THUDM / SWE-DevLinks
[ACL25' Findings] SWE-Dev is an SWE agent with a scalable test case construction pipeline.
☆55Updated 2 months ago
Alternatives and similar repositories for SWE-Dev
Users that are interested in SWE-Dev are comparing it to the libraries listed below
Sorting:
- ☆117Updated 4 months ago
- [COLM 2025] Official repository for R2E-Gym: Procedural Environment Generation and Hybrid Verifiers for Scaling Open-Weights SWE Agents☆159Updated 2 months ago
- DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL☆95Updated last week
- RepoQA: Evaluating Long-Context Code Understanding☆117Updated 10 months ago
- ☆52Updated last year
- StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback☆68Updated last year
- ☆112Updated 3 months ago
- WideSearch: Benchmarking Agentic Broad Info-Seeking☆93Updated last month
- [ICLR 2025] DSBench: How Far are Data Science Agents from Becoming Data Science Experts?☆75Updated last month
- [ACL 2025] Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems☆105Updated 3 months ago
- RL Scaling and Test-Time Scaling (ICML'25)☆111Updated 7 months ago
- [ICML 2025] Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples☆106Updated last month
- Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.☆182Updated 6 months ago
- CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings☆53Updated 7 months ago
- SWE-Swiss: A Multi-Task Fine-Tuning and RL Recipe for High-Performance Issue Resolution☆84Updated this week
- Training and Benchmarking LLMs for Code Preference.☆35Updated 10 months ago
- Code for the paper: CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models☆28Updated 5 months ago
- Code for paper "Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System"☆61Updated 10 months ago
- ☆37Updated 4 months ago
- ☆73Updated 3 weeks ago
- 🚀 SWE-bench Goes Live!☆119Updated this week
- Systematic evaluation framework that automatically rates overthinking behavior in large language models.☆93Updated 4 months ago
- ☆73Updated 6 months ago
- Official implementation for DenseMixer: Improving MoE Post-Training with Precise Router Gradient☆54Updated last month
- r2e: turn any github repository into a programming agent environment☆129Updated 5 months ago
- The code for the paper: "Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models"☆54Updated last year
- ☆103Updated 9 months ago
- Run SWE-bench evaluations remotely☆42Updated last month
- [ICML 2025] Teaching Language Models to Critique via Reinforcement Learning☆111Updated 4 months ago
- Efficient Agent Training for Computer Use☆131Updated 2 weeks ago