Tootfinder

Revolution or Hype? Seeking the Limits of Large Models in Hardware Design
Qiang Xu, Leon Stok, Rolf Drechsler, Xi Wang, Grace Li Zhang, Igor L. Markov
https://arxiv.org/abs/2509.04905

Revolution or Hype? Seeking the Limits of Large Models in Hardware Design
Recent breakthroughs in Large Language Models (LLMs) and Large Circuit Models (LCMs) have sparked excitement across the electronic design automation (EDA) community, promising a revolution in circuit design and optimization. Yet, this excitement is met with significant skepticism: Are these AI models a genuine revolution in circuit design, or a temporary wave of inflated expectations? This paper serves as a foundational text for the corresponding ICCAD 2025 panel, bringing together perspectives…

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.…

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…

Transforming Fashion with AI: A Comparative Study of Large Language Models in Apparel Design
Nusrat Jahan Lamia, Sadia Afrin Mim
https://arxiv.org/abs/2509.04705 https://…

Transforming Fashion with AI: A Comparative Study of Large Language Models in Apparel Design
Fashion has evolved from handcrafted designs to automated production over the years, where AI has added another dimension to it. Nowadays, practically every industry uses artificial models to automate their operations. To explore their role, we examined three prominent LLMs (OpenAI, GeminiAI, Deepseek) in multiple stages of textile manufacturing (e.g., sustainable choice, cost effectiveness, production planning, etc.). We assessed the models' ability to replicate garment design using certain pa…

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…

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

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…

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…

INGRID: Intelligent Generative Robotic Design Using Large Language Models
Guanglu Jia, Ceng Zhang, Gregory S. Chirikjian
https://arxiv.org/abs/2509.03842 https://

INGRID: Intelligent Generative Robotic Design Using Large Language Models
The integration of large language models (LLMs) into robotic systems has accelerated progress in embodied artificial intelligence, yet current approaches remain constrained by existing robotic architectures, particularly serial mechanisms. This hardware dependency fundamentally limits the scope of robotic intelligence. Here, we present INGRID (Intelligent Generative Robotic Design), a framework that enables the automated design of parallel robotic mechanisms through deep integration with recipr…

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…

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.

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…

Do Large Language Models Need Intent? Revisiting Response Generation Strategies for Service Assistant
Inbal Bolshinsky, Shani Kupiec, Almog Sasson, Yehudit Aperstein, Alexander Apartsin
https://arxiv.org/abs/2509.05006

Do Large Language Models Need Intent? Revisiting Response Generation Strategies for Service Assistant
In the era of conversational AI, generating accurate and contextually appropriate service responses remains a critical challenge. A central question remains: Is explicit intent recognition a prerequisite for generating high-quality service responses, or can models bypass this step and produce effective replies directly? This paper conducts a rigorous comparative study to address this fundamental design dilemma. Leveraging two publicly available service interaction datasets, we benchmark several…

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?

The Ethical Compass of the Machine: Evaluating Large Language Models for Decision Support in Construction Project Management
Somtochukwu Azie, Yiping Meng
https://arxiv.org/abs/2509.04505

The Ethical Compass of the Machine: Evaluating Large Language Models for Decision Support in Construction Project Management
The integration of Artificial Intelligence (AI) into construction project management (CPM) is accelerating, with Large Language Models (LLMs) emerging as accessible decision-support tools. This study aims to critically evaluate the ethical viability and reliability of LLMs when applied to the ethically sensitive, high-risk decision-making contexts inherent in CPM. A mixed-methods research design was employed, involving the quantitative performance testing of two leading LLMs against twelve real…

“Extensive bidirectional charging functions are also available for the new BMW iX3, meaning that it can be used as an energy supply source for a variety of applications. The Vehicle-to-Load (V2L) function turns the new BMW iX3 into a mobile powerbank, which can supply electric devices with power while on the move. Vehicle-to-Home (V2H) hands it the role of storage unit for solar energy generated by home-fitted photovoltaic systems. [1/2]

The start of a new era. The new BMW iX3.
BMW presents the first series-produced Neue Klasse model. The new-generation BMW iX3 is a fully electric Sports Activity Vehicle (SAV) that gives customers their first on-the-road taste of a whole new era of Sheer Driving Pleasure. An all-new design language gives the car a character-rich appearance that faithfully conveys the technological progress made by the new model. With sixth-generation BMW eDrive technology, a range of up to 805 kilometres (500 miles) and a peak charging rate of 400 kW,…

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…

Are We SOLID Yet? An Empirical Study on Prompting LLMs to Detect Design Principle Violations
Fatih Pehlivan, Ar\c{c}in \"Ulk\"u Erg\"uzen, Sahand Moslemi Yengejeh, Mayasah Lami, Anil Koyuncu
https://arxiv.org/abs/2509.03093

Are We SOLID Yet? An Empirical Study on Prompting LLMs to Detect Design Principle Violations
Traditional static analysis methods struggle to detect semantic design flaws, such as violations of the SOLID principles, which require a strong understanding of object-oriented design patterns and principles. Existing solutions typically focus on individual SOLID principles or specific programming languages, leaving a gap in the ability to detect violations across all five principles in multi-language codebases. This paper presents a new approach: a methodology that leverages tailored prompt e…

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…

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…

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…

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…

Bridging Language Models and Formal Methods for Intent-Driven Optical Network Design
Anis Bekri, Amar Abane, Abdella Battou, Saddek Bensalem
https://arxiv.org/abs/2509.22834 htt…

Bridging Language Models and Formal Methods for Intent-Driven Optical Network Design
Intent-Based Networking (IBN) aims to simplify network management by enabling users to specify high-level goals that drive automated network design and configuration. However, translating informal natural-language intents into formally correct optical network topologies remains challenging due to inherent ambiguity and lack of rigor in Large Language Models (LLMs). To address this, we propose a novel hybrid pipeline that integrates LLM-based intent parsing, formal methods, and Optical Retrieval…

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 …

Evaluating the Robustness of Retrieval-Augmented Generation to Adversarial Evidence in the Health Domain
Shakiba Amirshahi, Amin Bigdeli, Charles L. A. Clarke, Amira Ghenai
https://arxiv.org/abs/2509.03787

