Tootfinder

Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management
Miao Lu, Weiwei Sun, Weihua Du, Zhan Ling, Xuesong Yao, Kang Liu, Jiecao Chen
https://arxiv.org/abs/2510.06727

Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management
We study reinforcement learning (RL) fine-tuning of large language model (LLM) agents for long-horizon multi-turn tool use, where context length quickly becomes a fundamental bottleneck. Existing RL pipelines can suffer from degraded instruction following, excessive rollout costs, and most importantly, strict context limits. To address these challenges, we introduce summarization-based context management to training. In specific, it periodically compresses the tool using history by LLM-generate…

Origin of persistent photoconductivity in surface conducting hydrogenated diamond films
N. Mohasin Sulthana, K. Ganesan, P. K. Ajikumar
https://arxiv.org/abs/2507.06559

Origin of persistent photoconductivity in surface conducting hydrogenated diamond films
The p-type surface conductivity of hydrogen-terminated diamond (HD) has opened up new possibilities for the development of diamond-based electronic devices. However, the origin of the persistent photoconductivity (PPC) observed in surface-conducting HD remains unclear, an understanding that is crucial for advancing HD-based optoelectronic technologies. In this study, we investigate the underlying mechanism of PPC in surface-conducting HD films. A systematic analysis was performed by tuning the …

Chemotaxis Models with Nonlinear/Porous Medium Diffusion, Consumption, and Logistic source on $\mathbb{R}^N$: I. Global Solvability and Boundedness
Zulaihat Hassan, Wenxian Shen, Yuming Paul Zhang
https://arxiv.org/abs/2509.05494

Chemotaxis Models with Nonlinear/Porous Medium Diffusion, Consumption, and Logistic source on $\mathbb{R}^N$: I. Global Solvability and Boundedness
This series of papers is concerned with the global solvability, boundedness, regularity, and uniqueness of weak solutions to the following parabolic-parabolic chemotaxis system with a logistic source and chemical consumption: \begin{equation*} \begin{cases} u_t = m\nabla\cdot \left((\eps+u)^{m-1}\nabla u\right) - χ\nabla \cdot (u \nabla v) + u(a - b u), & \text{ in } (0,\infty)\times\mathbb{R}^N, \\ v_t = Δv - uv, & \text{ in } (0,\infty)\times\mathbb{R}^N, \end{cases} \end{equation*} where $…

Water Demand Forecasting of District Metered Areas through Learned Consumer Representations
Adithya Ramachandran, Thorkil Flensmark B. Neergaard, Tom\'as Arias-Vergara, Andreas Maier, Siming Bayer
https://arxiv.org/abs/2509.07515

Water Demand Forecasting of District Metered Areas through Learned Consumer Representations
Advancements in smart metering technologies have significantly improved the ability to monitor and manage water utilities. In the context of increasing uncertainty due to climate change, securing water resources and supply has emerged as an urgent global issue with extensive socioeconomic ramifications. Hourly consumption data from end-users have yielded substantial insights for projecting demand across regions characterized by diverse consumption patterns. Nevertheless, the prediction of water…

Dispersed multi-walled carbon nanotubes in polyvinyl butyral matrix for transparent ionic conductive films
Mykola O. Semenenko, Sergii O. Kravchenko, Nadiia V. Siharova, Olha V. Pylypova, Mariya I. Terets, Oleksandr S. Pylypchuk, Mariia V. Voitovych, Tetiana Yu. Obukhova, Taisiia O. Kuzmenko, Andrey Sarikov
https://arxiv.org/abs/2509.07584…

Dispersed multi-walled carbon nanotubes in polyvinyl butyral matrix for transparent ionic conductive films
In this work, we develop methods for increasing the dispersion degree of agglomerated multiwalled carbon nanotubes with subsequent introduction of them into polyvinyl butyral to create transparent conductive films. The influence of proton and a-proton solvents in combination with potassium triiodide (KI3) as a redox component for oxidation of the multiwalled carbon nanotubes surface, which reduces agglomeration due to electrostatic repulsion, is investigated. It is demonstrated that a-proton so…

An Enactivist Approach to Human-Computer Interaction: Bridging the Gap Between Human Agency and Affordances
Angjelin Hila
https://arxiv.org/abs/2509.07871 https://

An Enactivist Approach to Human-Computer Interaction: Bridging the Gap Between Human Agency and Affordances
Emerging paradigms in XR, AI, and BCI contexts necessitate novel theoretical frameworks for understanding human autonomy and agency in HCI. Drawing from enactivist theories of cognition, we conceptualize human agents as self-organizing, operationally closed systems that actively enact their cognitive domains through dynamic interaction with their environments. To develop measurable variables aligned with this framework, we introduce "feelings of agency" (FoA) as an alternative to the establishe…

sp_high_school_new: High school dynamic contacts (2011-2012)
These datasets contain the temporal network of contacts between students in a high school in Marseilles, France. The first dataset gives the contacts of the students of three classes during 4 days in Dec. 2011, and the second corresponds to the contacts of the students of 5 classes during 7 days (from a Monday to the Tuesday of the following week) in Nov. 2012.
This network has 126 nodes and 28561 edges.
Tags: Soc…

Factuality Beyond Coherence: Evaluating LLM Watermarking Methods for Medical Texts
Rochana Prih Hastuti, Rian Adam Rajagede, Mansour Al Ghanim, Mengxin Zheng, Qian Lou
https://arxiv.org/abs/2509.07755 …

Factuality Beyond Coherence: Evaluating LLM Watermarking Methods for Medical Texts
As large language models (LLMs) adapted to sensitive domains such as medicine, their fluency raises safety risks, particularly regarding provenance and accountability. Watermarking embeds detectable patterns to mitigate these risks, yet its reliability in medical contexts remains untested. Existing benchmarks focus on detection-quality tradeoffs, overlooking factual risks under low-entropy settings often exploited by watermarking's reweighting strategy. We propose a medical-focused evaluation w…

Dual Knowledge-Enhanced Two-Stage Reasoner for Multimodal Dialog Systems
Xiaolin Chen, Xuemeng Song, Haokun Wen, Weili Guan, Xiangyu Zhao, Liqiang Nie
https://arxiv.org/abs/2509.07817

Dual Knowledge-Enhanced Two-Stage Reasoner for Multimodal Dialog Systems
Textual response generation is pivotal for multimodal \mbox{task-oriented} dialog systems, which aims to generate proper textual responses based on the multimodal context. While existing efforts have demonstrated remarkable progress, there still exist the following limitations: 1) \textit{neglect of unstructured review knowledge} and 2) \textit{underutilization of large language models (LLMs)}. Inspired by this, we aim to fully utilize dual knowledge (\textit{i.e., } structured attribute and un…

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…