Tootfinder

reading more about the energia rockets at https://russianspaceweb.com

Free-MAD: Consensus-Free Multi-Agent Debate
Yu Cui, Hang Fu, Haibin Zhang, Licheng Wang, Cong Zuo
https://arxiv.org/abs/2509.11035 https://arxiv.org/pdf/25…

Free-MAD: Consensus-Free Multi-Agent Debate
Multi-agent debate (MAD) is an emerging approach to improving the reasoning capabilities of large language models (LLMs). Existing MAD methods rely on multiple rounds of interaction among agents to reach consensus, and the final output is selected by majority voting in the last round. However, this consensus-based design faces several limitations. First, multiple rounds of communication increases token overhead and limits scalability. Second, due to the inherent conformity of LLMs, agents that …

Aphideater fly (aka hover fly) on a tiny white flower. LA Arboretum, Arcadia, California, USA. October, 2025. #laarboretum #hoverfly #aphideater

SMILE: SeMantic Ids Enhanced CoLd Item Representation for Click-through Rate Prediction in E-commerce SEarch
Qihang Zhao, Zhongbo Sun, Xiaoyang Zheng, Xian Guo, Siyuan Wang, Zihan Liang, Mingcan Peng, Ben Chen, Chenyi Lei
https://arxiv.org/abs/2510.12604

SMILE: SeMantic Ids Enhanced CoLd Item Representation for Click-through Rate Prediction in E-commerce SEarch
With the rise of modern search and recommendation platforms, insufficient collaborative information of cold-start items exacerbates the Matthew effect of existing platform items, challenging platform diversity and becoming a longstanding issue. Existing methods align items' side content with collaborative information to transfer collaborative signals from high-popularity items to cold-start items. However, these methods fail to account for the asymmetry between collaboration and content, nor th…

Chameleon: Taming Dynamic Operator Sequences for Memory-Intensive LLM Training
Zibo Wang, Yuhang Zhou, Zhibin Wang, Shipeng Li, Xinjing Huang, Chendong Cai, Bingxu Mu, Yuqing Sun, Zhiheng Hu, Bin She, Shu You, Guanghuan Fang, Rong Gu, Wanchun Dou, Guihai Chen, Chen Tian
https://arxiv.org/abs/2509.11076…

Chameleon: Taming Dynamic Operator Sequences for Memory-Intensive LLM Training
The increasing size of large language models (LLMs) has led to a surge in memory requirements during training, often exceeding the capacity of high-bandwidth memory (HBM). Swap-based memory optimization incurs neither accuracy loss nor additional end-to-end overhead when effectively overlapped, thus being an attractive solution. However, existing swap methods assume consistent operator sequences, which is impractical in Eager Mode, where operator sequences can vary during change. We propose C…

Went on a fun adventure "fixing" an issue with a Slay the Spire mod. And by "fun" I actually mean fun. Even managed to fix the issue on the first try. However, it was a pain to get everything setup to work on the mod.
https://blog.jamesthebard.net/posts/build-…

VideoAgent: Personalized Synthesis of Scientific Videos
Xiao Liang, Bangxin Li, Zixuan Chen, Hanyue Zheng, Zhi Ma, Di Wang, Cong Tian, Quan Wang
https://arxiv.org/abs/2509.11253

VideoAgent: Personalized Synthesis of Scientific Videos
Automating the generation of scientific videos is a crucial yet challenging task for effective knowledge dissemination. However, existing works on document automation primarily focus on static media such as posters and slides, lacking mechanisms for personalized dynamic orchestration and multimodal content synchronization. To address these challenges, we introduce VideoAgent, a novel multi-agent framework that synthesizes personalized scientific videos through a conversational interface. VideoA…

ALLOY: Generating Reusable Agent Workflows from User Demonstration
Jiawen Li, Zheng Ning, Yuan Tian, Toby Jia-jun Li
https://arxiv.org/abs/2510.10049 https://

ALLOY: Generating Reusable Agent Workflows from User Demonstration
Large language models (LLMs) enable end-users to delegate complex tasks to autonomous agents through natural language. However, prompt-based interaction faces critical limitations: Users often struggle to specify procedural requirements for tasks, especially those that don't have a factually correct solution but instead rely on personal preferences, such as posting social media content or planning a trip. Additionally, a ''successful'' prompt for one task may not be reusable or generalizable ac…

Real-Time RAG for the Identification of Supply Chain Vulnerabilities
Jesse Ponnock, Grace Kenneally, Michael Robert Briggs, Elinor Yeo, Tyrone Patterson III, Nicholas Kinberg, Matthew Kalinowski, David Hechtman
https://arxiv.org/abs/2509.10469

Real-Time RAG for the Identification of Supply Chain Vulnerabilities
New technologies in generative AI can enable deeper analysis into our nation's supply chains but truly informative insights require the continual updating and aggregation of massive data in a timely manner. Large Language Models (LLMs) offer unprecedented analytical opportunities however, their knowledge base is constrained to the models' last training date, rendering these capabilities unusable for organizations whose mission impacts rely on emerging and timely information. This research propo…

ACADREASON: Exploring the Limits of Reasoning Models with Academic Research Problems
Xin Gui, King Zhu, JinCheng Ren, Qianben Chen, Zekun Moore Wang, Yizhi LI, Xinpeng Liu, Xiaowan Li, Wenli Ren, Linyu Miao, Tianrui Qin, Ziqi Shu, He Zhu, Xiangru Tang, Dingfeng Shi, Jiaheng Liu, Yuchen Eleanor Jiang, Minghao Liu, Ge Zhang, Wangchunshu Zhou
https://

ACADREASON: Exploring the Limits of Reasoning Models with Academic Research Problems
In recent years, the research focus of large language models (LLMs) and agents has shifted increasingly from demonstrating novel capabilities to complex reasoning and tackling challenging tasks. However, existing evaluations focus mainly on math/code contests or general tasks, while existing multi-domain academic benchmarks lack sufficient reasoning depth, leaving the field without a rigorous benchmark for high-level reasoning. To fill this gap, we introduce the Acadreason benchmark, designed t…