Evaluating the Robustness of Retrieval-Augmented Generation to Adversarial Evidence in the Health Domain
Retrieval augmented generation (RAG) systems provide a method for factually grounding the responses of a Large Language Model (LLM) by providing retrieved evidence, or context, as support. Guided by this context, RAG systems can reduce hallucinations and expand the ability of LLMs to accurately answer questions outside the scope of their training data. Unfortunately, this design introduces a critical vulnerability: LLMs may absorb and reproduce misinformation present in retrieved evidence. This…

Chat to Chip: Large Language Model Based Design of Arbitrarily Shaped Metasurfaces
Huanshu Zhang, Lei Kang, Sawyer D. Campbell, Douglas H. Werner
https://arxiv.org/abs/2509.24196

Chat to Chip: Large Language Model Based Design of Arbitrarily Shaped Metasurfaces
Traditional metasurface design is limited by the computational cost of full-wave simulations, preventing thorough exploration of complex configurations. Data-driven approaches have emerged as a solution to this bottleneck, replacing costly simulations with rapid neural network evaluations and enabling near-instant design for meta-atoms. Despite advances, implementing a new optical function still requires building and training a task-specific network, along with exhaustive searches for suitable …

Large Language Models (LLMs) for Electronic Design Automation (EDA)
Kangwei Xu, Denis Schwachhofer, Jason Blocklove, Ilia Polian, Peter Domanski, Dirk Pfl\"uger, Siddharth Garg, Ramesh Karri, Ozgur Sinanoglu, Johann Knechtel, Zhuorui Zhao, Ulf Schlichtmann, Bing Li
https://arxiv.org/abs/2508.20030…

Large Language Models (LLMs) for Electronic Design Automation (EDA)
With the growing complexity of modern integrated circuits, hardware engineers are required to devote more effort to the full design-to-manufacturing workflow. This workflow involves numerous iterations, making it both labor-intensive and error-prone. Therefore, there is an urgent demand for more efficient Electronic Design Automation (EDA) solutions to accelerate hardware development. Recently, large language models (LLMs) have shown remarkable advancements in contextual comprehension, logical …

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…

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…

Designing Gaze Analytics for ELA Instruction: A User-Centered Dashboard with Conversational AI Support
Eduardo Davalos, Yike Zhang, Shruti Jain, Namrata Srivastava, Trieu Truong, Nafees-ul Haque, Tristan Van, Jorge Salas, Sara McFadden, Sun-Joo Cho, Gautam Biswas, Amanda Goodwin
https://arxiv.org/abs/2509.03741

Designing Gaze Analytics for ELA Instruction: A User-Centered Dashboard with Conversational AI Support
Eye-tracking offers rich insights into student cognition and engagement, but remains underutilized in classroom-facing educational technology due to challenges in data interpretation and accessibility. In this paper, we present the iterative design and evaluation of a gaze-based learning analytics dashboard for English Language Arts (ELA), developed through five studies involving teachers and students. Guided by user-centered design and data storytelling principles, we explored how gaze data ca…

EvolveSignal: A Large Language Model Powered Coding Agent for Discovering Traffic Signal Control Algorithms
Leizhen Wang, Peibo Duan, Hao Wang, Yue Wang, Jian Xu, Nan Zheng, Zhenliang Ma
https://arxiv.org/abs/2509.03335

EvolveSignal: A Large Language Model Powered Coding Agent for Discovering Traffic Signal Control Algorithms
In traffic engineering, the fixed-time traffic signal control remains widely used for its low cost, stability, and interpretability. However, its design depends on hand-crafted formulas (e.g., Webster) and manual re-timing by engineers to adapt to demand changes, which is labor-intensive and often yields suboptimal results under heterogeneous or congested conditions. This paper introduces the EvolveSignal, a large language models (LLMs) powered coding agent to automatically discover new traffic…

y'know... from a language design perspective, i think rather little of go. i think its primary redeeming quality is that it is a sort of harm reduction outlet for C programmers
however, now that i've learned to be effective with it, i don't actually mind writing go code. sure, the language is an atrocity, but so is cmake and i don't mind being effective with that either

I wonder how many companies are breaking their own brand guidelines to conform with the Liquid Glass design language 🤔

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…

🤘 Design and Implementation of a 3D Korean Sign Language Learning System Using Pseudo-Hologram
#ui

Vision-Free Retrieval: Rethinking Multimodal Search with Textual Scene Descriptions
Ioanna Ntinou, Alexandros Xenos, Yassine Ouali, Adrian Bulat, Georgios Tzimiropoulos
https://arxiv.org/abs/2509.19203

Vision-Free Retrieval: Rethinking Multimodal Search with Textual Scene Descriptions
Contrastively-trained Vision-Language Models (VLMs), such as CLIP, have become the standard approach for learning discriminative vision-language representations. However, these models often exhibit shallow language understanding, manifesting bag-of-words behaviour. These limitations are reinforced by their dual-encoder design, which induces a modality gap. Additionally, the reliance on vast web-collected data corpora for training makes the process computationally expensive and introduces signif…

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…

BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design
Deepro Choudhury, Sinead Williamson, Adam Goli\'nski, Ning Miao, Freddie Bickford Smith, Michael Kirchhof, Yizhe Zhang, Tom Rainforth
https://arxiv.org/abs/2508.21184

BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design
We propose a general-purpose approach for improving the ability of Large Language Models (LLMs) to intelligently and adaptively gather information from a user or other external source using the framework of sequential Bayesian experimental design (BED). This enables LLMs to act as effective multi-turn conversational agents and interactively interface with external environments. Our approach, which we call BED-LLM (Bayesian Experimental Design with Large Language Models), is based on iteratively…

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…

Guiding Audio Editing with Audio Language Model
Zitong Lan, Yiduo Hao, Mingmin Zhao
https://arxiv.org/abs/2509.21625 https://arxiv.org/pdf/2509.21625

