Tootfinder

AgriEval: A Comprehensive Chinese Agricultural Benchmark for Large Language Models
Lian Yan, Haotian Wang, Chen Tang, Haifeng Liu, Tianyang Sun, Liangliang Liu, Yi Guan, Jingchi Jiang
https://arxiv.org/abs/2507.21773

AgriEval: A Comprehensive Chinese Agricultural Benchmark for Large Language Models
In the agricultural domain, the deployment of large language models (LLMs) is hindered by the lack of training data and evaluation benchmarks. To mitigate this issue, we propose AgriEval, the first comprehensive Chinese agricultural benchmark with three main characteristics: (1) Comprehensive Capability Evaluation. AgriEval covers six major agriculture categories and 29 subcategories within agriculture, addressing four core cognitive scenarios: memorization, understanding, inference, and genera…

Iterative Methods for the Projected Solutions of Quasi-equilibrium Problems
Didier Aussel, Jauny, Asrifa Sultana, Shivani Valecha
https://arxiv.org/abs/2506.22080

Iterative Methods for the Projected Solutions of Quasi-equilibrium Problems
Aussel et al. (J Optim Theory Appl 170 818-837 2016) introduced the concept of projected solutions for the quasi-variational inequalities with a non-self constraint map, that is, the case where the constraint map may take values outside the feasible set. This paper presents two iterative methods to determine the projected solutions for quasi-equilibrium problems (QEP). We prove the convergence of the sequence generated by iterative methods to a projected solution of the QEP under some suitable …

Foundations for Energy-Aware Zero-Energy Devices: From Energy Sensing to Adaptive Protocols
Onel L. A. L\'opez, Mateen Ashraf, Samer Nasser, Gabriel M. de Jesus, Ritesh Kumar Singh, Miltiadis C. Filippou, Jeroen Famaey
https://arxiv.org/abs/2507.22740

Foundations for Energy-Aware Zero-Energy Devices: From Energy Sensing to Adaptive Protocols
Zero-energy devices (ZEDs) are key enablers of sustainable Internet of Things networks by operating solely on harvested ambient energy. Their limited and dynamic energy budget calls for protocols that are energy-aware and intelligently adaptive. However, designing effective energy-aware protocols for ZEDs requires theoretical models that realistically reflect device constraints. Indeed, existing approaches often oversimplify key aspects such as energy information (EI) acquisition, task-level va…

The Xeno Sutra: Can Meaning and Value be Ascribed to an AI-Generated "Sacred" Text?
Murray Shanahan, Tara Das, Robert Thurman
https://arxiv.org/abs/2507.20525 https://…

The Xeno Sutra: Can Meaning and Value be Ascribed to an AI-Generated "Sacred" Text?
This paper presents a case study in the use of a large language model to generate a fictional Buddhist "sutr"', and offers a detailed analysis of the resulting text from a philosophical and literary point of view. The conceptual subtlety, rich imagery, and density of allusion found in the text make it hard to causally dismiss on account of its mechanistic origin. This raises questions about how we, as a society, should come to terms with the potentially unsettling possibility of a technology th…

Physics of the gluon mass gap
Mauricio N. Ferreira, Joannis Papavassiliou, Jan M. Pawlowski, Nicolas Wink
https://arxiv.org/abs/2508.20568 https://arxiv.or…

Physics of the gluon mass gap
It has long been known that the gluon propagator in Landau-gauge QCD exhibits a mass gap; and its emergence has been ascribed to the action of the Schwinger mechanism in the gauge sector of QCD. In the present work, we relate this property to the physical mass gap of QCD by considering two observables associated with confinement and chiral symmetry breaking, namely the confinement-deconfinement transition temperature and the pion decay constant, respectively. It turns out that the first observa…

Sycophancy as compositions of Atomic Psychometric Traits
Shreyans Jain, Alexandra Yost, Amirali Abdullah
https://arxiv.org/abs/2508.19316 https://arxiv.org…

Sycophancy as compositions of Atomic Psychometric Traits
Sycophancy is a key behavioral risk in LLMs, yet is often treated as an isolated failure mode that occurs via a single causal mechanism. We instead propose modeling it as geometric and causal compositions of psychometric traits such as emotionality, openness, and agreeableness - similar to factor decomposition in psychometrics. Using Contrastive Activation Addition (CAA), we map activation directions to these factors and study how different combinations may give rise to sycophancy (e.g., high e…

Learning Real-World Acrobatic Flight from Human Preferences
Colin Merk, Ismail Geles, Jiaxu Xing, Angel Romero, Giorgia Ramponi, Davide Scaramuzza
https://arxiv.org/abs/2508.18817

Learning Real-World Acrobatic Flight from Human Preferences
Preference-based reinforcement learning (PbRL) enables agents to learn control policies without requiring manually designed reward functions, making it well-suited for tasks where objectives are difficult to formalize or inherently subjective. Acrobatic flight poses a particularly challenging problem due to its complex dynamics, rapid movements, and the importance of precise execution. In this work, we explore the use of PbRL for agile drone control, focusing on the execution of dynamic maneuve…

Collective communication in a transparent world: Phase transitions in a many-body Potts model and social-quantum duality
Pawat Akarapipattana, Sergei Nechaev, Bogdan Slavov
https://arxiv.org/abs/2508.20267

Collective communication in a transparent world: Phase transitions in a many-body Potts model and social-quantum duality
We consider the Schelling-like social competition reflected in "dynamics of opinions" among groups of agents ("communities") in a highly transparent world. Specifically, we investigate a $q$-state Potts spin system with competing two- and three-body interactions on a complete graph. Agents interact through pairwise repulsion (opposing opinions) between different communities and three-body attraction (shared opinions) within the same community. In the thermodynamic limit, we identify variants of…

Signs of Struggle: Spotting Cognitive Distortions across Language and Register
Abhishek Kuber, Enrico Liscio, Ruixuan Zhang, Caroline Figueroa, Pradeep K. Murukannaiah
https://arxiv.org/abs/2508.20771 …

Signs of Struggle: Spotting Cognitive Distortions across Language and Register
Rising mental health issues among youth have increased interest in automated approaches for detecting early signs of psychological distress in digital text. One key focus is the identification of cognitive distortions, irrational thought patterns that have a role in aggravating mental distress. Early detection of these distortions may enable timely, low-cost interventions. While prior work has focused on English clinical data, we present the first in-depth study of cross-lingual and cross-regis…

Languages Still Left Behind: Toward a Better Multilingual Machine Translation Benchmark
Chihiro Taguchi, Seng Mai, Keita Kurabe, Yusuke Sakai, Georgina Agyei, Soudabeh Eslami, David Chiang
https://arxiv.org/abs/2508.20511

Languages Still Left Behind: Toward a Better Multilingual Machine Translation Benchmark
Multilingual machine translation (MT) benchmarks play a central role in evaluating the capabilities of modern MT systems. Among them, the FLORES+ benchmark is widely used, offering English-to-many translation data for over 200 languages, curated with strict quality control protocols. However, we study data in four languages (Asante Twi, Japanese, Jinghpaw, and South Azerbaijani) and uncover critical shortcomings in the benchmark's suitability for truly multilingual evaluation. Human assessments…