Official repository for the paper "LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code"
-
Updated
Jul 16, 2025 - Python
#
code-repair
Here are 61 public repositories matching this topic...
Evidence-grounded AI agent for Java code repair with LLM-guided patches and human-in-the-loop review.
static-analysis human-in-the-loop ai-agent code-repair agent-harness evidence-grounded llm-guided-repair
-
Updated
Aug 8, 2026 - Python
Exploring and improving the quality of ChatGPT-generated code for LeetCode programming tasks.
-
Updated
Jan 19, 2024 - Python
基于 AI Agent 服务自动化修复系统：Agent 自动读取错误日志，定位 Bug，生成补丁，运行测试，提交 PR，并通知开发者 Review。AI-powered auto-fix agent for web services: analyzes logs, patches code, runs tests, and creates pull requests automatically.
-
Updated
May 7, 2026 - Java
Repository-level automated code repair agent using SWE-Bench dataset
-
Updated
May 1, 2026 - Python
Trusted autonomy T&E runtime that links mission needs, hazards, scenarios, telemetry, evidence, verification reports, and hash-chained ledgers so AI/autonomous decisions can be reviewed instead of merely trusted.
python verification ci-cd developer-tools code-review traceability human-in-the-loop policy-enforcement policy-as-code code-repair ai-assurance ai-governance approval-workflows auditability agent-safety runtime-assurance ai-coding-agents controlled-execution runtime-guardrails evidence-bundles
-
Updated
May 13, 2026 - Python
python mcp gemini openai pytest-plugin self-healing ai-agents code-repair llm langchain anthropic langgraph agent-reliability
-
Updated
Aug 7, 2026 - Python
Multilingual software-engineering benchmark with pinned Docker environments & reproducible agent trajectories · 多语言软件工程评测基准
multilingual docker benchmark dataset software-engineering code-repair llm-evaluation coding-agent swe-bench agent-trajectories
-
Updated
Aug 18, 2026 - Shell
A reliability layer for AI-built systems: detect failures (tests or runtime drift), reproduce, repair one ticket at a time behind an approval gate, and prove the fix. The safety boundaries most AI agents skip.
-
Updated
Jun 12, 2026 - Python
Gymnasium RL environment for training LLM agents to autonomously debug and fix Python code with secure sandboxing and test-driven feedback.
reinforcement-learning pytorch gymnasium autonomous-agents rl-environment ai-agent code-repair large-language-models llm-agents code-debugging python-debugging open-environment sandbox-execution
-
Updated
Jul 11, 2026 - Python
A minimal lab for improving programs, agents and model parameters. Real demos, frozen evaluations, inspectable evidence. Zero runtime dependencies.
python evaluation ai-agents parameter-learning code-repair evolutionary-search llm recursive-self-improvement coding-agents agent-skills
-
Updated
Sep 21, 2026 - Python
PyPatch— OpenEnv RL environment where AI agents debug & fix buggy Python code across 3 difficulty levels.
python debugging open-source benchmark machine-learning research reinforcement-learning ai deep-learning developer-tools rl educational software-engineering code-generation coding-challenges bug-fixing autonomous-agents ai-agents code-repair openenv
-
Updated
Apr 8, 2026 - Python
🦑 CT 11 — Secure Self-Learning Repair Agent. Droste Fusion. 4 Engines. Reflection Engine. 9/10 Benchmark.
python agent open-source security research cybernetics self-learning ai-safety bug-analysis safety-first code-repair ai-coding llm-guardian safety-guardian
-
Updated
Jul 8, 2026 - Python
Run broken Python code → it fixes itself. Local-first Python runtime repair.
python debugging cli devops automation runtime devtools developer-tools self-healing local-first code-repair
-
Updated
Jul 17, 2026 - Python
When Free Executors Cost More: The Free-Executor Paradox in Iterative LLM Code-Repair Loops (paper + reproducibility kit)
reproducible-research claude cost-analysis code-repair llm prompt-caching qwen agentic-coding pareto-frontier deterministic-judge
-
Updated
Aug 2, 2026 - Python
AI proposes. Humans decide. Source-available AI assurance and live authority control plane for governed AI-produced code change: MCP/API pre-tool enforcement, authenticated agents, scoped authorization, evidence-conditioned authority, human-gated execution, revision-bound verification, chained receipts, and auditable replay.
ci-cd provenance traceability human-in-the-loop devsecops software-assurance policy-enforcement policy-as-code source-available code-repair ai-governance auditability runtime-assurance ai-coding-agents model-routing controlled-execution evidence-bundles workspace-isolation ai-agent-safety pr-evidence
-
Updated
Sep 17, 2026 - Python
5-agent LangGraph system that autonomously resolves GitHub issues, benchmarked across single-agent baseline, paid API, and open-weight HPC configurations on SWE-bench Lite
-
Updated
Jun 19, 2026 - Python
Self-healing code reasoning engine. Detective → QA → Patcher closed loop on SWE-bench, with an RL layer that turns every reasoning trace into DPO training data.
python typescript reinforcement-learning pytest developer-tools autonomous-agents code-intelligence ai-engineering automated-debugging code-repair llm tree-of-thoughts llm-agents agentic-ai ai-coding-assistant swe-bench self-healing-code dpo-training reasoning-traces closed-loop-reasoning
-
Updated
Aug 21, 2026 - TypeScript
Execution-grounded reinforcement learning for software repair on SWE-bench
-
Updated
Sep 13, 2026 - Python
OpenEnv-based reinforcement learning environment for automated Python code debugging and repair.
python docker debugging machine-learning reinforcement-learning artificial-intelligence pytest fastapi code-repair openenv
-
Updated
Jun 22, 2026 - Python
Add this topic to your repo
To associate your repository with the code-repair topic, visit your repo's landing page and select "manage topics."