Tootfinder

ParaCook: On Time-Efficient Planning for Multi-Agent Systems
Shiqi Zhang, Xinbei Ma, Yunqing Xu, Zouying Cao, Pengrui Lu, Haobo Yuan, Tiancheng Shen, Zhuosheng Zhang, Hai Zhao, Ming-Hsuan Yang
https://arxiv.org/abs/2510.11608

ParaCook: On Time-Efficient Planning for Multi-Agent Systems
Large Language Models (LLMs) exhibit strong reasoning abilities for planning long-horizon, real-world tasks, yet existing agent benchmarks focus on task completion while neglecting time efficiency in parallel and asynchronous operations. To address this, we present ParaCook, a benchmark for time-efficient collaborative planning. Inspired by the Overcooked game, ParaCook provides an environment for various challenging interaction planning of multi-agent systems that are instantiated as cooking t…

ExpVid: A Benchmark for Experiment Video Understanding & Reasoning
Yicheng Xu, Yue Wu, Jiashuo Yu, Ziang Yan, Tianxiang Jiang, Yinan He, Qingsong Zhao, Kai Chen, Yu Qiao, Limin Wang, Manabu Okumura, Yi Wang
https://arxiv.org/abs/2510.11606

ExpVid: A Benchmark for Experiment Video Understanding & Reasoning
Multimodal Large Language Models (MLLMs) hold promise for accelerating scientific discovery by interpreting complex experimental procedures. However, their true capabilities are poorly understood, as existing benchmarks neglect the fine-grained and long-horizon nature of authentic laboratory work, especially in wet-lab settings. To bridge this gap, we introduce ExpVid, the first benchmark designed to systematically evaluate MLLMs on scientific experiment videos. Curated from peer-reviewed video…

VeilAudit: Breaking the Deadlock Between Privacy and Accountability Across Blockchains
Minhao Qiao, Iqbal Gondal, Hai Dong
https://arxiv.org/abs/2510.12153 https://

VeilAudit: Breaking the Deadlock Between Privacy and Accountability Across Blockchains
Cross chain interoperability in blockchain systems exposes a fundamental tension between user privacy and regulatory accountability. Existing solutions enforce an all or nothing choice between full anonymity and mandatory identity disclosure, which limits adoption in regulated financial settings. We present VeilAudit, a cross chain auditing framework that introduces Auditor Only Linkability, which allows auditors to link transaction behaviors that originate from the same anonymous entity withou…

Imagine thinking now is the time to remove a protection on freedom of speech on the internet.
https://bsky.app/profile/judiciarydems.senate.gov/post/3m7sjbvhbms2z

Senate Judiciary Democrats 🇺🇸 (@judiciarydems.senate.gov)
Sen. WHITEHOUSE: We finally are moving to file a bipartisan Section 230 repeal bill. Waiting any longer serves no useful purpose.

The International Max Planck Research School for Solar System Science becomes a permanent institution in Göttingen and Braunschweig
The Solar System School, the joint graduate school of the Max Planck Institute for Solar System Research, the University of Göttingen, and the Technical University of Braunschweig, is now a permanent fixture in doctoral training in Göttingen and Braunschweig. The Max Planck Society will continue the International Max Planck Research School for Solar Syste…

Semihard interactions at TeV energies
T. V. Iser, E. G. S. Luna
https://arxiv.org/abs/2510.08963 https://arxiv.org/pdf/2510.08963

Semihard interactions at TeV energies
We investigate the high-energy behavior of the total cross section, $σ_{\text{tot}}$, and the ratio of the real to imaginary parts of the scattering amplitude, $ρ$, in both proton-proton and antiproton-proton channels. Our analysis is based on a QCD-inspired model in which the rise of the cross sections is predominantly driven by semihard processes involving gluons. We address the tension between measurements from the ATLAS/ALFA and TOTEM Collaborations, showing that independent analyses of t…

Learning to Guarantee Type Correctness in Code Generation through Type-Guided Program Synthesis
Zhechong Huang, Zhao Zhang, Ruyi Ji, Tingxuan Xia, Qihao Zhu, Qinxiang Cao, Zeyu Sun, Yingfei Xiong
https://arxiv.org/abs/2510.10216

Learning to Guarantee Type Correctness in Code Generation through Type-Guided Program Synthesis
Language models have shown remarkable proficiency in code generation; nevertheless, ensuring type correctness remains a challenge. Although traditional methods, such as constrained decoding, alleviate this problem by externally rejecting untypable code, the model itself does not effectively learn type reasoning internally, which ultimately limits its overall performance. This paper introduces TyFlow, a novel system that internalizes type reasoning within code generation to guide the model to le…

SocioBench: Modeling Human Behavior in Sociological Surveys with Large Language Models
Jia Wang, Ziyu Zhao, Tingjuntao Ni, Zhongyu Wei
https://arxiv.org/abs/2510.11131 https://

SocioBench: Modeling Human Behavior in Sociological Surveys with Large Language Models
Large language models (LLMs) show strong potential for simulating human social behaviors and interactions, yet lack large-scale, systematically constructed benchmarks for evaluating their alignment with real-world social attitudes. To bridge this gap, we introduce SocioBench-a comprehensive benchmark derived from the annually collected, standardized survey data of the International Social Survey Programme (ISSP). The benchmark aggregates over 480,000 real respondent records from more than 30 co…

A Faster Randomized Algorithm for Vertex Cover: An Automated Approach
Katie Clinch, Serge Gaspers, Tao Zixu He, Simon Mackenzie, Tiankuang Zhang
https://arxiv.org/abs/2510.09027

A Faster Randomized Algorithm for Vertex Cover: An Automated Approach
This work introduces two techniques for the design and analysis of branching algorithms, illustrated through the case study of the Vertex Cover problem. First, we present a method for automatically generating branching rules through a systematic case analysis of local structures. Second, we develop a new technique for analyzing randomized branching algorithms using the Measure & Conquer method, offering greater flexibility in formulating branching rules. By combining these innovations with addi…

FATHOMS-RAG: A Framework for the Assessment of Thinking and Observation in Multimodal Systems that use Retrieval Augmented Generation
Samuel Hildebrand (Louisiana State University), Curtis Taylor (Oak Ridge National Lab), Sean Oesch (Oak Ridge National Lab), James M Ghawaly Jr (Louisiana State University), Amir Sadovnik (Oak Ridge National Lab), Ryan Shivers (Oak Ridge National Lab), Brandon Schreiber (Oak Ridge National Lab), Kevin Kurian (University of Florida)

FATHOMS-RAG: A Framework for the Assessment of Thinking and Observation in Multimodal Systems that use Retrieval Augmented Generation
Retrieval-augmented generation (RAG) has emerged as a promising paradigm for improving factual accuracy in large language models (LLMs). We introduce a benchmark designed to evaluate RAG pipelines as a whole, evaluating a pipeline's ability to ingest, retrieve, and reason about several modalities of information, differentiating it from existing benchmarks that focus on particular aspects such as retrieval. We present (1) a small, human-created dataset of 93 questions designed to evaluate a pipe…