. In this paper, we focus on the native training of MLLMs in an end-to-end manner and systematically study its design space and scaling property under a practica…

Rule Encoding and Compliance in Large Language Models: An Information-Theoretic Analysis
Joachim Diederich
https://arxiv.org/abs/2510.05106 https://arxiv.o…

Rule Encoding and Compliance in Large Language Models: An Information-Theoretic Analysis
The design of safety-critical agents based on large language models (LLMs) requires more than simple prompt engineering. This paper presents a comprehensive information-theoretic analysis of how rule encodings in system prompts influence attention mechanisms and compliance behaviour. We demonstrate that rule formats with low syntactic entropy and highly concentrated anchors reduce attention entropy and improve pointer fidelity, but reveal a fundamental trade-off between anchor redundancy and at…

Leveraging LLMs to Improve Experimental Design: A Generative Stratification Approach
George Gui, Seungwoo Kim
https://arxiv.org/abs/2509.25709 https://arxi…

Leveraging LLMs to Improve Experimental Design: A Generative Stratification Approach
Pre-experiment stratification, or blocking, is a well-established technique for designing more efficient experiments and increasing the precision of the experimental estimates. However, when researchers have access to many covariates at the experiment design stage, they often face challenges in effectively selecting or weighting covariates when creating their strata. This paper proposes a Generative Stratification procedure that leverages Large Language Models (LLMs) to synthesize high-dimensio…

Hybrid Architectures for Language Models: Systematic Analysis and Design Insights
Sangmin Bae, Bilge Acun, Haroun Habeeb, Seungyeon Kim, Chien-Yu Lin, Liang Luo, Junjie Wang, Carole-Jean Wu
https://arxiv.org/abs/2510.04800

Hybrid Architectures for Language Models: Systematic Analysis and Design Insights
Recent progress in large language models demonstrates that hybrid architectures--combining self-attention mechanisms with structured state space models like Mamba--can achieve a compelling balance between modeling quality and computational efficiency, particularly for long-context tasks. While these hybrid models show promising performance, systematic comparisons of hybridization strategies and analyses on the key factors behind their effectiveness have not been clearly shared to the community.…

MLLM as a UI Judge: Benchmarking Multimodal LLMs for Predicting Human Perception of User Interfaces
Reuben A. Luera, Ryan Rossi, Franck Dernoncourt, Samyadeep Basu, Sungchul Kim, Subhojyoti Mukherjee, Puneet Mathur, Ruiyi Zhang, Jihyung Kil, Nedim Lipka, Seunghyun Yoon, Jiuxiang Gu, Zichao Wang, Cindy Xiong Bearfield, Branislav Kveton
https://

MLLM as a UI Judge: Benchmarking Multimodal LLMs for Predicting Human Perception of User Interfaces
In an ideal design pipeline, user interface (UI) design is intertwined with user research to validate decisions, yet studies are often resource-constrained during early exploration. Recent advances in multimodal large language models (MLLMs) offer a promising opportunity to act as early evaluators, helping designers narrow options before formal testing. Unlike prior work that emphasizes user behavior in narrow domains such as e-commerce with metrics like clicks or conversions, we focus on subje…

LLMs as Policy-Agnostic Teammates: A Case Study in Human Proxy Design for Heterogeneous Agent Teams
Aju Ani Justus, Chris Baber
https://arxiv.org/abs/2510.06151 https://

LLMs as Policy-Agnostic Teammates: A Case Study in Human Proxy Design for Heterogeneous Agent Teams
A critical challenge in modelling Heterogeneous-Agent Teams is training agents to collaborate with teammates whose policies are inaccessible or non-stationary, such as humans. Traditional approaches rely on expensive human-in-the-loop data, which limits scalability. We propose using Large Language Models (LLMs) as policy-agnostic human proxies to generate synthetic data that mimics human decision-making. To evaluate this, we conduct three experiments in a grid-world capture game inspired by Sta…

from my link log —
Tony Hoare’s hints on programming language design.
http://i.stanford.edu/pub/cstr/reports/cs/tr/73/403/CS-TR-73-403.pdf
saved 2025-09-26