Guiding Audio Editing with Audio Language Model
Audio editing plays a central role in VR/AR immersion, virtual conferencing, sound design, and other interactive media. However, recent generative audio editing models depend on template-like instruction formats and are restricted to mono-channel audio. These models fail to deal with declarative audio editing, where the user declares what the desired outcome should be, while leaving the details of editing operations to the system. We introduce SmartDJ, a novel framework for stereo audio editing…

Large Language Models and Futures Price Factors in China
Yuhan Cheng, Heyang Zhou, Yanchu Liu
https://arxiv.org/abs/2509.23609 https://arxiv.org/pdf/2509.2…

Large Language Models and Futures Price Factors in China
We leverage the capacity of large language models such as Generative Pre-trained Transformer (GPT) in constructing factor models for Chinese futures markets. We successfully obtain 40 factors to design single-factor and multi-factor portfolios through long-short and long-only strategies, conducting backtests during the in-sample and out-of-sample period. Comprehensive empirical analysis reveals that GPT-generated factors deliver remarkable Sharpe ratios and annualized returns while maintaining …

Large Language Models for 3D IC Space Planning
Hung-Ying Chu, Guan-Wei Chen, Shao-Yu Wei, Yu-Cheng Lin
https://arxiv.org/abs/2509.22716 https://arxiv.org/p…

Large Language Models for 3D IC Space Planning
Three-dimensional integrated circuits (3D ICs) have emerged as a promising solution to the scaling limits of two-dimensional designs, offering higher integration density, shorter interconnects, and improved performance. As design complexity increases, effective space planning becomes essential to reduce dead space and ensure layout quality. This study investigates the use of large language models (LLMs) for 3D IC space planning through a post-order slicing tree representation, which guarantees …

Nova: Real-Time Agentic Vision-Language Model Serving with Adaptive Cross-Stage Parallelization
Yuhang Xu, Shengzhong Liu, Dong Zhang, Bingheng Yan, Fan Wu, Guihai Chen
https://arxiv.org/abs/2509.21301

Nova: Real-Time Agentic Vision-Language Model Serving with Adaptive Cross-Stage Parallelization
This paper presents Nova, a real-time scheduling framework for serving agentic vision-language models (VLMs) on a single GPU with balanced per-request latency and overall request process throughput. Our design begins by enabling effective pipelining across vision encode, LLM prefill, and LLM decode stages of VLMs, by exploiting their heterogeneous resource demands during execution and incorporating elastic GPU spatial partitioning among stages to maximally utilize the compute and memory resourc…

Toward Engineering AGI: Benchmarking the Engineering Design Capabilities of LLMs
Xingang Guo, Yaxin Li, Xiangyi Kong, Yilan Jiang, Xiayu Zhao, Zhihua Gong, Yufan Zhang, Daixuan Li, Tianle Sang, Beixiao Zhu, Gregory Jun, Yingbing Huang, Yiqi Liu, Yuqi Xue, Rahul Dev Kundu, Qi Jian Lim, Yizhou Zhao, Luke Alexander Granger, Mohamed Badr Younis, Darioush Keivan, Nippun Sabharwal, Shreyanka Sinha, Prakhar Agarwal, Kojo Vandyck, Hanlin Mai, Zichen Wang, Aditya Venkatesh, Ayush Barik, Jiankun…

Toward Engineering AGI: Benchmarking the Engineering Design Capabilities of LLMs
Today, industry pioneers dream of developing general-purpose AI engineers capable of designing and building humanity's most ambitious projects--from starships that will carry us to distant worlds to Dyson spheres that harness stellar energy. Yet engineering design represents a fundamentally different challenge for large language models (LLMs) compared to traditional textbook-style problem solving or factual question answering. Real-world engineering design demands the synthesis of domain knowle…

PromptCOS: Towards System Prompt Copyright Auditing for LLMs via Content-level Output Similarity
Yuchen Yang, Yiming Li, Hongwei Yao, Enhao Huang, Shuo Shao, Bingrun Yang, Zhibo Wang, Dacheng Tao, Zhan Qin
https://arxiv.org/abs/2509.03117

PromptCOS: Towards System Prompt Copyright Auditing for LLMs via Content-level Output Similarity
The rapid progress of large language models (LLMs) has greatly enhanced reasoning tasks and facilitated the development of LLM-based applications. A critical factor in improving LLM-based applications is the design of effective system prompts, which significantly impact the behavior and output quality of LLMs. However, system prompts are susceptible to theft and misuse, which could undermine the interests of prompt owners. Existing methods protect prompt copyrights through watermark injection a…

PhenoMoler: Phenotype-Guided Molecular Optimization via Chemistry Large Language Model
Ran Song, Hui Liu
https://arxiv.org/abs/2509.21424 https://arxiv.org…

PhenoMoler: Phenotype-Guided Molecular Optimization via Chemistry Large Language Model
Current molecular generative models primarily focus on improving drug-target binding affinity and specificity, often neglecting the system-level phenotypic effects elicited by compounds. Transcriptional profiles, as molecule-level readouts of drug-induced phenotypic shifts, offer a powerful opportunity to guide molecular design in a phenotype-aware manner. We present PhenoMoler, a phenotype-guided molecular generation framework that integrates a chemistry large language model with expression pr…

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…

Comparing Open-Source and Commercial LLMs for Domain-Specific Analysis and Reporting: Software Engineering Challenges and Design Trade-offs
Theo Koraag, Niklas Wagner, Felix Dobslaw, Lucas Gren
https://arxiv.org/abs/2509.24344

Comparing Open-Source and Commercial LLMs for Domain-Specific Analysis and Reporting: Software Engineering Challenges and Design Trade-offs
Context: Large Language Models (LLMs) enable automation of complex natural language processing across domains, but research on domain-specific applications like Finance remains limited. Objectives: This study explored open-source and commercial LLMs for financial report analysis and commentary generation, focusing on software engineering challenges in implementation. Methods: Using Design Science Research methodology, an exploratory case study iteratively designed and evaluated two LLM-based sy…

AutoPBO: LLM-powered Optimization for Local Search PBO Solvers
Jinyuan Li, Yi Chu, Yiwen Sun, Mengchuan Zou, Shaowei Cai
https://arxiv.org/abs/2509.04007 https://

