PyTorch-based open-source code for paper "SOD: Step-wise On-policy Distillation for Small Language Model Agents"
☆166May 22, 2026Updated 5 months ago
Alternatives and similar repositories for SOD
Users that are interested in SOD are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 对客户面对的脏话进行过滤的系统☆14Jun 7, 2026Updated 4 months ago
- Official PyTorch implementation of "Steerable Rhythmic Complexity in Autoregressive Music Generation" (EI Accepted). A bar-level conditio…☆14May 27, 2026Updated 5 months ago
- Official code repo for 'Agentic-SQL Revisited: Autonomy-Based Taxonomy and Empirical Benchmark Analysis for LLM Text-to-SQL'☆14Aug 28, 2026Updated 2 months ago
- ☆15Jun 10, 2026Updated 4 months ago
- ☆15Sep 17, 2026Updated last month
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Zero-trust Rust/WASM execution engine for autonomous AI agent economies.☆14Jun 4, 2026Updated 4 months ago
- ☆12Apr 28, 2026Updated 6 months ago
- ☆20May 25, 2026Updated 5 months ago
- Evidence-first multi-agent debate skill: get a second opinion by pitting Codex × Claude Code (or GLM/DeepSeek/Qwen) to independently revi…☆25Oct 9, 2026Updated 3 weeks ago
- Tour Pass 是一个 AI 行程规划系统。项目可以帮助用户可保存的旅行方案。项目支持 AI 对话规划、结构化表单规划、热门行程推荐、行程保存与分享等功能。☆21Sep 28, 2026Updated last month
- ☆22Jul 25, 2026Updated 3 months ago
- Extends pageIndex into an AI document workspace with multi-format parsing, OCR, visual TOC, custom models, citations, and agentic QA.☆41Jun 30, 2026Updated 4 months ago
- ☆17May 21, 2026Updated 5 months ago
- [ICME 2026 Spotlight] Pytorch Code for "Learning Where to Attend: A Sparse Dynamic Gate Transformer for Efficient Image Deraining"☆14Mar 30, 2026Updated 7 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.
- The autonomous AI multi-agent swarm for end-to-end game development. From idea to playable game in one click.☆28Sep 7, 2026Updated last month
- A High-Performance Real-Time Inference Engine for World Action Models in Physical AI☆24Oct 21, 2026Updated last week
- 医疗口述查房记录 L0 Schema 结构化抽取：多模型零样本评测 + 裁判共识 + 人工真值 + 实体级 F1 四阶段流水线☆21Oct 17, 2026Updated 2 weeks ago
- [COLM 2026]TCOD: Exploring Temporal Curriculum in On-Policy Distillation for Multi-turn Autonomous Agents☆116Jul 9, 2026Updated 3 months ago
- [arxiv 2606] Visual-OPSD: Cross-Modal On-Policy Self-Distillation for Efficient Unified Multimodal Reasoning☆51Jul 3, 2026Updated 3 months ago
- 给 AI Coding Agent（Claude Code / Cursor / Codex / Gemini CLI）用的 **技能版 npm** —— 本地优先、模型无关、MCP 原生。☆31Aug 10, 2026Updated 2 months ago
- 一个通用的框架，小白可以在这个框架的基础上使用 AI 完成一个项目的从 0 到 1；也可以在这个框架中添加特定领域知识，让他成为特定领域的通用软件研发工具；☆13Apr 29, 2026Updated 6 months ago
- Local-first Chrome extension for timestamped transcription and human-reviewed short-form drama analysis.☆45Aug 24, 2026Updated 2 months ago
- A personal job application AI Agent for job discovery, fit scoring, tailored materials, form filling, human-gated submission and applicat…☆56Aug 2, 2026Updated 2 months ago
- 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.
- 专利侵权分析系统 —— 输入专利公开号，产出竞品侵权分析报告；同时打包成 skill，可被任意 agent（dsh, codex, claudecode 等） 调用。☆67Aug 29, 2026Updated 2 months ago
- An Obsidian plugin for quickly recording, browsing, and organizing ideas as text, links, images, and videos.☆58Aug 13, 2026Updated 2 months ago
- Turn messy research goals into evidence ledgers, method cards, experiment routes, artifact audits, and advisor-ready reports.☆57Jun 2, 2026Updated 4 months ago
- 🔔 Cross-window completion & approval notifications for DeepSeek Harness — popup reminders that bring you back to DSH, Codex/WorkBuddy st…☆19Aug 16, 2026Updated 2 months ago
- Auditable AI agent for electromechanical maintenance with LangGraph, RAG, fault diagnosis and human-in-the-loop review.☆47Aug 10, 2026Updated 2 months ago
- 跑在 Claude Code / Codex 之上的本地多 Agent 协作脚手架:一个人下指令,主 Agent 拆解分派给专职角色,共用文件级记忆层。作者自用的主要方法是接到飞书bot，你只需要跟飞书bot聊天他就能帮你干活了☆24May 29, 2026Updated 5 months ago
- ☆29Sep 7, 2026Updated last month
- ☆38Aug 27, 2026Updated 2 months ago
- Official code for "Self-Distilled Agentic Reinforcement Learning"☆376Oct 15, 2026Updated 2 weeks ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- ☆97Jun 1, 2026Updated 4 months ago
- A framework for AI-driven economic activity. Declarative, composable, observable, deterministic.☆74Oct 19, 2026Updated last week
- On Policy Distillation Build on top of Verl☆103Sep 3, 2026Updated last month
- Official code for "Breaking the Ceiling in On-Policy Distillation via Multi-Agent Debate" (arXiv:2605.01347).☆38Jul 31, 2026Updated 3 months ago
- [ICML 2026] Hybrid Policy Distillation (HPD) is a practical distillation framework for reasoning-oriented language models. This repositor…☆24Apr 24, 2026Updated 6 months ago
- A coding agent modeled after Claude Code, supporting code generation, refactoring and PR analysis.☆26Jul 4, 2026Updated 3 months ago
- Sven Family is an AI-native product suite that connects creation, collaboration, publishing, and operations into one integrated platform.☆159Jun 26, 2026Updated 4 months ago