Lang-PINN: From Language to Physics-Informed Neural Networks via a Multi-Agent Framework
Xin He, Liangliang You, Hongduan Tian, Bo Han, Ivor Tsang, Yew-Soon Ong
https://arxiv.org/abs/2510.05158

Lang-PINN: From Language to Physics-Informed Neural Networks via a Multi-Agent Framework
Physics-informed neural networks (PINNs) provide a powerful approach for solving partial differential equations (PDEs), but constructing a usable PINN remains labor-intensive and error-prone. Scientists must interpret problems as PDE formulations, design architectures and loss functions, and implement stable training pipelines. Existing large language model (LLM) based approaches address isolated steps such as code generation or architecture suggestion, but typically assume a formal PDE is alre…

HyperAgent: Leveraging Hypergraphs for Topology Optimization in Multi-Agent Communication
Heng Zhang, Yuling Shi, Xiaodong Gu, Zijian Zhang, Haochen You, Lubin Gan, Yilei Yuan, Jin Huang
https://arxiv.org/abs/2510.10611

HyperAgent: Leveraging Hypergraphs for Topology Optimization in Multi-Agent Communication
Recent advances in large language model-powered multi-agent systems have demonstrated remarkable collective intelligence through effective communication. However, existing approaches face two primary challenges: (i) \textit{Ineffective group collaboration modeling}, as they rely on pairwise edge representations in graph structures, limiting their ability to capture relationships among multiple agents; and (ii) \textit{Limited task-adaptiveness in communication topology design}, leading to exces…

Automated Discovery of Test Oracles for Database Management Systems Using LLMs
Qiuyang Mang, Runyuan He, Suyang Zhong, Xiaoxuan Liu, Huanchen Zhang, Alvin Cheung
https://arxiv.org/abs/2510.06663

Automated Discovery of Test Oracles for Database Management Systems Using LLMs
Since 2020, automated testing for Database Management Systems (DBMSs) has flourished, uncovering hundreds of bugs in widely-used systems. A cornerstone of these techniques is test oracle, which typically implements a mechanism to generate equivalent query pairs, thereby identifying bugs by checking the consistency between their results. However, while applying these oracles can be automated, their design remains a fundamentally manual endeavor. This paper explores the use of large language mode…

LLM-Driven Rubric-Based Assessment of Algebraic Competence in Multi-Stage Block Coding Tasks with Design and Field Evaluation
Yong Oh Lee, Byeonghun Bang, Sejun Oh
https://arxiv.org/abs/2510.06253

LLM-Driven Rubric-Based Assessment of Algebraic Competence in Multi-Stage Block Coding Tasks with Design and Field Evaluation
As online education platforms continue to expand, there is a growing need for assessment methods that not only measure answer accuracy but also capture the depth of students' cognitive processes in alignment with curriculum objectives. This study proposes and evaluates a rubric-based assessment framework powered by a large language model (LLM) for measuring algebraic competence, real-world-context block coding tasks. The problem set, designed by mathematics education experts, aligns each proble…

SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents
Zonghao Ying, Yangguang Shao, Jianle Gan, Gan Xu, Junjie Shen, Wenxin Zhang, Quanchen Zou, Junzheng Shi, Zhenfei Yin, Mingchuan Zhang, Aishan Liu, Xianglong Liu
https://arxiv.org/abs/2510.10073

SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents
Large vision-language model (LVLM)-based web agents are emerging as powerful tools for automating complex online tasks. However, when deployed in real-world environments, they face serious security risks, motivating the design of security evaluation benchmarks. Existing benchmarks provide only partial coverage, typically restricted to narrow scenarios such as user-level prompt manipulation, and thus fail to capture the broad range of agent vulnerabilities. To address this gap, we present \tool{…

