Official Code of ICML-2026 Paper "Beyond Majority Voting: Self-Reflective Test-Time Reinforcement Learning for LLM Reasoning"
☆14Aug 15, 2026Updated 2 months ago
Alternatives and similar repositories for SR-TTRL
Users that are interested in SR-TTRL are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- P2T: Unlocking Token Rewards via Training-Free Reward Attribution (CVPR 2026) - official code☆65Oct 18, 2026Updated last week
- DodoGuard: Take AI Agents to Production. Test, validate, and operate AI Agents before and after deployment.for Dify, Coze, FastGPT, n8n, …☆277Oct 8, 2026Updated 2 weeks ago
- A multi-agent AUTO Research loop for idea discovery, experiment execution, evidence-grounded paper writing, quality audit, and live Web o…☆534Sep 24, 2026Updated last month
- Inkiva — A free, open-source WYSIWYG Markdown editor. Write in Markdown without leaving the document you are creating.☆74Updated this week
- AI-powered music assistant project☆11Updated this week
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- A股level2行情数据接口 level2行情 level2数据 level2接口 level2实时行情 L2实时行情 level2实时 L2实时 实时level2 实时L2 实时行情 level2行情数据 level2数据接口 股票level2 A股level2 L2行情…☆208Oct 9, 2026Updated 2 weeks ago
- 同行 · Together — 面向自主经营、任务与全成就推进的 Stardew Valley AI Agent。原生工具、持续计划、游戏记忆与玩家辅助。☆190Sep 23, 2026Updated last month
- Governance standard and reference toolset for LLM-maintained knowledge corpora☆620Sep 12, 2026Updated last month
- Structured project progress and safe cross-agent handoffs in one local Markdown file☆93Updated this week
- 般若波罗蜜。回到每一个争吵和沉默的节点，看看另一个版本的结局。☆828Sep 17, 2026Updated last month
- 基于 Jingyun Studio + DeepSeek Harness (DSH) 打造的一站式 AI 商业化桌面客户端，一个将 AI 智能体 / 技能 / 工作流转化为可交易商品的完整商业化平台客户端。 井云为 DSH 注入了完整的商业闭环：登录注册 → 会员体系 →…☆923Sep 30, 2026Updated 3 weeks ago
- 一条命令，把口播毛片变成可二次精修的剪辑工程。☆929Updated this week
- MCPHub Desktop 是一款基于 Tauri 2 构建的桌面客户端，用于在个人电脑上统一管理 MCP服务器、Skills、RAG 知识库。所有进程、配置、密钥与向量数据都运行/保存在用户自己的机器上，不依赖任何远端服务。☆969Oct 15, 2026Updated last week
- FactCircuit: an auditable claim-and-evidence verification loop with immutable provenance, staged checks, bounded retrieval, and reproduci…☆853Oct 9, 2026Updated 2 weeks ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- A focused GitHub desktop workspace for notifications, issues, pull requests, Actions, repository discovery, and an optional repository-aw…☆265Sep 25, 2026Updated last month
- ☆741Oct 14, 2026Updated last week
- PrismDraw 是一个基于 DDD 的抽奖营销后端系统，支持活动配置、抽奖策略、签到返利、积分兑换、奖品发放与异步补偿。PrismDraw is a DDD-based backend for lottery marketing workflows, covering …☆37Aug 25, 2026Updated 2 months ago
- CraftStation Agent Runtime Composition System☆816Updated this week
- A reactive, extensible Markdown renderer built for streaming, ready to use out of the box with a renderer-agnostic core.☆116Updated this week
- Local-first AI agent workspace for multi-agent collaboration, agent orchestration, scoped permissions, evidence-aware runs, and human-in-…☆1,103Updated this week
- MOMO CODE — RSI *JEV*Pi --AI coding agent that evolves with you☆1,108Updated this week
- 软件实习项目作业☆999Sep 2, 2026Updated last month
- Multi-modal voice agent for your AI agents. Talk with Claude Code, Codex, and others by voice: answer their prompts, give instructions, a…☆648Sep 16, 2026Updated last month
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- ☆385Updated this week
- Animal shelter & adoption management prototype — role-based workflows, rule-based listing, applicant ranking, audit trail.☆178Oct 18, 2026Updated last week
- DeepSeek Harness disk analysis and safe cleanup plugin for Windows.☆20Oct 1, 2026Updated 3 weeks ago
- Occamy model repo☆369Sep 21, 2026Updated last month
- A local audio visualization workbench and TypeScript DSP library with waveform, spectrum, spectrogram, Web Audio, WAV interchange and str…☆34Sep 10, 2026Updated last month
- A parasitic investigation skill for AI agents. Adaptive research, verified sources, traceable evidence.☆129Updated this week
- Self-hosted two-way Notion and CalDAV sync on Cloudflare Workers + D1 or Node.js + PostgreSQL☆274Oct 8, 2026Updated 2 weeks ago
- ☆92Oct 12, 2026Updated 2 weeks ago
- Interactive, source-linked ML workflow diagrams written by your coding assistant (Copilot, Codex or Claude Code) and opened in VS Code.☆373Oct 5, 2026Updated 3 weeks ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- ☆59Oct 16, 2026Updated last week
- Run Linux-style commands on Windows via deterministic bash→PowerShell translation. No VM, no WSL. MCP server + CLI built for AI agents (C…☆903Updated this week
- 大模型驱动的npc决策，npc和玩家平权☆1,187Mar 29, 2026Updated 6 months ago
- 几个 AI 终端开着，谁在等你一眼能看见。Claude Code、Codex 还在原来的终端里，旁边就能改文件、看 Git。macOS 本地工作台。☆319Updated this week
- Benchmark for allocating scarce user attention during long-horizon agent work☆91Aug 26, 2026Updated 2 months ago
- Native vLLM serving for Jev decision models☆763Updated this week
- 面向 Agent 的轻量级工具选择与概率决策模型，基于 Qwen3.5-0.8B；DI BFCL 工具名选择准确率 77.39%。☆81Oct 15, 2026Updated last week