AutoPBO: LLM-powered Optimization for Local Search PBO Solvers
Pseudo-Boolean Optimization (PBO) provides a powerful framework for modeling combinatorial problems through pseudo-Boolean (PB) constraints. Local search solvers have shown excellent performance in PBO solving, and their efficiency is highly dependent on their internal heuristics to guide the search. Still, their design often requires significant expert effort and manual tuning in practice. While Large Language Models (LLMs) have demonstrated potential in automating algorithm design, their appl…

What Makes LLM Agent Simulations Useful for Policy? Insights From an Iterative Design Engagement in Emergency Preparedness
Yuxuan Li, Sauvik Das, Hirokazu Shirado
https://arxiv.org/abs/2509.21868

What Makes LLM Agent Simulations Useful for Policy? Insights From an Iterative Design Engagement in Emergency Preparedness
There is growing interest in using Large Language Models as agents (LLM agents) for social simulations to inform policy, yet real-world adoption remains limited. This paper addresses the question: How can LLM agent simulations be made genuinely useful for policy? We report on a year-long iterative design engagement with a university emergency preparedness team. Across multiple design iterations, we iteratively developed a system of 13,000 LLM agents that simulate crowd movement and communicatio…

Geopolitical Parallax: Beyond Walter Lippmann Just After Large Language Models
Mehmet Can Yavuz, Humza Gohar Kabir, Aylin \"Ozkan
https://arxiv.org/abs/2508.19492 https://

Geopolitical Parallax: Beyond Walter Lippmann Just After Large Language Models
Objectivity in journalism has long been contested, oscillating between ideals of neutral, fact-based reporting and the inevitability of subjective framing. With the advent of large language models (LLMs), these tensions are now mediated by algorithmic systems whose training data and design choices may themselves embed cultural or ideological biases. This study investigates geopolitical parallax-systematic divergence in news quality and subjectivity assessments-by comparing article-level embeddi…

Lang2Morph: Language-Driven Morphological Design of Robotic Hands
Yanyuan Qiao, Kieran Gilday, Yutong Xie, Josie Hughes
https://arxiv.org/abs/2509.18937 https://

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…

Mitigating Hallucination in Multimodal LLMs with Layer Contrastive Decoding
Bingkui Tong, Jiaer Xia, Kaiyang Zhou
https://arxiv.org/abs/2509.25177 https://…

Mitigating Hallucination in Multimodal LLMs with Layer Contrastive Decoding
Multimodal Large Language Models (MLLMs) have shown impressive perception and reasoning capabilities, yet they often suffer from hallucinations -- generating outputs that are linguistically coherent but inconsistent with the context of the input image, including inaccuracies in objects, attributes, and relations. To address this challenge, we propose a simple approach called Layer Contrastive Decoding (LayerCD). Our design is motivated by the observation that shallow visual features are much mo…

AI Propaganda factories with language models
Lukasz Olejnik
https://arxiv.org/abs/2508.20186 https://arxiv.org/pdf/2508.20186

AI Propaganda factories with language models
AI-powered influence operations can now be executed end-to-end on commodity hardware. We show that small language models produce coherent, persona-driven political messaging and can be evaluated automatically without human raters. Two behavioural findings emerge. First, persona-over-model: persona design explains behaviour more than model identity. Second, engagement as a stressor: when replies must counter-arguments, ideological adherence strengthens and the prevalence of extreme content incre…

AssertFix: Empowering Automated Assertion Fix via Large Language Models
Hongqin Lyu, Yunlin Du, Yonghao Wang, Zhiteng Chao, Tiancheng Wang, Huawei Li
https://arxiv.org/abs/2509.23972

AssertFix: Empowering Automated Assertion Fix via Large Language Models
Assertion-based verification (ABV) is critical in ensuring that register-transfer level (RTL) designs conform to their functional specifications. SystemVerilog Assertions (SVA) effectively specify design properties, but writing and maintaining them manually is challenging and error-prone. Although recent progress of assertion generation methods leveraging large language models (LLMs) have shown great potential in improving assertion quality, they typically treat assertion generation as a final …

Mamba-2 audio captioning: design space exploration and analysis
Taehan Lee, Jaehan Jung, Hyukjun Lee
https://arxiv.org/abs/2509.15680 https://arxiv.org/pdf…

Mamba-2 audio captioning: design space exploration and analysis
We present an audio captioning model built on the Mamba-2 large language model backbone, which is a state-of-the-art (SOTA) state-space model (SSM). We systematically explore the design space: LLM sizes, LoRA ranks, and connector designs leveraging Mamba-2's linear-time complexity with respect to sequence length. Across benchmarks, our models achieve strong captioning performance compared with larger language models trained on the same dataset, despite using fewer parameters. For the first time…

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.

Supporting Intervention Design for Suicide Prevention with Language Model Assistants
Jaspreet Ranjit, Hyundong J. Cho, Claire J. Smerdon, Yoonsoo Nam, Myles Phung, Jonathan May, John R. Blosnich, Swabha Swayamdipta
https://arxiv.org/abs/2508.18541

Supporting Intervention Design for Suicide Prevention with Language Model Assistants
Warning: This paper discusses topics of suicide and suicidal ideation, which may be distressing to some readers. The National Violent Death Reporting System (NVDRS) documents information about suicides in the United States, including free text narratives (e.g., circumstances surrounding a suicide). In a demanding public health data pipeline, annotators manually extract structured information from death investigation records following extensive guidelines developed painstakingly by experts. In…

"She was useful, but a bit too optimistic": Augmenting Design with Interactive Virtual Personas
Paluck Deep, Monica Bharadhidasan, A. Baki Kocaballi
https://arxiv.org/abs/2508.19463

"She was useful, but a bit too optimistic": Augmenting Design with Interactive Virtual Personas
Personas have been widely used to understand and communicate user needs in human-centred design. Despite their utility, they may fail to meet the demands of iterative workflows due to their static nature, limited engagement, and inability to adapt to evolving design needs. Recent advances in large language models (LLMs) pave the way for more engaging and adaptive approaches to user representation. This paper introduces Interactive Virtual Personas (IVPs): multimodal, LLM-driven, conversational …