Generalized Multi-agent Social Simulation Framework
Gang Li, Jie Lin, Yining Tang, Ziteng Wang, Yirui Huang, Junyu Zhang, Shuang Luo, Chao Wu, Yike Guo
https://arxiv.org/abs/2510.06225

Generalized Multi-agent Social Simulation Framework
Multi-agent social interaction has clearly benefited from Large Language Models. However, current simulation systems still face challenges such as difficulties in scaling to diverse scenarios and poor reusability due to a lack of modular design. To address these issues, we designed and developed a modular, object-oriented framework that organically integrates various base classes through a hierarchical structure, harvesting scalability and reusability. We inherited the framework to realize comm…

It’s strange to watch the world ignore that it’s not just the medium that matters, but the message does too.
And by “the message” I mean both the ideas and the precise language or visuals used to communicate them.
Subtle differences in linguistic execution of the same idea in the same format can have radically opposite effects. The same applies to an image captured from a different angle or in a different style or in a different composition.
And yet it feels like most organizations and most people within them are determined to march on ignoring any consideration of subtlety and craft.
#writing #design #art #marketing

What Slows Down FMware Development? An Empirical Study of Developer Challenges and Resolution Times
Zitao Wang, Zhimin Zhao, Michael W. Godfrey
https://arxiv.org/abs/2510.11138 …

What Slows Down FMware Development? An Empirical Study of Developer Challenges and Resolution Times
Foundation Models (FMs), such as OpenAI's GPT, are fundamentally transforming the practice of software engineering by enabling the development of \emph{FMware} -- applications and infrastructures built around these models. FMware systems now support tasks such as code generation, natural-language interaction, knowledge integration, and multi-modal content creation, underscoring their disruptive impact on current software engineering workflows. However, the design, implementation, and evolution …

UniVideo: Unified Understanding, Generation, and Editing for Videos
Cong Wei, Quande Liu, Zixuan Ye, Qiulin Wang, Xintao Wang, Pengfei Wan, Kun Gai, Wenhu Chen
https://arxiv.org/abs/2510.08377

UniVideo: Unified Understanding, Generation, and Editing for Videos
Unified multimodal models have shown promising results in multimodal content generation and editing but remain largely limited to the image domain. In this work, we present UniVideo, a versatile framework that extends unified modeling to the video domain. UniVideo adopts a dual-stream design, combining a Multimodal Large Language Model (MLLM) for instruction understanding with a Multimodal DiT (MMDiT) for video generation. This design enables accurate interpretation of complex multimodal instru…

HNote: Extending YNote with Hexadecimal Encoding for Fine-Tuning LLMs in Music Modeling
Hung-Ying Chu, Shao-Yu Wei, Guan-Wei Chen, Tzu-Wei Hung, ChengYang Tsai, Yu-Cheng Lin
https://arxiv.org/abs/2509.25694

HNote: Extending YNote with Hexadecimal Encoding for Fine-Tuning LLMs in Music Modeling
Recent advances in large language models (LLMs) have created new opportunities for symbolic music generation. However, existing formats such as MIDI, ABC, and MusicXML are either overly complex or structurally inconsistent, limiting their suitability for token-based learning architectures. To address these challenges, we propose HNote, a novel hexadecimal-based notation system extended from YNote, which encodes both pitch and duration within a fixed 32-unit measure framework. This design ensure…

AutoMaAS: Self-Evolving Multi-Agent Architecture Search for Large Language Models
Bo Ma, Hang Li, ZeHua Hu, XiaoFan Gui, LuYao Liu, Simon Liu
https://arxiv.org/abs/2510.02669 ht…

AutoMaAS: Self-Evolving Multi-Agent Architecture Search for Large Language Models
Multi-agent systems powered by large language models have demonstrated remarkable capabilities across diverse domains, yet existing automated design approaches seek monolithic solutions that fail to adapt resource allocation based on query complexity and domain requirements. This paper introduces AutoMaAS, a self-evolving multi-agent architecture search framework that leverages neural architecture search principles to automatically discover optimal agent configurations through dynamic operator …

