Tootfinder

Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR
Xiao Liang, Zhongzhi Li, Yeyun Gong, Yelong Shen, Ying Nian Wu, Zhijiang Guo, Weizhu Chen
https://arxiv.org/abs/2508.14029

Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR
Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a key paradigm for post-training Large Language Models (LLMs), particularly for complex reasoning tasks. However, vanilla RLVR training has been shown to improve Pass@1 performance at the expense of policy entropy, leading to reduced generation diversity and limiting the Pass@k performance, which typically represents the upper bound of LLM reasoning capability. In this paper, we systematically analyze the policy's gen…

Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration
Zhicheng Yang, Zhijiang Guo, Yinya Huang, Yongxin Wang, Dongchun Xie, Yiwei Wang, Xiaodan Liang, Jing Tang
https://arxiv.org/abs/2508.13755

Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration
Reinforcement Learning with Verifiable Reward (RLVR) has emerged as a powerful paradigm for unlocking reasoning capabilities in large language models, yet its full potential is hindered by two under-explored dimensions: Depth-the hardest problem a model can sample; Breadth-the number of instances consumed in a single iteration. We dissect the popular GRPO algorithm and reveal a systematic bias: the cumulative-advantage disproportionately weights samples with medium accuracy, while down-weightin…

Reinforcement Learning with Rubric Anchors
Zenan Huang, Yihong Zhuang, Guoshan Lu, Zeyu Qin, Haokai Xu, Tianyu Zhao, Ru Peng, Jiaqi Hu, Zhanming Shen, Xiaomeng Hu, Xijun Gu, Peiyi Tu, Jiaxin Liu, Wenyu Chen, Yuzhuo Fu, Zhiting Fan, Yanmei Gu, Yuanyuan Wang, Zhengkai Yang, Jianguo Li, Junbo Zhao
https://arxiv.org/abs/2508.12790

Reinforcement Learning with Rubric Anchors
Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a powerful paradigm for enhancing Large Language Models (LLMs), exemplified by the success of OpenAI's o-series. In RLVR, rewards are derived from verifiable signals-such as passing unit tests in code generation or matching correct answers in mathematical reasoning. While effective, this requirement largely confines RLVR to domains with automatically checkable outcomes. To overcome this, we extend the RLVR paradigm to open-end…

I tried out a sign handle but didn't like it so I started to design my own...
Mine is parametric and has a separate clamping piece that attaches with two 8-32 (or 4mm) bolts.
On a 256x256 print bed you can print one about 270mm (10.6") tall.
( Here's the one I originally tried: https…

LaViPlan : Language-Guided Visual Path Planning with RLVR
Hayeon Oh
https://arxiv.org/abs/2507.12911 https://arxiv.org/pdf/2507.12911…

LaViPlan : Language-Guided Visual Path Planning with RLVR
Out-of-distribution (OOD) scenarios in autonomous driving refer to situations that deviate from the training domain, often leading to unexpected and potentially hazardous behavior from planners that lack prior exposure to such cases. Recently, Vision-Language Models (VLMs) have been introduced into autonomous driving research for their promising generalization capabilities in OOD settings. Early studies demonstrated that VLMs could recognize OOD scenarios and generate user-level decisions such …

🇺🇦 #NowPlaying on #BBC6Music's #6MusicsIndieForever
The Ting Tings:
🎵 Great DJ
#TheTingTings
https://rolivaroliva.bandcamp.com/track/great-dj-roliva-edit-the-ting-tings
https://open.spotify.com/track/3kmSzP8JUM4kUwPWbOFwqA

Hello les gens ! Question #OpenStreetMap. J'ai déjŠ contribué modestement Š #OSM par le passé, mais lŠ , il y a un défi autrement plus complexe que j'aurais Š relever : Je souhaiterais ajouter une nouvelle voie publique ainsi qu'un nouvel équipement dans mon village, Š Guern. Il s'agit de l'…

MEML-GRPO: Heterogeneous Multi-Expert Mutual Learning for RLVR Advancement
Weitao Jia, Jinghui Lu, Haiyang Yu, Siqi Wang, Guozhi Tang, An-Lan Wang, Weijie Yin, Dingkang Yang, Yuxiang Nie, Bin Shan, Hao Feng, Irene Li, Kun Yang, Han Wang, Jingqun Tang, Teng Fu, Changhong Jin, Chao Feng, Xiaohui Lv, Can Huang
https://arxiv.org/abs/2508.09670…

MEML-GRPO: Heterogeneous Multi-Expert Mutual Learning for RLVR Advancement
Recent advances demonstrate that reinforcement learning with verifiable rewards (RLVR) significantly enhances the reasoning capabilities of large language models (LLMs). However, standard RLVR faces challenges with reward sparsity, where zero rewards from consistently incorrect candidate answers provide no learning signal, particularly in challenging tasks. To address this, we propose Multi-Expert Mutual Learning GRPO (MEML-GRPO), an innovative framework that utilizes diverse expert prompts as …

You could 3D print a little sign holder handle...
➡️ https://www.printables.com/model/1248678-ergonomic-foam-board-holder-for-rallyprotest-signs

Ergonomic Foam Board Holder for Rally/Protest Signs by ＮＥＦＡＲＩＯＵＳ | Download free STL model | Printables.com
Ergonomic Foam Board Holder for Rally/Protest Signs | Download free 3D printable STL models

G$^2$RPO-A: Guided Group Relative Policy Optimization with Adaptive Guidance
Yongxin Guo, Wenbo Deng, Zhenglin Cheng, Xiaoying Tang
https://arxiv.org/abs/2508.13023 https://

G$^2$RPO-A: Guided Group Relative Policy Optimization with Adaptive Guidance
Reinforcement Learning with Verifiable Rewards (RLVR) has markedly enhanced the reasoning abilities of large language models (LLMs). Its success, however, largely depends on strong base models with rich world knowledge, yielding only modest improvements for small-size language models (SLMs). To address this limitation, we investigate Guided GRPO, which injects ground-truth reasoning steps into roll-out trajectories to compensate for SLMs' inherent weaknesses. Through a comprehensive study of va…