CODESIM: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and Debugging
Paper
•
2502.05664
•
Published
•
24
Code Agent
-
-
AgentCoder: Multi-Agent-based Code Generation with Iterative Testing and Optimisation
Paper • 2312.13010 • Published • 6 -
HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale
Paper • 2409.16299 • Published • 12 -
Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AI
Paper • 2505.19443 • Published • 15 -
GSO: Challenging Software Optimization Tasks for Evaluating SWE-Agents
Paper • 2505.23671 • Published • 3 -
SWE-Flow: Synthesizing Software Engineering Data in a Test-Driven Manner
Paper • 2506.09003 • Published • 18 -
Skywork-SWE: Unveiling Data Scaling Laws for Software Engineering in LLMs
Paper • 2506.19290 • Published • 52 -
SWE-Perf: Can Language Models Optimize Code Performance on Real-World Repositories?
Paper • 2507.12415 • Published • 42 -
GitChameleon: Evaluating AI Code Generation Against Python Library Version Incompatibilities
Paper • 2507.12367 • Published • 6 -
SWE-Exp: Experience-Driven Software Issue Resolution
Paper • 2507.23361 • Published • 13 -
SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution
Paper • 2507.23348 • Published • 11 -
GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
Paper • 2508.06471 • Published • 181 -
CoAct-1: Computer-using Agents with Coding as Actions
Paper • 2508.03923 • Published • 14 -
Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning
Paper • 2508.03501 • Published • 56 -
Agentic Software Engineering: Foundational Pillars and a Research Roadmap
Paper • 2509.06216 • Published • 7 -
SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
Paper • 2509.16941 • Published • 19