IA aplicada al an\'alisis del conflicto Ir\'an-Israel: Mapeo de discursos en YouTube
Alvaro Vallejo Ram\'irez
https://arxiv.org/abs/2510.00021 https://

IA aplicada al análisis del conflicto Irán-Israel: Mapeo de discursos en YouTube
Purpose. This study analyzes the digital representation of the Iran-Israel conflict that occurred in June 2025, based on 120,000 comments posted on YouTube. It sought to identify discursive positions regarding the actors involved and to examine how media and algorithmic biases shape digital conversations. Methodology. A mixed-methods design with triangulation was adopted. In the quantitative phase, natural language processing techniques and machine learning models (BERT and XLM-RoBERTa) were us…

Developing a Cost-Effective Spectrometer: A Practical Approach
Mohammad Tahsin Alam, Zafrin Jahan Nikita, Yasir Mahmud, Rafichha Yeasmin, Fairuz Darimi Bushra, Sheikh Hasib Cheragee, Redwanul Talukder Zeem
https://arxiv.org/abs/2510.06703

Developing a Cost-Effective Spectrometer: A Practical Approach
The paper demonstrates the design and execution of a low-cost optical spectrometer that employs a webcam, diffraction grating & Python (a free, open-source programming language). The device's design prioritized economy and usability, with a black box casing to reduce stray light and increase measurement accuracy. A diffraction grating made from a DVD was used to split light into its constituent wavelengths, which were then collected by the camera. The calibration procedure used a RED TIDE USB65…

A Trace-based Approach for Code Safety Analysis
Hui Xu
https://arxiv.org/abs/2510.10410 https://arxiv.org/pdf/2510.10410

A Trace-based Approach for Code Safety Analysis
Rust is a memory-safe programming language that disallows undefined behavior. Its safety guarantees have been extensively examined by the community through empirical studies, which has led to its remarkable success. However, unsafe code remains a critical concern in Rust. By reviewing the safety design of Rust and analyzing real-world Rust projects, this paper establishes a systematic framework for understanding unsafe code and undefined behavior, and summarizes the soundness criteria for Rust …

Exploring Database Normalization Effects on SQL Generation
Ryosuke Kohita
https://arxiv.org/abs/2510.01989 https://arxiv.org/pdf/2510.01989

Exploring Database Normalization Effects on SQL Generation
Schema design, particularly normalization, is a critical yet often overlooked factor in natural language to SQL (NL2SQL) systems. Most prior research evaluates models on fixed schemas, overlooking the influence of design on performance. We present the first systematic study of schema normalization's impact, evaluating eight leading large language models on synthetic and real-world datasets with varied normalization levels. We construct controlled synthetic datasets with formal normalization (1N…

A Practitioner's Guide to Multi-turn Agentic Reinforcement Learning
Ruiyi Wang, Prithviraj Ammanabrolu
https://arxiv.org/abs/2510.01132 https://arxiv.o…

A Practitioner's Guide to Multi-turn Agentic Reinforcement Learning
We study what actually works and what doesn't for training large language models as agents via multi-turn reinforcement learning. Despite rapid progress, existing frameworks and definitions are fragmented, and there is no systematic formulation or analysis of which design choices matter across tasks. We address this gap by first breaking down the design space into three inter-related pillars -- environment, reward, and policy -- and empirically derive a recipe for training LLM agents in situate…

TriQuest:An AI Copilot-Powered Platform for Interdisciplinary Curriculum Design
Huazhen Wang, Huimin Yang, Hainbin Lin, Yan Dong, Lili Chen, Liangliang Xia, Wenwen Xu
https://arxiv.org/abs/2510.03369

