Tootfinder

OdysseyBench: Evaluating LLM Agents on Long-Horizon Complex Office Application Workflows
Weixuan Wang, Dongge Han, Daniel Madrigal Diaz, Jin Xu, Victor R\"uhle, Saravan Rajmohan
https://arxiv.org/abs/2508.09124

OdysseyBench: Evaluating LLM Agents on Long-Horizon Complex Office Application Workflows
Autonomous agents powered by large language models (LLMs) are increasingly deployed in real-world applications requiring complex, long-horizon workflows. However, existing benchmarks predominantly focus on atomic tasks that are self-contained and independent, failing to capture the long-term contextual dependencies and multi-interaction coordination required in realistic scenarios. To address this gap, we introduce OdysseyBench, a comprehensive benchmark for evaluating LLM agents on long-horizo…

ODYSSEY: Open-World Quadrupeds Exploration and Manipulation for Long-Horizon Tasks
Kaijun Wang, Liqin Lu, Mingyu Liu, Jianuo Jiang, Zeju Li, Bolin Zhang, Wancai Zheng, Xinyi Yu, Hao Chen, Chunhua Shen
https://arxiv.org/abs/2508.08240

ODYSSEY: Open-World Quadrupeds Exploration and Manipulation for Long-Horizon Tasks
Language-guided long-horizon mobile manipulation has long been a grand challenge in embodied semantic reasoning, generalizable manipulation, and adaptive locomotion. Three fundamental limitations hinder progress: First, although large language models have improved spatial reasoning and task planning through semantic priors, existing implementations remain confined to tabletop scenarios, failing to address the constrained perception and limited actuation ranges of mobile platforms. Second, curre…

Mediator-Guided Multi-Agent Collaboration among Open-Source Models for Medical Decision-Making
Kaitao Chen, Mianxin Liu, Daoming Zong, Chaoyue Ding, Shaohao Rui, Yankai Jiang, Mu Zhou, Xiaosong Wang
https://arxiv.org/abs/2508.05996

Mediator-Guided Multi-Agent Collaboration among Open-Source Models for Medical Decision-Making
Complex medical decision-making involves cooperative workflows operated by different clinicians. Designing AI multi-agent systems can expedite and augment human-level clinical decision-making. Existing multi-agent researches primarily focus on language-only tasks, yet their extension to multimodal scenarios remains challenging. A blind combination of diverse vision-language models (VLMs) can amplify an erroneous outcome interpretation. VLMs in general are less capable in instruction following a…

Testing new-physics scenarios with the combined LHAASO and Carpet-3 fluence spectrum of GRB 221009A: axion-like particles and Lorentz-invariance violation
P. S. Satunin, S. V. Troitsky
https://arxiv.org/abs/2510.07234

Testing new-physics scenarios with the combined LHAASO and Carpet-3 fluence spectrum of GRB 221009A: axion-like particles and Lorentz-invariance violation
From gamma-ray burst (GRB) 221009A, very high-energy photons were detected: >10 TeV with LHAASO and >100 TeV with Carpet-3. Such energetic photons are expected to be absorbed via electron-positron pair production on their way to the Earth. Their observation might be explained by new physics, including Lorentz invariance violation (LIV) or photon mixing with axion-like particles (ALPs). Here, we construct a joint fluence spectrum by combining flux measurements from both experiments, and fit it u…

ScamAgents: How AI Agents Can Simulate Human-Level Scam Calls
Sanket Badhe
https://arxiv.org/abs/2508.06457 https://arxiv.org/pdf/2508.06457

ScamAgents: How AI Agents Can Simulate Human-Level Scam Calls
Large Language Models (LLMs) have demonstrated impressive fluency and reasoning capabilities, but their potential for misuse has raised growing concern. In this paper, we present ScamAgent, an autonomous multi-turn agent built on top of LLMs, capable of generating highly realistic scam call scripts that simulate real-world fraud scenarios. Unlike prior work focused on single-shot prompt misuse, ScamAgent maintains dialogue memory, adapts dynamically to simulated user responses, and employs dece…

SciVideoBench: Benchmarking Scientific Video Reasoning in Large Multimodal Models
Andong Deng, Taojiannan Yang, Shoubin Yu, Lincoln Spencer, Mohit Bansal, Chen Chen, Serena Yeung-Levy, Xiaohan Wang
https://arxiv.org/abs/2510.08559

SciVideoBench: Benchmarking Scientific Video Reasoning in Large Multimodal Models
Large Multimodal Models (LMMs) have achieved remarkable progress across various capabilities; however, complex video reasoning in the scientific domain remains a significant and challenging frontier. Current video benchmarks predominantly target general scenarios where perception/recognition is heavily relied on, while with relatively simple reasoning tasks, leading to saturation and thus failing to effectively evaluate advanced multimodal cognitive skills. To address this critical gap, we intr…

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…

Just finished "Sinners".
Have a feeling it's going to stay with me for a while. Anyone who says "cinema" is dying is digging in the wrong place.
https://www.themoviedb.org/movie/1233413-sinners

Sinners
Trying to leave their troubled lives behind, twin brothers return to their hometown to start again, only to discover that an even greater evil is waiting to welcome them back.

R-Horizon: How Far Can Your Large Reasoning Model Really Go in Breadth and Depth?
Yi Lu, Jianing Wang, Linsen Guo, Wei He, Hongyin Tang, Tao Gui, Xuanjing Huang, Xuezhi Cao, Wei Wang, Xunliang Cai
https://arxiv.org/abs/2510.08189

R-Horizon: How Far Can Your Large Reasoning Model Really Go in Breadth and Depth?
Recent trends in test-time scaling for reasoning models (e.g., OpenAI o1, DeepSeek-R1) have led to remarkable improvements through long Chain-of-Thought (CoT). However, existing benchmarks mainly focus on immediate, single-horizon tasks, failing to adequately evaluate models' ability to understand and respond to complex, long-horizon scenarios. To address this incomplete evaluation of Large Reasoning Models (LRMs), we propose R-HORIZON, a method designed to stimulate long-horizon reasoning beha…

DACIP-RC: Domain Adaptive Continual Instruction Pre-Training via Reading Comprehension on Business Conversations
Elena Khasanova, Harsh Saini, Md Tahmid Rahman Laskar, Xue-Yong Fu, Cheng Chen, Shashi Bhushan TN
https://arxiv.org/abs/2510.08152

DACIP-RC: Domain Adaptive Continual Instruction Pre-Training via Reading Comprehension on Business Conversations
The rapid advancements in Large Language Models (LLMs) have enabled their adoption in real-world industrial scenarios for various natural language processing tasks. However, the high inference cost of large-scale LLMs makes their deployment impractical, necessitating the use of smaller models. Despite their efficiency, smaller LLMs lack robust zero-shot instruction-following capabilities across diverse domains, limiting their adaptability to dynamic user requirements. Traditional fine-tuning ap…