Close the Loop: Synthesizing Infinite Tool-Use Data via Multi-Agent Role-Playing
Paper
• 2512.23611 • Published
• 5
Agent Loops, Character, Work Ethics & Behavior
-
-
Context as a Tool: Context Management for Long-Horizon SWE-Agents
Paper • 2512.22087 • Published • 3 -
AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications
Paper • 2508.16279 • Published • 54 -
Very Large-Scale Multi-Agent Simulation in AgentScope
Paper • 2407.17789 • Published • 35 -
AutoDev: Automated AI-Driven Development
Paper • 2403.08299 • Published • 9 -
SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents
Paper • 2601.16746 • Published • 89 -
CODESIM: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and Debugging
Paper • 2502.05664 • Published • 24 -
A Practical Guide for Designing, Developing, and Deploying Production-Grade Agentic AI Workflows
Paper • 2512.08769 • Published -
Gistify! Codebase-Level Understanding via Runtime Execution
Paper • 2510.26790 • Published -
DeepCode: Open Agentic Coding
Paper • 2512.07921 • Published • 33 -
Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL
Paper • 2508.13167 • Published • 129 -
Qwen3-Coder-Next Technical Report
Paper • 2603.00729 • Published • 33 -
daVinci-Dev: Agent-native Mid-training for Software Engineering
Paper • 2601.18418 • Published • 126 -
GLM-5: from Vibe Coding to Agentic Engineering
Paper • 2602.15763 • Published • 105 -
Endless Terminals: Scaling RL Environments for Terminal Agents
Paper • 2601.16443 • Published • 18 -
Hybrid-Gym: Training Coding Agents to Generalize Across Tasks
Paper • 2602.16819 • Published -
CWM: An Open-Weights LLM for Research on Code Generation with World Models
Paper • 2510.02387 • Published • 10 -
Confucius Code Agent: An Open-sourced AI Software Engineer at Industrial Scale
Paper • 2512.10398 • Published • 13