QuantaAlpha / GitTaskBenchLinks
Repo-level benchmark for real-world Code Agents: from repo understanding → env setup → incremental dev/bug-fixing → task delivery, with cost-aware α metric.
☆244Updated 4 months ago
Alternatives and similar repositories for GitTaskBench
Users that are interested in GitTaskBench are comparing it to the libraries listed below
Sorting:
- Marco Search Agent for Realistic and Challenging Agentic Search☆240Updated 3 months ago
- ☆359Updated 7 months ago
- ☆265Updated 3 weeks ago
- ☆210Updated last month
- ☆110Updated 3 weeks ago
- Code for "FaithLens: Detecting and Explaining Faithfulness Hallucination"☆97Updated 3 weeks ago
- MTLA: Multi-head Temporal Latent Attention☆760Updated 3 months ago
- We introduce temporal working memory (TWM), which aims to enhance the temporal modeling capabilities of Multimodal foundation models (MFM…☆311Updated 2 months ago
- ☆73Updated 2 months ago
- Group Expectation Policy Optimization for Heterogeneous Reinforcement Learning☆164Updated 2 months ago
- A powerful multi-format file parsing, data cleaning, and AI annotation toolkit.☆145Updated last month
- [BIRD-INTERACT] Re-imagines Text-to-SQL evaluation via lens of dynamic interactions.☆455Updated last week
- Tokenize The Virtual Agents Onchain☆243Updated 7 months ago
- [ACL 2025] FinMME: Benchmark Dataset for Financial Multi-Modal Reasoning Evaluation☆62Updated 7 months ago
- ☆293Updated 7 months ago
- Official Code for MTSQL-R1: Towards Long-Horizon Multi-Turn Text-to-SQL via Agentic Training☆37Updated 3 months ago
- Science-Star: A Platform for Building, Extending, and Experimenting with Scientific Agents.☆740Updated 3 months ago
- This repo collects research papers that use AI tools and are in the field of scientific research (including computer science, agronomy, c…☆98Updated 10 months ago
- ☆128Updated 3 months ago
- [MM 2024] Official code for VeCAF: Vision-language Collaborative Active Finetuning with Training Objective Awareness☆52Updated last year
- (EMNLP 2025 Findings) Source Evaluation scripts for Humanity's Last Code Exam☆95Updated 5 months ago
- ☆516Updated 11 months ago
- [TMLR'25] The Curse of CoT: On the Limitations of Chain-of-Thought in In-Context Learning☆53Updated 9 months ago
- ☆71Updated 4 months ago
- 超能文献|AI驱动的文档翻译与学术搜索服务。支持PDF、DOCX、PPTX等多格式文档的高质量翻译（支持11种语言），特别优化了数学公式翻译。同时提供PubMed学术文献智能搜索功能。更多访问：https://suppr.wilddata.cn☆246Updated 3 months ago
- A database operations and data analysis AI agent☆430Updated 5 months ago
- Valuation of tokens corresponding to influential individuals on social platforms through AI algorithms☆229Updated 4 months ago
- A reading list for trustworthy audio large language models.☆113Updated last week
- 4th Place Solution for the Kaggle Competition: LMSYS - Chatbot Arena Human Preference Predictions☆170Updated last year
- DPO-Shift: Shifting the Distribution of Direct Preference Optimization☆59Updated 10 months ago