An LLM-powered Natural-to-Robotic Language Translation Framework with Correctness Guarantees
ZhenDong Chen, ZhanShang Nie, ShiXing Wan, JunYi Li, YongTian Cheng, Shuai Zhao
https://arxiv.org/abs/2508.19074

An LLM-powered Natural-to-Robotic Language Translation Framework with Correctness Guarantees
The Large Language Models (LLM) are increasingly being deployed in robotics to generate robot control programs for specific user tasks, enabling embodied intelligence. Existing methods primarily focus on LLM training and prompt design that utilize LLMs to generate executable programs directly from user tasks in natural language. However, due to the inconsistency of the LLMs and the high complexity of the tasks, such best-effort approaches often lead to tremendous programming errors in the gener…

Towards Understanding the Shape of Representations in Protein Language Models
Kosio Beshkov, Anders Malthe-S{\o}renssen
https://arxiv.org/abs/2509.24895 https://

Towards Understanding the Shape of Representations in Protein Language Models
While protein language models (PLMs) are one of the most promising avenues of research for future de novo protein design, the way in which they transform sequences to hidden representations, as well as the information encoded in such representations is yet to be fully understood. Several works have attempted to propose interpretability tools for PLMs, but they have focused on understanding how individual sequences are transformed by such models. Therefore, the way in which PLMs transform the wh…

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…

Unlocking the Effectiveness of LoRA-FP for Seamless Transfer Implantation of Fingerprints in Downstream Models
Zhenhua Xu, Zhaokun Yan, Binhan Xu, Xin Tong, Haitao Xu, Yourong Chen, Meng Han
https://arxiv.org/abs/2509.00820

Unlocking the Effectiveness of LoRA-FP for Seamless Transfer Implantation of Fingerprints in Downstream Models
With the rapid advancement of large language models (LLMs), safeguarding intellectual property (IP) has become increasingly critical. To address the challenges of high costs and potential contamination in fingerprint integration, we propose LoRA-FP, a lightweight, plug-and-play framework that embeds backdoor fingerprints into LoRA adapters through constrained fine-tuning. This design enables seamless fingerprint transplantation via parameter fusion, eliminating the need for full-parameter updat…

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…

Green Prompt Engineering: Investigating the Energy Impact of Prompt Design in Software Engineering
Vincenzo De Martino, Mohammad Amin Zadenoori, Xavier Franch, Alessio Ferrari
https://arxiv.org/abs/2509.22320

Green Prompt Engineering: Investigating the Energy Impact of Prompt Design in Software Engineering
Language Models are increasingly applied in software engineering, yet their inference raises growing environmental concerns. Prior work has examined hardware choices and prompt length, but little attention has been paid to linguistic complexity as a sustainability factor. This paper introduces Green Prompt Engineering, framing linguistic complexity as a design dimension that can influence energy consumption and performance. We conduct an empirical study on requirement classification using open-…

AI Agents for Photonic Integrated Circuit Design Automation
Ankita Sharma, YuQi Fu, Vahid Ansari, Rishabh Iyer, Fiona Kuang, Kashish Mistry, Raisa Islam Aishy, Sara Ahmad, Joaquin Matres, Dirk R. Englund, Joyce K. S. Poon
https://arxiv.org/abs/2508.14123

AI Agents for Photonic Integrated Circuit Design Automation
We present Photonics Intelligent Design and Optimization (PhIDO), a multi-agent framework that converts natural-language photonic integrated circuit (PIC) design requests into layout mask files. We compare 7 reasoning large language models for PhIDO using a testbench of 102 design descriptions that ranged from single devices to 112-component PICs. The success rate for single-device designs was up to 91%. For design queries with less than or equal to 15 components, o1, Gemini-2.5-pro, and Claude…

Text-to-Layout: A Generative Workflow for Drafting Architectural Floor Plans Using LLMs
Jayakrishna Duggempudi, Lu Gao, Ahmed Senouci, Zhe Han, Yunpeng Zhang
https://arxiv.org/abs/2509.00543

Text-to-Layout: A Generative Workflow for Drafting Architectural Floor Plans Using LLMs
This paper presents the development of an AI-powered workflow that uses Large Language Models (LLMs) to assist in drafting schematic architectural floor plans from natural language prompts. The proposed system interprets textual input to automatically generate layout options including walls, doors, windows, and furniture arrangements. It combines prompt engineering, a furniture placement refinement algorithm, and Python scripting to produce spatially coherent draft plans compatible with design …

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…

Communication Bias in Large Language Models: A Regulatory Perspective
Adrian Kuenzler, Stefan Schmid
https://arxiv.org/abs/2509.21075 https://arxiv.org/pdf…

Communication Bias in Large Language Models: A Regulatory Perspective
Large language models (LLMs) are increasingly central to many applications, raising concerns about bias, fairness, and regulatory compliance. This paper reviews risks of biased outputs and their societal impact, focusing on frameworks like the EU's AI Act and the Digital Services Act. We argue that beyond constant regulation, stronger attention to competition and design governance is needed to ensure fair, trustworthy AI. This is a preprint of the Communications of the ACM article of the same t…

Is this chart lying to me? Automating the detection of misleading visualizations
Jonathan Tonglet, Jan Zimny, Tinne Tuytelaars, Iryna Gurevych
https://arxiv.org/abs/2508.21675 h…

Is this chart lying to me? Automating the detection of misleading visualizations
Misleading visualizations are a potent driver of misinformation on social media and the web. By violating chart design principles, they distort data and lead readers to draw inaccurate conclusions. Prior work has shown that both humans and multimodal large language models (MLLMs) are frequently deceived by such visualizations. Automatically detecting misleading visualizations and identifying the specific design rules they violate could help protect readers and reduce the spread of misinformatio…

Cooperative Design Optimization through Natural Language Interaction
Ryogo Niwa, Shigeo Yoshida, Yuki Koyama, Yoshitaka Ushiku
https://arxiv.org/abs/2508.16077 https://

