OPPO-PersonalAI / TaskCraftLinks
A library for generating difficulty-scalable, multi-tool, and verifiable agentic tasks with execution trajectories.
☆110Updated last week
Alternatives and similar repositories for TaskCraft
Users that are interested in TaskCraft are comparing it to the libraries listed below
Sorting:
- Search and Refine During Think: Autonomous Retrieval‑Augmented Reasoning of LLMs☆83Updated 2 weeks ago
- This includes the original implementation of CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control.☆61Updated 9 months ago
- Official implementation of RARE: Retrieval-Augmented Reasoning Modeling☆184Updated last month
- Explore concepts like Self-Correct, Self-Refine, Self-Improve, Self-Contradict, Self-Play, and Self-Knowledge, alongside o1-like reasonin…☆169Updated 7 months ago
- ☆141Updated 4 months ago
- [EMNLP 2024] DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models☆70Updated last month
- MPLSandbox is an out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler a…☆178Updated 3 months ago
- [ICML 2025] "SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator"☆249Updated last week
- A scalable, end-to-end training pipeline for general-purpose agents☆258Updated last week
- SQL-o1: A Self-Reward Heuristic Dynamic Search Method for Text-to-SQL☆185Updated last month
- Grimoire is All You Need for Enhancing Large Language Models☆116Updated last year
- We leverage 14 datasets as OOD test data and conduct evaluations on 8 NLU tasks over 21 popularly used models. Our findings confirm that …☆93Updated last year
- Reverse Chain-of-Thought Problem Generation for Geometric Reasoning in Large Multimodal Models☆176Updated 8 months ago
- Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning☆75Updated 2 months ago
- Hybrid Latent Reasoning via Reinforcement Learning☆135Updated last month
- ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code (https://arxiv.org/abs/2311.098…☆301Updated last week
- Recipes to train the self-rewarding reasoning LLMs.☆224Updated 4 months ago
- Your efficient and accurate answer verification system for RL training.☆31Updated 3 weeks ago
- [ACL 2024] User-friendly evaluation framework: Eval Suite & Benchmarks: UHGEval, HaluEval, HalluQA, etc.☆169Updated last month
- GraphRAG-Bench, the official repo of comprehensive benchmark and dataset for evaluating GraphRAG models.☆126Updated this week
- A general AI agent framework that can be adapted to various tasks and environments.☆100Updated 5 months ago
- RobustFT: Robust Supervised Fine-tuning for Large Language Models under Noisy Response☆42Updated 6 months ago
- Official code of "StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs".☆69Updated 3 weeks ago
- This is the official code repository of MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tas…☆83Updated 3 months ago
- ☆31Updated this week
- The repository for the paper titled "Leopard: A Vision Language Model For Text-Rich Multi-Image Tasks"☆157Updated 6 months ago
- Code and dataset of CodeSteer☆58Updated 3 months ago
- LLM Benchmark for Code☆30Updated 11 months ago
- This tool(enhance_long) aims to enhance the LlaMa2 long context extrapolation capability in the lowest-cost approach, preferably without …☆45Updated last year
- A Contamination-free Multi-task Language Understanding Benchmark [Official, ACL 2025]☆117Updated last month