Staged SFT→DPO→GRPO/OPD reinforcement learning pipeline for training a ReAct tool-use agent on arXiv paper retrieval tasks, with a deterministic snapshot-replay environment.
☆232Oct 31, 2026Updated last week
Alternatives and similar repositories for AgenticArXiv-RL
Users that are interested in AgenticArXiv-RL are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 大模型算法 / 应用 / Infra 岗位面试资料：10 份文档、345 道题、约 36 万字。含字节 11 篇面经实录、大模型八股上下篇、RAG / Agent / 推理部署 / AI Infra 四大专题，以及 12 家大厂面经横向对比。☆57Updated this week
- DPO训练reward模型，然后训练GRPO模型示例☆11Mar 12, 2026Updated 7 months ago
- LLM 面试手撕代码分享☆27Jun 2, 2026Updated 5 months ago
- Full-process resume optimization agent — use AI to refine your resume before submitting, ensuring it better aligns with the job descripti…☆15Sep 26, 2026Updated last month
- [NeurIPS 2026] Official repository for Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning☆12Jun 29, 2026Updated 4 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Long CoT Fine-Tuning and Reinforcement Learning for LLMs in the Context of the 24-Point Game: A Toy Project☆27Feb 22, 2025Updated last year
- ☆332Jul 16, 2026Updated 3 months ago
- Reproducing and studying RL algorithms for LLM agents, including GRPO, GSPO, DAPO, OPD, Search-R1, ReTool, ALFWorld and beyond.☆1,265Updated this week
- An open source book reader for kids, built for my daughter☆20Aug 27, 2026Updated 2 months ago
- ☆138Oct 24, 2026Updated 2 weeks ago
- Agentic RL最详细入门☆405Aug 6, 2026Updated 3 months ago
- 一个生产级的深度研究 Agent 系统，从零构建多智能体编排、Red-Blue 对抗降噪、 语义级上下文压缩、跨 Agent 共享记忆四大核心能力，配套 165 次独立实验 + Bootstrap 统计显著性检验的完整评测体系。☆175May 11, 2026Updated 5 months ago
- 基于轻量级 Qwen2.5-0.5B 和 SigLIP 的视觉语言多模态模型实现,包含训练和 SFT 代码。分享训练和 SFT 相关代码,记录一下探索和学习的过程。欢迎一起交流讨论~☆22Aug 31, 2025Updated last year
- Nosis is a lightweight personal agent runtime: per-session execution boundaries with OS-level sandboxing, computer use, a full built-in t…☆103Updated this week
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- 本项目基于Tiktok, Instagram, 快手等流媒推荐系统的 OneRec 生成式推荐范式架构，探索推荐系统统一建模为序列生成与偏好对齐问题，通过 Semantic ID 实现多模态内容与用户行为的统一表示，并结合强化学习驱动的 Reward 机制进行端到端优化。在…☆24Aug 27, 2026Updated 2 months ago
- A Godot 4 arena-survivor mini game — sweep the beach-landing waves, farm XP gems and evolve your build. Playable in browser. 抢滩登陆式生存割草小游戏☆33Oct 30, 2026Updated last week
- 麦顺路（McRoutePin）是一个基于麦当劳 MCP 的麦乐送拼单墙 Skill——把"附近正在一起点单的人"亮出来，用顺路度算法撮合最合适的两个人拼成一趟配送。☆31Oct 19, 2026Updated 2 weeks ago
- AI side-question layer — ask aside, stay on track.☆53Aug 29, 2026Updated 2 months ago
- Hands-on modules for LLMs: concise implementations for whiteboard-style practice.☆45May 19, 2026Updated 5 months ago
- 晴课表｜本地优先的 Android 课程表：周视图、教务网页与 Excel 导入、深色模式、课程提醒和学期管理☆79Updated this week
- ☆34Sep 15, 2026Updated last month
- Fixing GRPO training collapse in long-horizon multi-tool agents. A lightweight PRM-Lite + LATA joint approach achieves +37% over vanilla …☆268Jun 27, 2026Updated 4 months ago
- OpsCore demo single binary☆33Oct 15, 2026Updated 3 weeks ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Cross-platform port usage viewer and manager: find and kill processes occupying specified ports, with wildcard support, IPv6 and TCP/UDP …☆35Oct 14, 2026Updated 3 weeks ago
- TyDiP Multilingual Politeness dataset and code☆12Oct 15, 2023Updated 3 years ago
- Differential analysis tool for coding-free researchers – instant statistical results and charts, ready for your lab meeting. Just unzip a…☆96Sep 14, 2026Updated last month
- A lightweight Minecraft launcher optimized for Chinese networks and beginners. Built-in full performance optimizations and self-hosted hi…☆37Sep 25, 2026Updated last month
- A project implementing various agentic RL based on the Slime post-training framework☆549Apr 11, 2026Updated 6 months ago
- Enterprise multi-agent self-evolving workflow orchestration platform MVP☆43Sep 25, 2026Updated last month
- A Codex skill for evidence-grounded paper reading, reusable academic writing, literature synthesis, and research co-creation. 论文深读、写作迁移与研…☆15Oct 26, 2026Updated last week
- Shopping system by piggy and doggy☆65Sep 21, 2026Updated last month
- This is an AI Agent project; it's used for learning.☆21Jul 21, 2026Updated 3 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- AAAI2024 - Multi-Cross Sampling and Frequency-Division Reconstruction for Image Compressed Sensing☆13Jul 2, 2024Updated 2 years ago
- 赛博苏神：你的 research 好老师☆15Jun 16, 2026Updated 4 months ago
- KitAgent：开源 AI Agent 运行时与可视化工作台，支持 Web／CLI／TUI 交互、实时工具追踪、人工审批、会话记忆，以及 Skills、MCP 和 Kubernetes 沙箱扩展。☆64Updated this week
- ☆38Apr 3, 2026Updated 7 months ago
- ☆44Sep 20, 2026Updated last month
- 綦桐AI网关 - Android本地AI API网关 | QiTong AI Gateway - Local AI API Gateway. 多模型管理/智能故障转移/代理加速/Auto Failover/Multi-language v3.3.0☆17Updated this week
- 基于用户上传简历，动态筛选央国企与事业单位岗位，优先识别无笔试机会，并生成固定六工作表 Excel 的 ChatGPT/Codex Skill。☆41Aug 27, 2026Updated 2 months ago