Cooperative Design Optimization through Natural Language Interaction
Designing successful interactions requires identifying optimal design parameters. To do so, designers often conduct iterative user testing and exploratory trial-and-error. This involves balancing multiple objectives in a high-dimensional space, making the process time-consuming and cognitively demanding. System-led optimization methods, such as those based on Bayesian optimization, can determine for designers which parameters to test next. However, they offer limited opportunities for designers…

Evaluating Large Language Models for Code Translation: Effects of Prompt Language and Prompt Design
Aamer Aljagthami, Mohammed Banabila, Musab Alshehri, Mohammed Kabini, Mohammad D. Alahmadi
https://arxiv.org/abs/2509.12973

Evaluating Large Language Models for Code Translation: Effects of Prompt Language and Prompt Design
Large language models (LLMs) have shown promise for automated source-code translation, a capability critical to software migration, maintenance, and interoperability. Yet comparative evidence on how model choice, prompt design, and prompt language shape translation quality across multiple programming languages remains limited. This study conducts a systematic empirical assessment of state-of-the-art LLMs for code translation among C++, Java, Python, and C#, alongside a traditional baseline (Tra…

ASIC-Agent: An Autonomous Multi-Agent System for ASIC Design with Benchmark Evaluation
Ahmed Allam, Youssef Mansour, Mohamed Shalan
https://arxiv.org/abs/2508.15940 https://

ASIC-Agent: An Autonomous Multi-Agent System for ASIC Design with Benchmark Evaluation
Large Language Models (LLMs) have demonstrated remarkable capabilities in Register Transfer Level (RTL) design, enabling high-quality code generation from natural language descriptions. However, LLMs alone face significant limitations in real-world hardware design workflows, including the inability to execute code, lack of debugging capabilities, and absence of long-term memory. To address these challenges, we present ASIC-Agent, an autonomous system designed specifically for digital ASIC desig…

Digital Twin-Guided Robot Path Planning: A Beta-Bernoulli Fusion with Large Language Model as a Sensor
Mani Amani, Reza Akhavian
https://arxiv.org/abs/2509.20709 https://…

Digital Twin-Guided Robot Path Planning: A Beta-Bernoulli Fusion with Large Language Model as a Sensor
Integrating natural language (NL) prompts into robotic mission planning has attracted significant interest in recent years. In the construction domain, Building Information Models (BIM) encapsulate rich NL descriptions of the environment. We present a novel framework that fuses NL directives with BIM-derived semantic maps via a Beta-Bernoulli Bayesian fusion by interpreting the LLM as a sensor: each obstacle's design-time repulsive coefficient is treated as a Beta(alpha, beta) random variable a…

Estimating the Empowerment of Language Model Agents
Jinyeop Song, Jeff Gore, Max Kleiman-Weiner
https://arxiv.org/abs/2509.22504 https://arxiv.org/pdf/2509…

Estimating the Empowerment of Language Model Agents
As language model (LM) agents become more capable and gain broader access to real-world tools, there is a growing need for scalable evaluation frameworks of agentic capability. However, conventional benchmark-centric evaluations are costly to design and require human designers to come up with valid tasks that translate into insights about general model capabilities. In this work, we propose information-theoretic evaluation based on empowerment, the mutual information between an agent's actions …

Automating Modelica Module Generation Using Large Language Models: A Case Study on Building Control Description Language
Hanlong Wan, Xing Lu, Yan Chen, Karthik Devaprasad, Laura Hinkle
https://arxiv.org/abs/2509.14623

Automating Modelica Module Generation Using Large Language Models: A Case Study on Building Control Description Language
Dynamic energy systems and controls require advanced modeling frameworks to design and test supervisory and fault tolerant strategies. Modelica is a widely used equation based language, but developing control modules is labor intensive and requires specialized expertise. This paper examines the use of large language models (LLMs) to automate the generation of Control Description Language modules in the Building Modelica Library as a case study. We developed a structured workflow that combines s…

Enabling Multi-Agent Systems as Learning Designers: Applying Learning Sciences to AI Instructional Design
Jiayi Wang, Ruiwei Xiao, Xinying Hou, John Stamper
https://arxiv.org/abs/2508.16659

Enabling Multi-Agent Systems as Learning Designers: Applying Learning Sciences to AI Instructional Design
K-12 educators are increasingly using Large Language Models (LLMs) to create instructional materials. These systems excel at producing fluent, coherent content, but often lack support for high-quality teaching. The reason is twofold: first, commercial LLMs, such as ChatGPT and Gemini which are among the most widely accessible to teachers, do not come preloaded with the depth of pedagogical theory needed to design truly effective activities; second, although sophisticated prompt engineering can …

Insights into User Interface Innovations from a Design Thinking Workshop at deRSE25
Maximilian Frank, Simon Lund
https://arxiv.org/abs/2508.18784 https://a…

Insights into User Interface Innovations from a Design Thinking Workshop at deRSE25
Large Language Models have become widely adopted tools due to their versatile capabilities, yet their user interfaces remain limited, often following rigid, linear interaction paradigms. In this paper, we present insights from a design thinking workshop held at the deRSE25 conference aiming at collaboratively developing innovative user interface concepts for LLMs. During the workshop, participants identified common use cases, evaluated the strengths and shortcomings of current LLM interfaces, a…

Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[2/2]:
- Trust but Verify! A Survey on Verification Design for Test-time Scaling
V Venktesh, Mandeep Rathee, Avishek Anand

Re-evaluating LLM-based Heuristic Search: A Case Study on the 3D Packing Problem
Guorui Quan, Mingfei Sun, Manuel L\'opez-Ib\'a\~nez
https://arxiv.org/abs/2509.02297 htt…

Re-evaluating LLM-based Heuristic Search: A Case Study on the 3D Packing Problem
The art of heuristic design has traditionally been a human pursuit. While Large Language Models (LLMs) can generate code for search heuristics, their application has largely been confined to adjusting simple functions within human-crafted frameworks, leaving their capacity for broader innovation an open question. To investigate this, we tasked an LLM with building a complete solver for the constrained 3D Packing Problem. Direct code generation quickly proved fragile, prompting us to introduce t…

IDfRA: Self-Verification for Iterative Design in Robotic Assembly
Nishka Khendry, Christos Margadji, Sebastian W. Pattinson
https://arxiv.org/abs/2509.16998 https://