TriQuest:An AI Copilot-Powered Platform for Interdisciplinary Curriculum Design
Interdisciplinary teaching is a cornerstone of modern curriculum reform, but its implementation is hindered by challenges in knowledge integration and time-consuming lesson planning. Existing tools often lack the required pedagogical and domain-specific depth.We introduce TriQuest, an AI-copilot platform designed to solve these problems. TriQuest uses large language models and knowledge graphs via an intuitive GUI to help teachers efficiently generate high-quality interdisciplinary lesson plans…

Devstral: Fine-tuning Language Models for Coding Agent Applications
Abhinav Rastogi, Adam Yang, Albert Q. Jiang, Alexander H. Liu, Alexandre Sablayrolles, Am\'elie H\'eliou, Am\'elie Martin, Anmol Agarwal, Andy Ehrenberg, Andy Lo, Antoine Roux, Arthur Darcet, Arthur Mensch, Baptiste Bout, Baptiste Rozi\`ere, Baudouin De Monicault, Chris Bamford, Christian Wallenwein, Christophe Renaudin, Cl\'emence Lanfranchi, Cl\'ement Denoix, Corentin Barreau, Darius Dabert Devon …

Devstral: Fine-tuning Language Models for Coding Agent Applications
We introduce Devstral-Small, a lightweight open source model for code agents with the best performance among models below 100B size. In this technical report, we give an overview of how we design and develop a model and craft specializations in agentic software development. The resulting model, Devstral-Small is a small 24B model, fast and easy to serve. Despite its size, Devstral-Small still attains competitive performance compared to models more than an order of magnitude larger.

Beyond Words: Infusing Conversational Agents with Human-like Typing Behaviors
Jijie Zhou, Yuhan Hu
https://arxiv.org/abs/2510.08912 https://arxiv.org/pdf/2…

Beyond Words: Infusing Conversational Agents with Human-like Typing Behaviors
Recently, large language models have facilitated the emergence of highly intelligent conversational AI capable of engaging in human-like dialogues. However, a notable distinction lies in the fact that these AI models predominantly generate responses rapidly, often producing extensive content without emulating the thoughtful process characteristic of human cognition and typing. This paper presents a design aimed at simulating human-like typing behaviors, including patterns such as hesitation and…

DeepV: A Model-Agnostic Retrieval-Augmented Framework for Verilog Code Generation with a High-Quality Knowledge Base
Zahin Ibnat, Paul E. Calzada, Rasin Mohammed Ihtemam, Sujan Kumar Saha, Jingbo Zhou, Farimah Farahmandi, Mark Tehranipoor
https://arxiv.org/abs/2510.05327

DeepV: A Model-Agnostic Retrieval-Augmented Framework for Verilog Code Generation with a High-Quality Knowledge Base
As large language models (LLMs) continue to be integrated into modern technology, there has been an increased push towards code generation applications, which also naturally extends to hardware design automation. LLM-based solutions for register transfer level (RTL) code generation for intellectual property (IP) designs have grown, especially with fine-tuned LLMs, prompt engineering, and agentic approaches becoming popular in literature. However, a gap has been exposed in these techniques, as t…

CoLLM-NAS: Collaborative Large Language Models for Efficient Knowledge-Guided Neural Architecture Search
Zhe Li, Zhiwei Lin, Yongtao Wang
https://arxiv.org/abs/2509.26037 https:…

CoLLM-NAS: Collaborative Large Language Models for Efficient Knowledge-Guided Neural Architecture Search
The integration of Large Language Models (LLMs) with Neural Architecture Search (NAS) has introduced new possibilities for automating the design of neural architectures. However, most existing methods face critical limitations, including architectural invalidity, computational inefficiency, and inferior performance compared to traditional NAS. In this work, we present Collaborative LLM-based NAS (CoLLM-NAS), a two-stage NAS framework with knowledge-guided search driven by two complementary LLMs…

Learning to Rewrite Prompts for Bootstrapping LLMs on Downstream Tasks
Qinhao Zhou, Xiang Xiang, Kun He, John E. Hopcroft
https://arxiv.org/abs/2510.06695 https://

