Tootfinder

A Practitioner's Guide to Multi-turn Agentic Reinforcement Learning
Ruiyi Wang, Prithviraj Ammanabrolu
https://arxiv.org/abs/2510.01132 https://arxiv.o…

A Practitioner's Guide to Multi-turn Agentic Reinforcement Learning
We study what actually works and what doesn't for training large language models as agents via multi-turn reinforcement learning. Despite rapid progress, existing frameworks and definitions are fragmented, and there is no systematic formulation or analysis of which design choices matter across tasks. We address this gap by first breaking down the design space into three inter-related pillars -- environment, reward, and policy -- and empirically derive a recipe for training LLM agents in situate…

KeySG: Hierarchical Keyframe-Based 3D Scene Graphs
Abdelrhman Werby, Dennis Rotondi, Fabio Scaparro, Kai O. Arras
https://arxiv.org/abs/2510.01049 https://…

KeySG: Hierarchical Keyframe-Based 3D Scene Graphs
In recent years, 3D scene graphs have emerged as a powerful world representation, offering both geometric accuracy and semantic richness. Combining 3D scene graphs with large language models enables robots to reason, plan, and navigate in complex human-centered environments. However, current approaches for constructing 3D scene graphs are semantically limited to a predefined set of relationships, and their serialization in large environments can easily exceed an LLM's context window. We introdu…

Sources: ByteDance plans to spend about $14B on Nvidia's AI chips in 2026, an increase of about 18% from 2025 (Wency Chen/South China Morning Post)
https://www.scmp.com/tech/big-tech/article/3338191/bytedance-pour-u…

Exclusive | ByteDance to pour US$14 billion into Nvidia chips in 2026 as AI demand surges
Chinese unicorn’s computing needs have climbed across its portfolio of popular apps, cloud unit Volcano Engine and large language models.

Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards
Yiran Shen, Yu Xia, Jonathan Chang, Prithviraj Ammanabrolu
https://arxiv.org/abs/2510.01167 h…

Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards
Aligning large language models to human preferences is inherently multidimensional, yet most pipelines collapse heterogeneous signals into a single optimizeable objective. We seek to answer what it would take to simultaneously align a model across various domains spanning those with: verifiable rewards (mathematical accuracy), non-verifiable subjective preferences (human values), and complex interactive scenarios (multi-turn AI tutoring dialogues). Such multi-objective reinforcement learning se…

While testing some new misp-modules, such as the OpenAPI interface, I discovered a strange behavior in Firefox when trying to reach TCP port 6666, which is the default port used by misp-modules.
It seems Firefox blocks access to a predefined list of TCP ports, and this has been in place for quite some time, as you can see in the commit log.
If you want to override the blocked port list, there is an obscure setting called network.security.ports.banned.override.
…

LinguaSim: Interactive Multi-Vehicle Testing Scenario Generation via Natural Language Instruction Based on Large Language Models
Qingyuan Shi, Qingwen Meng, Hao Cheng, Qing Xu, Jianqiang Wang
https://arxiv.org/abs/2510.08046

LinguaSim: Interactive Multi-Vehicle Testing Scenario Generation via Natural Language Instruction Based on Large Language Models
The generation of testing and training scenarios for autonomous vehicles has drawn significant attention. While Large Language Models (LLMs) have enabled new scenario generation methods, current methods struggle to balance command adherence accuracy with the realism of real-world driving environments. To reduce scenario description complexity, these methods often compromise realism by limiting scenarios to 2D, or open-loop simulations where background vehicles follow predefined, non-interactive…