IDfRA: Self-Verification for Iterative Design in Robotic Assembly
As robots proliferate in manufacturing, Design for Robotic Assembly (DfRA), which is designing products for efficient automated assembly, is increasingly important. Traditional approaches to DfRA rely on manual planning, which is time-consuming, expensive and potentially impractical for complex objects. Large language models (LLM) have exhibited proficiency in semantic interpretation and robotic task planning, stimulating interest in their application to the automation of DfRA. But existing met…

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…

SnipSnap: A Joint Compression Format and Dataflow Co-Optimization Framework for Efficient Sparse LLM Accelerator Design
Junyi Wu, Chao Fang, Zhongfeng Wang
https://arxiv.org/abs/2509.17072

SnipSnap: A Joint Compression Format and Dataflow Co-Optimization Framework for Efficient Sparse LLM Accelerator Design
The growing scale of large language models (LLMs) has intensified demands on computation and memory, making efficient inference a key challenge. While sparsity can reduce these costs, existing design space exploration (DSE) frameworks often overlook compression formats, a key factor for leveraging sparsity on accelerators. This paper proposes SnipSnap, a joint compression format and dataflow co-optimization framework for efficient sparse LLM accelerator design. SnipSnap introduces: (1) a hierar…

Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search
Yuxian Gu, Qinghao Hu, Shang Yang, Haocheng Xi, Junyu Chen, Song Han, Han Cai
https://arxiv.org/abs/2508.15884

Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search
We present Jet-Nemotron, a new family of hybrid-architecture language models, which matches or exceeds the accuracy of leading full-attention models while significantly improving generation throughput. Jet-Nemotron is developed using Post Neural Architecture Search (PostNAS), a novel neural architecture exploration pipeline that enables efficient model design. Unlike prior approaches, PostNAS begins with a pre-trained full-attention model and freezes its MLP weights, allowing efficient explorat…

Reverse Engineering User Stories from Code using Large Language Models
Mohamed Ouf, Haoyu Li, Michael Zhang, Mariam Guizani
https://arxiv.org/abs/2509.19587 https://

Reverse Engineering User Stories from Code using Large Language Models
User stories are essential in agile development, yet often missing or outdated in legacy and poorly documented systems. We investigate whether large language models (LLMs) can automatically recover user stories directly from source code and how prompt design impacts output quality. Using 1,750 annotated C++ snippets of varying complexity, we evaluate five state-of-the-art LLMs across six prompting strategies. Results show that all models achieve, on average, an F1 score of 0.8 for code up to 20…

FedChip: Federated LLM for Artificial Intelligence Accelerator Chip Design
Mahmoud Nazzal, Khoa Nguyen, Deepak Vungarala, Ramtin Zand, Shaahin Angizi, Hai Phan, Abdallah Khreishah
https://arxiv.org/abs/2508.13162

FedChip: Federated LLM for Artificial Intelligence Accelerator Chip Design
AI hardware design is advancing rapidly, driven by the promise of design automation to make chip development faster, more efficient, and more accessible to a wide range of users. Amongst automation tools, Large Language Models (LLMs) offer a promising solution by automating and streamlining parts of the design process. However, their potential is hindered by data privacy concerns and the lack of domain-specific training. To address this, we introduce FedChip, a Federated fine-tuning approach th…

Vibe Coding for UX Design: Understanding UX Professionals' Perceptions of AI-Assisted Design and Development
Jie Li, Youyang Hou, Laura Lin, Ruihao Zhu, Hancheng Cao, Abdallah El Ali
https://arxiv.org/abs/2509.10652

Vibe Coding for UX Design: Understanding UX Professionals' Perceptions of AI-Assisted Design and Development
Generative AI is reshaping UX design practices through "vibe coding," where UX professionals express intent in natural language and AI translates it into functional prototypes and code. Despite rapid adoption, little research has examined how vibe coding reconfigures UX workflows and collaboration. Drawing on interviews with 20 UX professionals across enterprises, startups, and academia, we show how vibe coding follows a four-stage workflow of ideation, AI generation, debugging, and review. Thi…

Evaluating Multilingual and Code-Switched Alignment in LLMs via Synthetic Natural Language Inference
Samir Abdaljalil, Erchin Serpedin, Khalid Qaraqe, Hasan Kurban
https://arxiv.org/abs/2508.14735

Evaluating Multilingual and Code-Switched Alignment in LLMs via Synthetic Natural Language Inference
Large language models (LLMs) are increasingly applied in multilingual contexts, yet their capacity for consistent, logically grounded alignment across languages remains underexplored. We present a controlled evaluation framework for multilingual natural language inference (NLI) that generates synthetic, logic-based premise-hypothesis pairs and translates them into a typologically diverse set of languages. This design enables precise control over semantic relations and allows testing in both mon…

From Law to Gherkin: A Human-Centred Quasi-Experiment on the Quality of LLM-Generated Behavioural Specifications from Food-Safety Regulations
Shabnam Hassani, Mehrdad Sabetzadeh, Daniel Amyot
https://arxiv.org/abs/2508.20744

From Law to Gherkin: A Human-Centred Quasi-Experiment on the Quality of LLM-Generated Behavioural Specifications from Food-Safety Regulations
Context: Laws and regulations increasingly affect software design and quality assurance, but legal texts are written in technology-neutral language. This creates challenges for engineers who must develop compliance artifacts such as requirements and acceptance criteria. Manual creation is labor-intensive, error-prone, and requires domain expertise. Advances in Generative AI (GenAI), especially Large Language Models (LLMs), offer a way to automate deriving such artifacts. Objective: We present…

ST-LINK: Spatially-Aware Large Language Models for Spatio-Temporal Forecasting
Hyotaek Jeon, Hyunwook Lee, Juwon Kim, Sungahn Ko
https://arxiv.org/abs/2509.13753 https://…

ST-LINK: Spatially-Aware Large Language Models for Spatio-Temporal Forecasting
Traffic forecasting represents a crucial problem within intelligent transportation systems. In recent research, Large Language Models (LLMs) have emerged as a promising method, but their intrinsic design, tailored primarily for sequential token processing, introduces notable challenges in effectively capturing spatial dependencies. Specifically, the inherent limitations of LLMs in modeling spatial relationships and their architectural incompatibility with graph-structured spatial data remain la…

