Papers

• SWE-rebench V2: Language-Agnostic SWE Task Collection at Scale (2026)
  Ibragim Badertdinov et al.
  1.94
• ProRL Agent: Rollout-as-a-Service for RL Training of Multi-Turn LLM Agents (2026)
  Hao Zhang et al.
  1.94
• SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents (2026)
  Bingchen Zhao et al.
  1.94
• TUA-Bench: A Benchmark for General-Purpose Terminal-Use Agents (2026)
  Shoufa Chen et al.
  1.94
• SWE-INTERACT: Reimagining SWE Benchmarks as User-Driven Long-Horizon Coding Sessions (2026)
  Mohit Raghavendra et al.
  1.94
• Programming with Data: Test-Driven Data Engineering for Self-Improving LLMs from Raw Corpora (2026)
  Chenkai Pan et al.
  1.83
• Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis (2025)
  Tianbao Xie et al.
  1.28
• Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks (2025)
  Hongyuan Tao et al.
  1.28
• RExBench: Can coding agents autonomously implement AI research extensions? (2025)
  Nicholas Edwards et al.
  1.28
• SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution (2025)
  Han Li et al.
  1.28
• Tool-integrated Reinforcement Learning for Repo Deep Search (2025)
  Zexiong Ma et al.
  1.28
• VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use (2025)
  Dongfu Jiang et al.
  1.28
• Agent Data Protocol: Unifying Datasets for Diverse, Effective Fine-tuning of LLM Agents (2025)
  Yueqi Song et al.
  1.28
• Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning (2025)
  Yihe Deng et al.
  1.28
• Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents (2024)
  Kexun Zhang et al.
  —
• Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale (2024)
  Rogerio Bonatti et al.
  —
• HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale (2024)
  Huy Nhat Phan et al.
  —
• CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding Capabilities of CodeLLMs (2024)
  Dung Nguyen Manh et al.
  —