1
VRPRM: Process Reward Modeling via Visual Reasoning
通过视觉推理提升过程奖励建模精度，为复杂任务训练提供新思路。
arXiv:2508.03556v3 Announce Type: replace Abstract: Process Reward Model (PRM) is widely used in the post-training of Large Language Model (LLM) becau…
2
Linear Dynamics in the RLVR Training of Large Language Models
揭秘大语言模型RLVR训练中的线性动力学机制，为强化学习优化提供新视角。
arXiv:2601.04537v3 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has driven significant performance gai…
3
Ask HN: Is the next big thing locally running coding agents?
当云端API成本飙升，本地运行开源模型完成编程任务或将成主流趋势。
There's extreme price escalation on part of Anthropic, with token spend now approaching levels that have made many-an-enterprise scratch their heads. …
4
Conformal Selective Acting: Anytime-Valid Risk Control for RLVR-Trained LLMs
新方法保障LLM在线部署每轮风险可控，基于共形预测与RLVR训练，安全认证更可靠。
arXiv:2605.20270v1 Announce Type: new Abstract: A local specialist LLM, fine-tuned with reinforcement learning from verifiable rewards (RLVR) on opera…
5
You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories
揭示RLVR训练中参数轨迹的秩一结构，仅需极小规模训练即可外推LLM推理能力，颠覆传统认知。
arXiv:2605.21468v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a dominant paradigm for improving rea…
6
Step-wise Rubric Rewards for LLM Reasoning
提出逐步评分奖励机制，优化LLM推理的中间步骤监督，突破传统仅奖励最终答案的局限。
arXiv:2605.17291v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) is widely used to improve reasoning in large lan…
7
CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG
提出CuSearch课程采样法，通过搜索深度优化Agentic RAG的强化学习训练，提升效率
arXiv:2605.11611v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising paradigm for trai…
8
Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVR
Muon优化器在视觉语言对齐与强化学习微调中暴露频谱失效问题，作者提出高通滤波器补救方案，刷新大模型训练认知。
arXiv:2605.19282v1 Announce Type: new Abstract: Muon is a matrix-aware optimizer that leverages Newton-Schulz (NS) iterations to enforce spectral grad…
9
Reasoning Portability: Guiding Continual Learning for MLLMs in the RLVR Era
提出“推理可移植性”新概念，为多模态大模型在强化学习时代的持续学习指明方向。
arXiv:2605.18903v1 Announce Type: new Abstract: Vision-Language Models in Continual Learning (VLM-CL) aim to continuously adapt to new multimodal task…
10
Knowledge-to-Verification: Exploring RLVR for LLMs in Knowledge-Intensive Domains
探索强化学习与可验证奖励在知识密集型领域对LLM推理能力的提升，填补研究空白。
arXiv:2605.18261v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has demonstrated promising potential to enhance …
11
CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models
用奖励模型突破测试用例限制，实现代码大模型训练与推理阶段的可扩展强化学习。
arXiv:2602.17684v2 Announce Type: replace Abstract: Reinforcement Learning from Verifiable Rewards (RLVR) has driven recent progress in code large lan…
12
The Unlearnability Phenomenon in RLVR for Language Models
揭示RLVR训练中LLM对困难样本无法学习的反直觉现象，挑战现有认知
arXiv:2605.16787v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Reward (RLVR) has proven effective in improving Large Language …
13
AI Rings on Fingers Can Interpret Sign Language
手指上的AI戒指实时翻译手语，还有望拓展VR/AR交互新场景。
Article URL: https://spectrum.ieee.org/sign-language-interpreter Comments URL: https://news.ycombinator.com/item?id=48181012 Points: 1 # Comments: 0
14
Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR
提出双令牌约束方法，稳定知识并提升推理能力，解决RLVR中令牌均匀优化问题
arXiv:2507.15778v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become an effective post-training method…
15
ReactVision Studio
用React Native构建AR/VR应用并直接部署到设备，简化跨平台沉浸式开发流程。
Build AR/VR Apps in React Native + ship directly to devices Discussion | Link
16
Hosting a website on an 8-bit microcontroller
一篇教你用8位微控制器（AVR芯片）搭建迷你Web服务器的硬核动手指南，代码与硬件全公开，极客味十足
Article URL: https://maurycyz.com/projects/mcusite/ Comments URL: https://news.ycombinator.com/item?id=48165295 Points: 211 # Comments: 17