Democracy-in-Silico: Institutional Design as Alignment in AI-Governed Polities
Trisanth Srinivasan, Santosh Patapati
https://arxiv.org/abs/2508.19562 https://

Democracy-in-Silico: Institutional Design as Alignment in AI-Governed Polities
This paper introduces Democracy-in-Silico, an agent-based simulation where societies of advanced AI agents, imbued with complex psychological personas, govern themselves under different institutional frameworks. We explore what it means to be human in an age of AI by tasking Large Language Models (LLMs) to embody agents with traumatic memories, hidden agendas, and psychological triggers. These agents engage in deliberation, legislation, and elections under various stressors, such as budget cris…

AnalogSeeker: An Open-source Foundation Language Model for Analog Circuit Design
Zihao Chen, Ji Zhuang, Jinyi Shen, Xiaoyue Ke, Xinyi Yang, Mingjie Zhou, Zhuoyao Du, Xu Yan, Zhouyang Wu, Zhenyu Xu, Jiangli Huang, Li Shang, Xuan Zeng, Fan Yang
https://arxiv.org/abs/2508.10409

AnalogSeeker: An Open-source Foundation Language Model for Analog Circuit Design
In this paper, we propose AnalogSeeker, an effort toward an open-source foundation language model for analog circuit design, with the aim of integrating domain knowledge and giving design assistance. To overcome the scarcity of data in this field, we employ a corpus collection strategy based on the domain knowledge framework of analog circuits. High-quality, accessible textbooks across relevant subfields are systematically curated and cleaned into a textual domain corpus. To address the complex…

WeDesign: Generative AI-Facilitated Community Consultations for Urban Public Space Design
Rashid Mushkani, Hugo Berard, Shin Koseki
https://arxiv.org/abs/2508.19256 https://

WeDesign: Generative AI-Facilitated Community Consultations for Urban Public Space Design
Community consultations are integral to urban planning processes intended to incorporate diverse stakeholder perspectives. However, limited resources, visual and spoken language barriers, and uneven power dynamics frequently constrain inclusive decision-making. This paper examines how generative text-to-image methods, specifically Stable Diffusion XL integrated into a custom platform (WeDesign), may support equitable consultations. A half-day workshop in Montreal involved five focus groups, eac…

DESIGNER: Design-Logic-Guided Multidisciplinary Data Synthesis for LLM Reasoning
Weize Liu, Yongchi Zhao, Yijia Luo, Mingyu Xu, Jiaheng Liu, Yanan Li, Xiguo Hu, Yuchi Xu, Wenbo Su, Bo Zheng
https://arxiv.org/abs/2508.12726

DESIGNER: Design-Logic-Guided Multidisciplinary Data Synthesis for LLM Reasoning
Large language models (LLMs) have achieved remarkable success in many natural language tasks but still struggle with complex, multi-step reasoning, particularly across diverse disciplines. Existing reasoning datasets often either lack disciplinary breadth or the structural depth necessary to elicit robust reasoning behaviors. We propose DESIGNER: a DESIGN-logic-guidEd Reasoning data synthesis pipeline that leverages naturally available, extensive raw documents (book corpus and web corpus) to ge…

Development of Automated Software Design Document Review Methods Using Large Language Models
Takasaburo Fukuda, Takao Nakagawa, Keisuke Miyazaki, Susumu Tokumoto
https://arxiv.org/abs/2509.09975

Development of Automated Software Design Document Review Methods Using Large Language Models
In this study, we explored an approach to automate the review process of software design documents by using LLM. We first analyzed the review methods of design documents and organized 11 review perspectives. Additionally, we analyzed the issues of utilizing LLMs for these 11 review perspectives and determined which perspectives can be reviewed by current general-purpose LLMs instead of humans. For the reviewable perspectives, we specifically developed new techniques to enable LLMs to comprehend…

Affordances of Sketched Notations for Multimodal UI Design and Development Tools
Sam H. Ross, Yunseo Lee, Coco K. Lee, Jayne Everson, R. Benjamin Shapiro
https://arxiv.org/abs/2508.09342

Affordances of Sketched Notations for Multimodal UI Design and Development Tools
Multimodal UI design and development tools that interpret sketches or natural language descriptions of UIs inherently have notations: the inputs they can understand. In AI-based systems, notations are implicitly defined by the data used to train these systems. In order to create usable and intuitive notations for interactive design systems, we must regard, design, and evaluate these training datasets as notation specifications. To better understand the design space of notational possibilities f…

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…

WIP: Leveraging LLMs for Enforcing Design Principles in Student Code: Analysis of Prompting Strategies and RAG
Dhruv Kolhatkar, Soubhagya Akkena, Edward F. Gehringer
https://arxiv.org/abs/2508.11717

WIP: Leveraging LLMs for Enforcing Design Principles in Student Code: Analysis of Prompting Strategies and RAG
This work-in-progress research-to-practice paper explores the integration of Large Language Models (LLMs) into the code-review process for open-source software projects developed in computer science and software engineering courses. The focus is on developing an automated feedback tool that evaluates student code for adherence to key object-oriented design principles, addressing the need for more effective and scalable methods to teach software design best practices. The innovative practice inv…

Computational Economics in Large Language Models: Exploring Model Behavior and Incentive Design under Resource Constraints
Sandeep Reddy, Kabir Khan, Rohit Patil, Ananya Chakraborty, Faizan A. Khan, Swati Kulkarni, Arjun Verma, Neha Singh
https://arxiv.org/abs/2508.10426

Computational Economics in Large Language Models: Exploring Model Behavior and Incentive Design under Resource Constraints
Large language models (LLMs) are limited by substantial computational cost. We introduce a "computational economics" framework that treats an LLM as an internal economy of resource-constrained agents (attention heads and neuron blocks) that must allocate scarce computation to maximize task utility. First, we show empirically that when computation is scarce, standard LLMs reallocate attention toward high-value tokens while preserving accuracy. Building on this observation, we propose an incentiv…