Learning to Rewrite Prompts for Bootstrapping LLMs on Downstream Tasks
In recent years, the growing interest in Large Language Models (LLMs) has significantly advanced prompt engineering, transitioning from manual design to model-based optimization. Prompts for LLMs generally comprise two components: the \textit{instruction}, which defines the task or objective, and the \textit{input}, which is tailored to the instruction type. In natural language generation (NLG) tasks such as machine translation, the \textit{input} component is particularly critical, while the \…

From Delegates to Trustees: How Optimizing for Long-Term Interests Shapes Bias and Alignment in LLM
Suyash Fulay, Jocelyn Zhu, Michiel Bakker
https://arxiv.org/abs/2510.12689 ht…

From Delegates to Trustees: How Optimizing for Long-Term Interests Shapes Bias and Alignment in LLM
Large language models (LLMs) have shown promising accuracy in predicting survey responses and policy preferences, which has increased interest in their potential to represent human interests in various domains. Most existing research has focused on behavioral cloning, effectively evaluating how well models reproduce individuals' expressed preferences. Drawing on theories of political representation, we highlight an underexplored design trade-off: whether AI systems should act as delegates, mirr…

InstructX: Towards Unified Visual Editing with MLLM Guidance
Chong Mou, Qichao Sun, Yanze Wu, Pengze Zhang, Xinghui Li, Fulong Ye, Songtao Zhao, Qian He
https://arxiv.org/abs/2510.08485

InstructX: Towards Unified Visual Editing with MLLM Guidance
With recent advances in Multimodal Large Language Models (MLLMs) showing strong visual understanding and reasoning, interest is growing in using them to improve the editing performance of diffusion models. Despite rapid progress, most studies lack an in-depth analysis of MLLM design choices. Moreover, the integration of MLLMs and diffusion models remains an open challenge in some difficult tasks, such as video editing. In this paper, we present InstructX, a unified framework for image and video…

Co-Authoring the Self: A Human-AI Interface for Interest Reflection in Recommenders
Ruixuan Sun, Junyuan Wang, Sanjali Roy, Joseph A. Konstan
https://arxiv.org/abs/2510.08930 ht…

Co-Authoring the Self: A Human-AI Interface for Interest Reflection in Recommenders
Natural language-based user profiles in recommender systems have been explored for their interpretability and potential to help users scrutinize and refine their interests, thereby improving recommendation quality. Building on this foundation, we introduce a human-AI collaborative profile for a movie recommender system that presents editable personalized interest summaries of a user's movie history. Unlike static profiles, this design invites users to directly inspect, modify, and reflect on th…

Taming Imperfect Process Verifiers: A Sampling Perspective on Backtracking
Dhruv Rohatgi, Abhishek Shetty, Donya Saless, Yuchen Li, Ankur Moitra, Andrej Risteski, Dylan J. Foster
https://arxiv.org/abs/2510.03149

Taming Imperfect Process Verifiers: A Sampling Perspective on Backtracking
Test-time algorithms that combine the generative power of language models with process verifiers that assess the quality of partial generations offer a promising lever for eliciting new reasoning capabilities, but the algorithmic design space and computational scaling properties of such approaches are still opaque, and their benefits are far from apparent when one accounts for the cost of learning a high-quality verifier. Our starting point is the observation that seemingly benign errors in a l…

Automatic Building Code Review: A Case Study
Hanlong Wan, Weili Xu, Michael Rosenberg, Jian Zhang, Aysha Siddika
https://arxiv.org/abs/2510.02634 https://a…

Automatic Building Code Review: A Case Study
Building officials, particularly those in resource-constrained or rural jurisdictions, face labor-intensive, error-prone, and costly manual reviews of design documents as projects increase in size and complexity. The growing adoption of Building Information Modeling (BIM) and Large Language Models (LLMs) presents opportunities for automated code review (ACR) solutions. This study introduces a novel agent-driven framework that integrates BIM-based data extraction with automated verification usin…

