Tootfinder

AI Playing Business Games: Benchmarking Large Language Models on Managerial Decision-Making in Dynamic Simulations
Berdymyrat Ovezmyradov
https://arxiv.org/abs/2509.26331 https:…

AI Playing Business Games: Benchmarking Large Language Models on Managerial Decision-Making in Dynamic Simulations
The rapid advancement of LLMs sparked significant interest in their potential to augment or automate managerial functions. One of the most recent trends in AI benchmarking is performance of Large Language Models (LLMs) over longer time horizons. While LLMs excel at tasks involving natural language and pattern recognition, their capabilities in multi-step, strategic business decision-making remain largely unexplored. Few studies demonstrated how results can be different from benchmarks in short-…

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[3/5]:
- RS-OOD: A Vision-Language Augmented Framework for Out-of-Distribution Detection in Remote Sensing
Chenhao Wang, Yingrui Ji, Yu Meng, Yunjian Zhang, Yao Zhu

Convergence and Divergence of Language Models under Different Random Seeds
Finlay Fehlauer (ETH Zurich), Kyle Mahowald (University of Texas at Austin), Tiago Pimentel (ETH Zurich)
https://arxiv.org/abs/2509.26643

Convergence and Divergence of Language Models under Different Random Seeds
In this paper, we investigate the convergence of language models (LMs) trained under different random seeds, measuring convergence as the expected per-token Kullback--Leibler (KL) divergence across seeds. By comparing LM convergence as a function of model size and training checkpoint, we identify a four-phase convergence pattern: (i) an initial uniform phase, (ii) a sharp-convergence phase, (iii) a sharp-divergence phase, and (iv) a slow-reconvergence phase. Further, we observe that larger mode…

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[5/5]:
- HAMLET: Switch your Vision-Language-Action Model into a History-Aware Policy
Myungkyu Koo, Daewon Choi, Taeyoung Kim, Kyungmin Lee, Changyeon Kim, Younggyo Seo, Jinwoo Shin

"Very sad day for crow enthusiasts" says #pastagang

SPADE: A Large Language Model Framework for Soil Moisture Pattern Recognition and Anomaly Detection in Precision Agriculture
Yeonju Lee, Rui Qi Chen, Joseph Oboamah, Po Nien Su, Wei-zhen Liang, Yeyin Shi, Lu Gan, Yongsheng Chen, Xin Qiao, Jing Li
https://arxiv.org/abs/2509.18123

Synergizing Static Analysis with Large Language Models for Vulnerability Discovery and beyond
Vaibhav Agrawal, Kiarash Ahi
https://arxiv.org/abs/2509.15433 https://

Synergizing Static Analysis with Large Language Models for Vulnerability Discovery and beyond
This report examines the synergy between Large Language Models (LLMs) and Static Application Security Testing (SAST) to improve vulnerability discovery. Traditional SAST tools, while effective for proactive security, are limited by high false-positive rates and a lack of contextual understanding. Conversely, LLMs excel at code analysis and pattern recognition but can be prone to inconsistencies and hallucinations. By integrating these two technologies, a more intelligent and efficient system is…

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[5/7]:
- CoFFT: Chain of Foresight-Focus Thought for Visual Language Models
Zhang, Dong, Zhang, Jia, Dang, Fernando, Liu, Shou

I am really interested in the linked.art initiative, but I’m finding it hard to wrap my head around it. What strikes me as particularly odd:
* The types-of-types pattern, which creates JSON structures that are very unlike usual JSON properties.
* The AATization of everything, including things like language tags, for which perfectly fine native RDF patterns exist.
Has anyone worked with it? Are there good Getting Started guides?

Man I hate the new language for a task one doesn't want to do — "aversive”.
Primary reason is that it externalizes the problem. It's fixed mindset framing, that something _else_ has to change to make the situation better, that it's the task's fault for being aversive, instead of our own for not working on the aversion to the needed task.
We have a bad habit lately of attributing relational traits to the party in a relationship, rather than to the relationship itself and it weakens our thinking about things. Noticing this pattern really changes how you think, because you can start attributing things better and noticing the contexts — and contexts are often things that can be changed!

