Tootfinder

Merci trump
En Argentine, le parti de Javier Milei remporte largement les législatives de mi-mandat
https://www.lemonde.fr/international/article/2025/10/27/en-argentine-le-pa…

En Argentine, le parti de Javier Milei remporte largement les législatives de mi-mandat
La Libertad Avanza a recueilli plus de 40 % des votes au niveau national, selon des résultats officiels à 97 % du décompte. Le président d’extrême droite a salué un « point de bascule » et promis davantage de réformes.

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control
Quanfeng Lu, Zhantao Ma, Shuai Zhong, Jin Wang, Dahai Yu, Michael K. Ng, Ping Luo
https://arxiv.org/abs/2508.20018 …

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control
The rapid advancement of large vision language models (LVLMs) and agent systems has heightened interest in mobile GUI agents that can reliably translate natural language into interface operations. Existing single-agent approaches, however, remain limited by structural constraints. Although multi-agent systems naturally decouple different competencies, recent progress in multi-agent reinforcement learning (MARL) has often been hindered by inefficiency and remains incompatible with current LVLM a…

GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Lakshya A Agrawal, Shangyin Tan, Dilara Soylu, Noah Ziems, Rishi Khare, Krista Opsahl-Ong, Arnav Singhvi, Herumb Shandilya, Michael J Ryan, Meng Jiang, Christopher Potts, Koushik Sen, Alexandros G. Dimakis, Ion Stoica, Dan Klein, Matei Zaharia, Omar Khattab
https://arx…

GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Large language models (LLMs) are increasingly adapted to downstream tasks via reinforcement learning (RL) methods like Group Relative Policy Optimization (GRPO), which often require thousands of rollouts to learn new tasks. We argue that the interpretable nature of language can often provide a much richer learning medium for LLMs, compared with policy gradients derived from sparse, scalar rewards. To test this, we introduce GEPA (Genetic-Pareto), a prompt optimizer that thoroughly incorporates …

ReCoDe: Reinforcement Learning-based Dynamic Constraint Design for Multi-Agent Coordination
Michael Amir, Guang Yang, Zhan Gao, Keisuke Okumura, Heedo Woo, Amanda Prorok
https://arxiv.org/abs/2507.19151

ReCoDe: Reinforcement Learning-based Dynamic Constraint Design for Multi-Agent Coordination
Constraint-based optimization is a cornerstone of robotics, enabling the design of controllers that reliably encode task and safety requirements such as collision avoidance or formation adherence. However, handcrafted constraints can fail in multi-agent settings that demand complex coordination. We introduce ReCoDe--Reinforcement-based Constraint Design--a decentralized, hybrid framework that merges the reliability of optimization-based controllers with the adaptability of multi-agent reinforce…

DxHF: Providing High-Quality Human Feedback for LLM Alignment via Interactive Decomposition
Danqing Shi, Furui Cheng, Tino Weinkauf, Antti Oulasvirta, Mennatallah El-Assady
https://arxiv.org/abs/2507.18802

DxHF: Providing High-Quality Human Feedback for LLM Alignment via Interactive Decomposition
Human preferences are widely used to align large language models (LLMs) through methods such as reinforcement learning from human feedback (RLHF). However, the current user interfaces require annotators to compare text paragraphs, which is cognitively challenging when the texts are long or unfamiliar. This paper contributes by studying the decomposition principle as an approach to improving the quality of human feedback for LLM alignment. This approach breaks down the text into individual claim…

InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
Weiyun Wang, Zhangwei Gao, Lixin Gu, Hengjun Pu, Long Cui, Xingguang Wei, Zhaoyang Liu, Linglin Jing, Shenglong Ye, Jie Shao, Zhaokai Wang, Zhe Chen, Hongjie Zhang, Ganlin Yang, Haomin Wang, Qi Wei, Jinhui Yin, Wenhao Li, Erfei Cui, Guanzhou Chen, Zichen Ding, Changyao Tian, Zhenyu Wu, Jingjing Xie, Zehao Li, Bowen Yang, Yuchen Duan, Xuehui Wang, Songze Li, Xiangyu Zhao, Haodong Duan, Nianche…

InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
We introduce InternVL 3.5, a new family of open-source multimodal models that significantly advances versatility, reasoning capability, and inference efficiency along the InternVL series. A key innovation is the Cascade Reinforcement Learning (Cascade RL) framework, which enhances reasoning through a two-stage process: offline RL for stable convergence and online RL for refined alignment. This coarse-to-fine training strategy leads to substantial improvements on downstream reasoning tasks, e.g.…

« Oskar », colonel ukrainien : « Une mobilisation massive serait une décision impopulaire, mais nécessaire »
https://www.lemonde.fr/international/article/2025/08/27/oskar…

« Oskar », colonel ukrainien : « Une mobilisation massive serait une décision impopulaire, mais nécessaire »
Agé de 34 ans, Vassyl Matiïv, dit « Oskar », appartient à une nouvelle génération de commandants émergeant à la faveur d’une réorganisation profonde de l’armée ukrainienne. Il raconte l’évolution des techniques d’assaut et insiste sur le besoin de renforts afin de tenir dans la durée.

UserRL: Training Interactive User-Centric Agent via Reinforcement Learning
Cheng Qian, Zuxin Liu, Akshara Prabhakar, Jielin Qiu, Zhiwei Liu, Haolin Chen, Shirley Kokane, Heng Ji, Weiran Yao, Shelby Heinecke, Silvio Savarese, Caiming Xiong, Huan Wang
https://arxiv.org/abs/2509.19736

UserRL: Training Interactive User-Centric Agent via Reinforcement Learning
Reinforcement learning (RL) has shown promise in training agentic models that move beyond static benchmarks to engage in dynamic, multi-turn interactions. Yet, the ultimate value of such agents lies in their ability to assist users, a setting where diversity and dynamics of user interaction pose challenges. In this work, we propose UserRL, a unified framework for training and evaluating user-centric abilities through standardized gym environments paired with simulated users. We systematically v…

MOSS-ChatV: Reinforcement Learning with Process Reasoning Reward for Video Temporal Reasoning
Sicheng Tao, Jungang Li, Yibo Yan, Junyan Zhang, Yubo Gao, Hanqian Li, ShuHang Xun, Yuxuan Fan, Hong Chen, Jianxiang He, Xuming Hu
https://arxiv.org/abs/2509.21113

MOSS-ChatV: Reinforcement Learning with Process Reasoning Reward for Video Temporal Reasoning
Video reasoning has emerged as a critical capability for multimodal large language models (MLLMs), requiring models to move beyond static perception toward coherent understanding of temporal dynamics in complex scenes. Yet existing MLLMs often exhibit process inconsistency, where intermediate reasoning drifts from video dynamics even when the final answer is correct, undermining interpretability and robustness. To address this issue, we introduce MOSS-ChatV, a reinforcement learning framework w…

Increasing Interaction Fidelity: Training Routines for Biomechanical Models in HCI
Micha{\l} Patryk Miazga, Patrick Ebel
https://arxiv.org/abs/2508.16581 https://

Increasing Interaction Fidelity: Training Routines for Biomechanical Models in HCI
Biomechanical forward simulation holds great potential for HCI, enabling the generation of human-like movements in interactive tasks. However, training biomechanical models with reinforcement learning is challenging, particularly for precise and dexterous movements like those required for touchscreen interactions on mobile devices. Current approaches are limited in their interaction fidelity, require restricting the underlying biomechanical model to reduce complexity, and do not generalize well…