MPIE-Bench: Benchmark for multi-person character-consistent image editing under contact, with a six-axis evaluation protocol.

A 125-task benchmark for knowledge-mediated implicit associations and retrieval blind spots in long-term agent memory.

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, P…

A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物

AI Agent prompts for deep paper reading — auto-routes to benchmark, methodology, or survey/opinion analysis frameworks. Works with Cursor, Claude Code, Codex, and OpenCode.

Open-source AI agent desktop app for Windows & macOS. One-click install Claude Code, MCP tools, and Skills — with sandbox isolation, multi-model support, and Feishu/Slack integration.

😎 Awesome list of Retrieval-Augmented Generation (RAG) applications in Generative AI.

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.

[ACL 2026] WildGraphBench: Benchmarking GraphRAG with Wild-Source Corpora

A-RAG: Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces. State-of-the-art RAG framework with keyword, semantic, and chunk read tools for multi-hop QA.

Wiki Live Challenge: Challenging Deep Research Agents with Expert-Level Wikipedia Articles

Baidu Qianfan Deep Research

The AI that really does things. Any OS. Any Platform. The lobster way. 🦞

The paper list of "Memory in the Age of AI Agents: A Survey"

DeepResearch Bench II (DRB2) is the follow-up to DeepResearch Bench, with a stronger focus on measuring the gap between deep research systems and human experts. It does so by decomposing expert-wri…

A benchmark for LLMs on complicated tasks in the terminal

bloom - evaluate any behavior immediately  🌸🌱

一站式原生AI PPT生成应用，几分钟内生成一套幻灯片; 支持上传任意模板图片，上传任意素材&智能解析，一句话/大纲/页面描述自动生成PPT，口头修改指定区域、一键导出可编辑ppt、视频等 - An AI-native slides generator based on nano banana pro🍌

[ICLR 2026] LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora

ThinkDepth.ai Deep Research

Awesome curated collection of images and prompts built with the soon-to-launch Nano Banana Pro model. Browse limited early-access test cases that highlight Nano Banana Pro’s strengths in consistent…

Scaling Deep Research via Reinforcement Learning in Real-world Environments.

Salesforce Enterprise Deep Research

The official repo of GraphRAG-Bench for evaluating GraphRAG models. "When to use Graphs in RAG: A Comprehensive Analysis for Graph Retrieval-Augmented Generation". (ICLR'26)

Tongyi Deep Research, the Leading Open-source Deep Research Agent