My brilliant (almost) 13-year-old is learning about verbal nouns and adjectives in his language studies class
This morning I discovered that he pronounces "gerund" with the stress pattern of "Gerard"* not "Jared"
And now I'm doubting *my own* pronunciation of that word
* His choice is almost certainly influenced by his current favorite rocker Gerard Way

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[2/7]:
- LFTR: Learning-Free Token Reduction for Multimodal Large Language Models
Zihui Zhao, Yingxin Li, Yang Li

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

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

Automating Code Generation for Semiconductor Equipment Control from Developer Utterances with LLMs
Youngkyoung Kim, Sanghyeok Park, Misoo Kim, Gangho Yoon, Eunseok Lee, Simon S. Woo
https://arxiv.org/abs/2509.13055

Automating Code Generation for Semiconductor Equipment Control from Developer Utterances with LLMs
Semiconductors form the backbone of modern electronics, with their manufacturing and testing relying on highly specialized equipment and domain-specific programming languages. Equipment languages such as the Algorithmic Pattern Generator (ALPG) are critical for precise hardware control but are challenging to program due to their low-level syntax and steep learning curve. While large language models (LLMs) have shown promise in generating high-level code from natural language, their effectivenes…

this should keep yous out of trouble for a while :luna_moth: 🎹
#liveCoding

One of the rhythms BC Manjunath, Matt Davies and me will be exploring on the 8th November in Sheffield UK. It's going to be a lot of fun

Finally, what Xia & Lindell call a "separation problem" is, in our view, a feature of our approach and not a bug.
If, e.g., all languages in a family are polysynthetic (or none are), that’s not a statistical artefact – it’s the signal. The outcome is well associated with genealogy, showing that family membership captures someth genuinely informative about the process. When the model finds that family explains a large share of the variance, that's not a failure–it's evidence that phylogenetic structure dominates the pattern.
So while Xia & Lindell insist that "autocorrelation due to relationships and distance cannot be captured in family or regional-level analyses", we see that as an empirical question – and we treated it as one.
The real test is whether a mixed model that explicitly represents phylogeny and geography performs worse than their alternative, where the entire shared history of languages and environments is effectively collapsed into a single dimension (an eigenvector).
In other words: we model relationships – Xia & Lindell summarise them into one number per language.

Language-Instructed Reasoning for Group Activity Detection via Multimodal Large Language Model
Jihua Peng, Qianxiong Xu, Yichen Liu, Chenxi Liu, Cheng Long, Rui Zhao, Ziyue Li
https://arxiv.org/abs/2509.16054

Language-Instructed Reasoning for Group Activity Detection via Multimodal Large Language Model
Group activity detection (GAD) aims to simultaneously identify group members and categorize their collective activities within video sequences. Existing deep learning-based methods develop specialized architectures (e.g., transformer networks) to model the dynamics of individual roles and semantic dependencies between individuals and groups. However, they rely solely on implicit pattern recognition from visual features and struggle with contextual reasoning and explainability. In this work, we …

Reasoning Pattern Matters: Learning to Reason without Human Rationales
Chaoxu Pang, Yixuan Cao, Ping Luo
https://arxiv.org/abs/2510.12643 https://arxiv.org…

Reasoning Pattern Matters: Learning to Reason without Human Rationales
Large Language Models (LLMs) have demonstrated remarkable reasoning capabilities under the widely adopted SFT+RLVR paradigm, which first performs Supervised Fine-Tuning (SFT) on human-annotated reasoning trajectories (rationales) to establish initial reasoning behaviors, then applies Reinforcement Learning with Verifiable Rewards (RLVR) to optimize the model using verifiable signals without golden rationales. However, annotating high-quality rationales for the SFT stage remains prohibitively ex…

Crosslisted article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[1/2]:
- SGAligner : Cross-Modal Language-Aided 3D Scene Graph Alignment
Binod Singh, Sayan Deb Sarkar, Iro Armeni

Poseidon: A OneGraph Engine
Brad Bebee, \"Umit V. \c{C}ataly\"urek, Olaf Hartig, Ankesh Khandelwal, Simone Rondelli, Michael Schmidt, Lefteris Sidirourgos, Bryan Thompson
https://arxiv.org/abs/2510.11166