MENLO: From Preferences to Proficiency - Evaluating and Modeling Native-like Quality Across 47 Languages
Chenxi Whitehouse, Sebastian Ruder, Tony Lin, Oksana Kurylo, Haruka Takagi, Janice Lam, Nicol\`o Busetto, Denise Diaz
https://arxiv.org/abs/2509.26601

MENLO: From Preferences to Proficiency - Evaluating and Modeling Native-like Quality Across 47 Languages
Ensuring native-like quality of large language model (LLM) responses across many languages is challenging. To address this, we introduce MENLO, a framework that operationalizes the evaluation of native-like response quality based on audience design-inspired mechanisms. Using MENLO, we create a dataset of 6,423 human-annotated prompt-response preference pairs covering four quality dimensions with high inter-annotator agreement in 47 language varieties. Our evaluation reveals that zero-shot LLM j…

Designing Walrus: Relational Programming with Rich Types, On-Demand Laziness, and Structured Traces
Santiago Cu\'ellar, Naomi Spargo, Jonathan Daugherty, David Darais
https://arxiv.org/abs/2510.02579

Designing Walrus: Relational Programming with Rich Types, On-Demand Laziness, and Structured Traces
We present Walrus, a functional relational programming language embedded in Haskell that extends the miniKanren model with type-polymorphic unification, on-demand laziness, and a range of usability features aimed at practical development. These include use of Haskell Generics for boilerplate reduction, structured debugging traces, and ergonomic support for product types. We describe the design and implementation of Walrus through the lens of our experience developing bidirectional compilers, an…

ARM: Discovering Agentic Reasoning Modules for Generalizable Multi-Agent Systems
Bohan Yao, Shiva Krishna Reddy Malay, Vikas Yadav
https://arxiv.org/abs/2510.05746 https://

ARM: Discovering Agentic Reasoning Modules for Generalizable Multi-Agent Systems
Large Language Model (LLM)-powered Multi-agent systems (MAS) have achieved state-of-the-art results on various complex reasoning tasks. Recent works have proposed techniques to automate the design of MASes, eliminating the need for manual engineering. However, these techniques perform poorly, often achieving similar or inferior performance to simple baselines. Furthermore, they require computationally expensive re-discovery of architectures for each new task domain and expensive data annotation…

Adaptive LLM-Symbolic Reasoning via Dynamic Logical Solver Composition
Lei Xu, Pierre Beckmann, Marco Valentino, Andr\'e Freitas
https://arxiv.org/abs/2510.06774 https://

Adaptive LLM-Symbolic Reasoning via Dynamic Logical Solver Composition
Neuro-symbolic NLP methods aim to leverage the complementary strengths of large language models and formal logical solvers. However, current approaches are mostly static in nature, i.e., the integration of a target solver is predetermined at design time, hindering the ability to employ diverse formal inference strategies. To address this, we introduce an adaptive, multi-paradigm, neuro-symbolic inference framework that: (1) automatically identifies formal reasoning strategies from problems expr…

PromptPilot: Improving Human-AI Collaboration Through LLM-Enhanced Prompt Engineering
Niklas Gutheil, Valentin Mayer, Leopold M\"uller, J\"org Rommelt, Niklas K\"uhl
https://arxiv.org/abs/2510.00555

PromptPilot: Improving Human-AI Collaboration Through LLM-Enhanced Prompt Engineering
Effective prompt engineering is critical to realizing the promised productivity gains of large language models (LLMs) in knowledge-intensive tasks. Yet, many users struggle to craft prompts that yield high-quality outputs, limiting the practical benefits of LLMs. Existing approaches, such as prompt handbooks or automated optimization pipelines, either require substantial effort, expert knowledge, or lack interactive guidance. To address this gap, we design and evaluate PromptPilot, an interacti…