Roadmap: Emerging Platforms and Applications of Optical Frequency Combs and Dissipative Solitons
Dmitry Skryabin, Arne Kordts, Richard Zeltner, Ronald Holzwarth, Victor Torres-Company, Tobias Herr, Fuchuan Lei, Qi-Fan Yang, Camille-Sophie Br\`es, John F. Donegan, Hai-Zhong Weng, Delphine Marris-Morini, Adel Bousseksou, Markku Vainio, Thomas Bunel, Matteo Conforti, Arnaud Mussot, Erwan Lucas, Julien Fatome, Yuk Shan Cheng, Derryck T. Reid, Alessia Pasquazi, Marco Peccianti, M. Giudici, M. Marconi, A. Bartolo, N. Vigne, B. Chomet, A. Garnache, G. Beaudoin, I. Sagnes, Richard Burguete, Sarah Hammer, Jonathan Silver
https://arxiv.org/abs/2511.18231 https://arxiv.org/pdf/2511.18231 https://arxiv.org/html/2511.18231
arXiv:2511.18231v1 Announce Type: new
Abstract: The discovery of optical frequency combs (OFCs) has revolutionised science and technology by bridging electronics and photonics, driving major advances in precision measurements, atomic clocks, spectroscopy, telecommunications, and astronomy. However, current OFC systems still require further development to enable broader adoption in fields such as communication, aerospace, defence, and healthcare. There is a growing need for compact, portable OFCs that deliver high output power, robust self-referencing, and application-specific spectral coverage. On the conceptual side, progress toward such systems is hindered by an incomplete understanding of the fundamental principles governing OFC generation in emerging devices and materials, as well as evolving insights into the interplay between soliton and mode-locking effects. This roadmap presents the vision of a diverse group of academic and industry researchers and educators from Europe, along with their collaborators, on the current status and future directions of OFC science. It highlights a multidisciplinary approach that integrates novel physics, engineering innovation, and advanced researcher training. Topics include advances in soliton science as it relates to OFCs, the extension of OFC spectra into the visible and mid-infrared ranges, metrology applications and noise performance of integrated OFC sources, new fibre-based OFC modules, OFC lasers and OFC applications in astronomy.
toXiv_bot_toot

Diffusion-Augmented Reinforcement Learning for Robust Portfolio Optimization under Stress Scenarios
Himanshu Choudhary, Arishi Orra, Manoj Thakur
https://arxiv.org/abs/2510.07099

Diffusion-Augmented Reinforcement Learning for Robust Portfolio Optimization under Stress Scenarios
In the ever-changing and intricate landscape of financial markets, portfolio optimisation remains a formidable challenge for investors and asset managers. Conventional methods often struggle to capture the complex dynamics of market behaviour and align with diverse investor preferences. To address this, we propose an innovative framework, termed Diffusion-Augmented Reinforcement Learning (DARL), which synergistically integrates Denoising Diffusion Probabilistic Models (DDPMs) with Deep Reinforc…

M3Retrieve: Benchmarking Multimodal Retrieval for Medicine
Arkadeep Acharya, Akash Ghosh, Pradeepika Verma, Kitsuchart Pasupa, Sriparna Saha, Priti Singh
https://arxiv.org/abs/2510.06888

M3Retrieve: Benchmarking Multimodal Retrieval for Medicine
With the increasing use of RetrievalAugmented Generation (RAG), strong retrieval models have become more important than ever. In healthcare, multimodal retrieval models that combine information from both text and images offer major advantages for many downstream tasks such as question answering, cross-modal retrieval, and multimodal summarization, since medical data often includes both formats. However, there is currently no standard benchmark to evaluate how well these models perform in medica…

In-Context Clustering with Large Language Models
Ying Wang, Mengye Ren, Andrew Gordon Wilson
https://arxiv.org/abs/2510.08466 https://arxiv.org/pdf/2510.08…

In-Context Clustering with Large Language Models
We propose In-Context Clustering (ICC), a flexible LLM-based procedure for clustering data from diverse distributions. Unlike traditional clustering algorithms constrained by predefined similarity measures, ICC flexibly captures complex relationships among inputs through an attention mechanism. We show that pretrained LLMs exhibit impressive zero-shot clustering capabilities on text-encoded numeric data, with attention matrices showing salient cluster patterns. Spectral clustering using attenti…