Tootfinder

ProSEA: Problem Solving via Exploration Agents
William Nguyen, Vinh Luong, Christopher Nguyen
https://arxiv.org/abs/2510.07423 https://arxiv.org/pdf/2510.0…

ProSEA: Problem Solving via Exploration Agents
Large language models (LLMs) have empowered AI agents to tackle increasingly complex tasks. However, most existing agents remain limited to static planning and brittle interactions, falling short of true collaboration or adaptive reasoning. We introduce ProSEA, a modular, general-purpose multi-agent framework designed for iterative problem solving through exploration and plan evolution. ProSEA features a hierarchical architecture in which a Manager Agent orchestrates domain-specialized Expert A…

OpenJAI-v1.0: An Open Thai Large Language Model
Pontakorn Trakuekul, Attapol T. Rutherford, Jullajak Karnjanaekarin, Narongkorn Panitsrisit, Sumana Sumanakul
https://arxiv.org/abs/2510.06847

OpenJAI-v1.0: An Open Thai Large Language Model
We introduce OpenJAI-v1.0, an open-source large language model for Thai and English, developed from the Qwen3-14B model. Our work focuses on boosting performance on practical tasks through carefully curated data across three key use cases: instruction following, long-context understanding, and tool use. Evaluation results show that OpenJAI-v1.0 improves on the capabilities of its base model and outperforms other leading open-source Thai models on a diverse suite of benchmarks, while avoiding ca…

Here’s the lightning sketch of Paul’s Treatise Against Efficiency that I’ve never written:
1. Efficiency is asymptotically inefficient: as costs approach zero, the cost of further reducing them approaches infinity.
2. Efficiency prioritizes the measurable over the difficult-to-measure.
3. Efficiency prioritizes what those in power see (or imagine) over on-the-ground reality.
4. Following from 2 and 3, efficiency reduces the amount and quality of information flowing into a human system.
5. Efficiency foments institutional inflexibility.
6. By removing slack, efficiency causes small failures to cascade more readily and increases the risk of catastrophic failure.
7. Following rom 4, 5, and 6, efficiency trades small costs for massive risks: from failures, from missed opportunities, and from inability to adjust.
8. Efficiency, when pushed, strangles the emergent phenomena that in the long term create all new things of value.
9. Thus, although it can be a by-product of evolution, efficiency as a goal in itself strangles evolution.
10. Efficiency as a goal strangles joy.

Evolution of spin excitations in superconducting La$_{2-x}$Ca$_{x}$CuO$_{4-\delta}$ from the underdoped to the heavily overdoped regime
S. Hameed, Y. Liu, M. Knauft, K. S. Rabinovich, G. Kim, G. Christiani, G. Logvenov, F. Yakhou-Harris, A. V. Boris, B. Keimer, M. Minola
https://arxiv.org/abs/2509.06680

Evolution of spin excitations in superconducting La$_{2-x}$Ca$_{x}$CuO$_{4-δ}$ from the underdoped to the heavily overdoped regime
We investigate high-energy spin excitations in hole-doped La$_{2-x}$Ca$_{x}$CuO$_{4-δ}$ films across a broad Ca doping range $x = 0.05-0.50$ using resonant inelastic x-ray scattering (RIXS). Polarization analysis and incident-photon energy detuning measurements confirm the persistence of collective paramagnon excitations up to $x = 0.50$. Consistent with previous studies on other cuprate families, we observe a pronounced crossover near $x = 0.15$, where paramagnon spectral weight is transferre…

First Measurement of Neutrino Emissions from Spent Nuclear Fuel by the Double Chooz Experiment
Double Chooz Collaboration, T. Abrah\~ao, H. Almazan, J. C. dos Anjos, S. Appel, J. C. Barriere, I. Bekman, T. J. C. Bezerra, L. Bezrukov, E. Blucher, C. Bourgeois, C. Buck, J. Busenitz, A. Cabrera, M. Cerrada, E. Chauveau, P. Chimenti, O. Corpace, J. V. Dawson, J. F. Du, Z. Djurcic, A. Etenko, H. Furuta, I. Gil-Botella, A. Givaudan, H. Gomez, M. C. Goodman, T. Hara, J. Haser, D. Hellwig, A. …