Poseidon: A OneGraph Engine
We present the Poseidon engine behind the Neptune Analytics graph database service. Customers interact with Poseidon using the declarative openCypher query language, which enables requests that seamlessly combine traditional querying paradigms (such as graph pattern matching, variable length paths, aggregation) with algorithm invocations and has been syntactically extended to facilitate OneGraph interoperability, such as the disambiguation between globally unique IRIs (as exposed via RDF) vs. l…

Talking with Oompa Loompas: A novel framework for evaluating linguistic acquisition of LLM agents
Sankalp Tattwadarshi Swain, Anshika Krishnatray, Dhruv Kumar, Jagat Sesh Challa
https://arxiv.org/abs/2509.07389

Talking with Oompa Loompas: A novel framework for evaluating linguistic acquisition of LLM agents
Existing evaluation studies on linguistic competence of large language models (LLM agents) have focused primarily on vocabulary learning, morphological rule induction, syntactic generalization, pragmatic inference, and cross-linguistic transfer. However, none assess whether LLM agents can acquire a language through pattern recognition and interactive feedback, a central feature of human language acquisition. We propose a novel experimental framework in which an LLM agent is evaluated on its abi…

i made some nice satdee morning tune for yous

Crosslisted article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[2/2]:
- CaTS-Bench: Can Language Models Describe Numeric Time Series?
Luca Zhou, Pratham Yashwante, Marshall Fisher, Alessio Sampieri, Zihao Zhou, Fabio Galasso, Rose Yu

Architecting Resilient LLM Agents: A Guide to Secure Plan-then-Execute Implementations
Ron F. Del Rosario, Klaudia Krawiecka, Christian Schroeder de Witt
https://arxiv.org/abs/2509.08646

Architecting Resilient LLM Agents: A Guide to Secure Plan-then-Execute Implementations
As Large Language Model (LLM) agents become increasingly capable of automating complex, multi-step tasks, the need for robust, secure, and predictable architectural patterns is paramount. This paper provides a comprehensive guide to the ``Plan-then-Execute'' (P-t-E) pattern, an agentic design that separates strategic planning from tactical execution. We explore the foundational principles of P-t-E, detailing its core components - the Planner and the Executor - and its architectural advantages i…

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[4/5]:
- Investigating Traffic Accident Detection Using Multimodal Large Language Models
Ilhan Skender, Kailin Tong, Selim Solmaz, Daniel Watzenig

Understanding Economic Tradeoffs Between Human and AI Agents in Bargaining Games
Crystal Qian, Kehang Zhu, John Horton, Benjamin S. Manning, Vivian Tsai, James Wexler, Nithum Thain
https://arxiv.org/abs/2509.09071

Understanding Economic Tradeoffs Between Human and AI Agents in Bargaining Games
Coordination tasks traditionally performed by humans are increasingly being delegated to autonomous agents. As this pattern progresses, it becomes critical to evaluate not only these agents' performance but also the processes through which they negotiate in dynamic, multi-agent environments. Furthermore, different agents exhibit distinct advantages: traditional statistical agents, such as Bayesian models, may excel under well-specified conditions, whereas large language models (LLMs) can genera…

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[2/8]:
- SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlea...
Chen, Deng, Zheng, Yan, Liu, Wu, Jiang, Liu, Hu

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[8/8]:
- The Better You Learn, The Smarter You Prune: Towards Efficient Vision-language-action Models via ...
Jiang, Jiang, Ma, Wen, Li, Zhan, Jia, Liu, Sun, Lang

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[4/4]:
- Evaluating the Robustness of Open-Source Vision-Language Models to Domain Shift in Object Captioning
Federico Tavella, Amber Drinkwater, Angelo Cangelosi

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[1/5]:
- Video-based Sign Language Recognition without Temporal Segmentation
Jie Huang, Wengang Zhou, Qilin Zhang, Houqiang Li, Weiping Li

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

Crosslisted article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[1/1]:
- Sample-efficient Integration of New Modalities into Large Language Models
Osman Batur \.Ince, Andr\'e F. T. Martins, Oisin Mac Aodha, Edoardo M. Ponti

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[3/7]:
- AutoDrive-QA: A Multiple-Choice Benchmark for Vision-Language Evaluation in Urban Autonomous Driving
Boshra Khalili, Andrew W. Smyth