2026.05.06 | ARIS自怼写论文；PRISM三段洗数据再RL

【目录】本期的 15 篇论文如下：[00:25] 🤖 ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration（自主研究：通过对抗性多智能体协作实现自动化科研）[00:59] 🎯 Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL（超越SFT到RL：通过黑盒在线策略蒸馏实现多模态强化学习的预对齐）[01:54] 🔍 OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories（OpenSeeker-v2：用信息丰富且高难度的轨迹推动搜索智能体的极限）[02:42] 🎯 X2SAM: Any Segmentation in Images and Videos（X2SAM：图像与视频中的任意分割）[03:23] 🧠 HeavySkill: Heavy Thinking as the Inner Skill in Agentic Harness（HeavySkill：智能体框架中的深度思考作为内在技能）[04:23] 🎬 Video Generation with Predictive Latents（基于预测性潜变量的视频生成）[05:05] 📜 PatRe: A Full-Stage Office Action and Rebuttal Generation Benchmark for Patent Examination（PatRe：面向专利审查的全阶段审查意见与答复生成基准）[05:45] 🎨 SVGS: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors（SVGS：利用空间变化颜色基元增强高斯泼溅）[06:31] 📂 Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies（工作空间基准1.0：针对具有大规模文件依赖的工作空间任务评估AI代理）[07:28] 🤒 SymptomAI: Towards a Conversational AI Agent for Everyday Symptom Assessment（SymptomAI: 面向日常症状评估的对话式AI代理）[08:11] 🤖 Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces（基于编排轨迹的大语言模型多智能体系统强化学习）[08:44] 🧩 SplAttN: Bridging 2D and 3D with Gaussian Soft Splatting and Attention for Point Cloud Completion（SplAttN：利用高斯软溅射与注意力机制桥接2D和3D的点云补全）[09:39] 🌍 A Benchmark for Interactive World Models with a Unified Action Generation Framework（交互式世界模型基准测试与统一动作生成框架）[10:25] 🔄 The TTS-STT Flywheel: Synthetic Entity-Dense Audio Closes the Indic ASR Gap Where Commercial and Open-Source Systems Fail（TTS-STT飞轮：合成密集实体音频填补了商业和开源系统失败的印地语ASR差距）[11:12] 💬 TCDA: Thread-Constrained Discourse-Aware Modeling for Conversational Sentiment Quadruple Analysis（TCDA：线程约束的对话感知建模用于对话情感四元组分析）【关注我们】您还可以在以下平台找到我们，获得播客内容以外更多信息小红书: AI速递在小宇宙查看该单集文稿