First Measurement of Neutrino Emissions from Spent Nuclear Fuel by the Double Chooz Experiment
Neutrino emission from nuclear reactors provides real-time insights into reactor power and fuel evolution, with potential applications in monitoring and nuclear safeguards. Following reactor shutdown, a low-intensity flux of ``residual neutrinos'' persists due to the decay of long-lived fission isotopes in the partially burnt fuel remaining within the reactor cores and in spent nuclear fuel stored in nearby cooling pools. The Double Chooz experiment at the Chooz B nuclear power plant in France …

We've reached the point in the evolution of cyber scamming where military units are blowing up buildings to stop the digital crimes.
Stragglers from Myanmar scam center raided by army cross into Thailand as buildings are blown up
https://apnews.com/artic…

Stragglers from Myanmar scam center raided by army cross into Thailand as buildings are blown up
A Thai regional army commander say that the number of people fleeing from Myanmar to Thailand after Myanmar’s military shut down a major online scam center has slowed to a trickle. The news on Tuesday came after more than 1,500 people had left in the past week. The KK Park site was identified by Thai officials and independent experts as housing a major cybercrime operation. It was raided by Myanmar’s army in mid-October as part of operations starting in early September to suppress cross-bor…

Evolution of quasiparticle edge states with Hubbard interaction in Rice-Mele chain
Jyoti Bisht, Brijesh Kumar
https://arxiv.org/abs/2508.21008 https://arxi…

Evolution of quasiparticle edge states with Hubbard interaction in Rice-Mele chain
We study the behaviour of edge states in Rice-Mele model with Hubbard interaction, U , at half-filling using density matrix renormalization group, exact diagonalization and effective charge dynamics in Kumar representation. For a fixed dimerization, $δ$, and staggered potential, V , we find by increasing U the quasiparticle edge states in the charge gap to come down in energy from V in the absence of Hubbard interaction to zero energy for U $\approx$ 2V . This presents an uncommon case where r…

High temporal stability of niobium superconducting resonators by surface passivation with organophosphonate self-assembled monolayers
Harsh Gupta, Rui Pereira, Leon Koch, Niklas Bruckmoser, Moritz Singer, Benedikt Schoof, Manuel Kompatscher, Stefan Filipp, Marc Tornow
https://arxiv.org/abs/2508.15957…

High temporal stability of niobium superconducting resonators by surface passivation with organophosphonate self-assembled monolayers
One main limiting factor towards achieving high coherence times in superconducting circuits is two level system (TLS) losses. Mitigating such losses requires controlling the formation of native oxides at the metal-air interface. Here, we report the growth of alkyl-phosphonate self-assembled monolayers (SAMs) on Nb thin films following oxide removal. The impact of passivation was evaluated via the performance of coplanar waveguide resonators at 10mK, in terms of quality factor and resonant frequ…

Geometric Analysis of Magnetic Labyrinthine Stripe Evolution via U-Net Segmentation
Vin\'icius Yu Okubo, Kotaro Shimizu, B. S. Shivaran, Gia-Wei Chern, Hae Yong Kim
https://arxiv.org/abs/2509.11485

Geometric Analysis of Magnetic Labyrinthine Stripe Evolution via U-Net Segmentation
Labyrinthine stripe patterns are common in many physical systems, yet their lack of long-range order makes quantitative characterization challenging. We investigate the evolution of such patterns in bismuth-doped yttrium iron garnet (Bi:YIG) films subjected to a magnetic field annealing protocol. A U-Net deep learning model, trained with synthetic degradations including additive white Gaussian and Simplex noise, enables robust segmentation of experimental magneto-optical images despite noise an…

Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs
Mario Sanz-Guerrero, Minh Duc Bui, Katharina von der Wense
https://arxiv.org/abs/2509.15020

Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMs
When evaluating large language models (LLMs) with multiple-choice question answering (MCQA), it is common to end the prompt with the string "Answer:" to facilitate automated answer extraction via next-token probabilities. However, there is no consensus on how to tokenize the space following the colon, often overlooked as a trivial choice. In this paper, we uncover accuracy differences of up to 11% due to this (seemingly irrelevant) tokenization variation as well as reshuffled model rankings, ra…