THUDM / SWE-DevLinks
[ACL25' Findings] SWE-Dev is an SWE agent with a scalable test case construction pipeline.
☆47Updated last week
Alternatives and similar repositories for SWE-Dev
Users that are interested in SWE-Dev are comparing it to the libraries listed below
Sorting:
- ☆94Updated last month
- RepoQA: Evaluating Long-Context Code Understanding☆111Updated 8 months ago
- ☆104Updated 2 months ago
- A benchmark for LLMs on complicated tasks in the terminal☆240Updated this week
- Scaling Data for SWE-agents☆293Updated this week
- DSBench: How Far are Data Science Agents from Becoming Data Science Experts?☆58Updated 4 months ago
- r2e: turn any github repository into a programming agent environment☆127Updated 2 months ago
- Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.☆173Updated 4 months ago
- ☆49Updated last year
- Enhancing AI Software Engineering with Repository-level Code Graph☆191Updated 3 months ago
- [ICML 2025] Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples☆101Updated last month
- StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback☆67Updated 10 months ago
- Code for paper "Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System"☆59Updated 8 months ago
- Official repository for R2E-Gym: Procedural Environment Generation and Hybrid Verifiers for Scaling Open-Weights SWE Agents☆112Updated 2 weeks ago
- [ACL 2025] Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems☆96Updated last month
- Systematic evaluation framework that automatically rates overthinking behavior in large language models.☆91Updated 2 months ago
- InstructCoder: Instruction Tuning Large Language Models for Code Editing | Oral ACL-2024 srw☆61Updated 9 months ago
- Moatless Testbeds allows you to create isolated testbed environments in a Kubernetes cluster where you can apply code changes through git…☆13Updated 3 months ago
- A benchmark that challenges language models to code solutions for scientific problems☆127Updated last week
- A Comprehensive Benchmark for Software Development.☆111Updated last year
- Training and Benchmarking LLMs for Code Preference.☆33Updated 8 months ago
- 🚀 SWE-bench Goes Live!☆94Updated last week
- SWE Arena☆34Updated last week
- CRUXEval: Code Reasoning, Understanding, and Execution Evaluation☆149Updated 9 months ago
- ☆55Updated 2 weeks ago
- Official implementation of paper "On the Diagram of Thought" (https://arxiv.org/abs/2409.10038)☆185Updated 3 months ago
- Self-Reflection in LLM Agents: Effects on Problem-Solving Performance☆77Updated 7 months ago
- Official code for the paper "CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules"☆45Updated 6 months ago
- Code for the paper: CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models☆24Updated 3 months ago
- ☆75Updated 10 months ago