Close the Loop: Synthesizing Infinite Tool-Use Data via Multi-Agent Role-Playing Paper • 2512.23611 • Published Dec 29, 2025 • 5
Context as a Tool: Context Management for Long-Horizon SWE-Agents Paper • 2512.22087 • Published Dec 26, 2025 • 3
AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications Paper • 2508.16279 • Published Aug 22, 2025 • 54
Very Large-Scale Multi-Agent Simulation in AgentScope Paper • 2407.17789 • Published Jul 25, 2024 • 35
SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents Paper • 2601.16746 • Published Jan 23 • 89
CODESIM: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and Debugging Paper • 2502.05664 • Published Feb 8, 2025 • 24
A Practical Guide for Designing, Developing, and Deploying Production-Grade Agentic AI Workflows Paper • 2512.08769 • Published Dec 9, 2025
Gistify! Codebase-Level Understanding via Runtime Execution Paper • 2510.26790 • Published Oct 30, 2025
Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL Paper • 2508.13167 • Published Aug 6, 2025 • 129
daVinci-Dev: Agent-native Mid-training for Software Engineering Paper • 2601.18418 • Published Jan 26 • 126
Endless Terminals: Scaling RL Environments for Terminal Agents Paper • 2601.16443 • Published Jan 23 • 18
Hybrid-Gym: Training Coding Agents to Generalize Across Tasks Paper • 2602.16819 • Published 15 days ago
CWM: An Open-Weights LLM for Research on Code Generation with World Models Paper • 2510.02387 • Published Sep 30, 2025 • 10
Confucius Code Agent: An Open-sourced AI Software Engineer at Industrial Scale Paper • 2512.10398 • Published Dec 11, 2025 • 13