live-swe-agent
gpt-5_swebench_verified_traj
Live-SWE-agent: live, self-evolving software agent
Live-SWE-agent is the first live, runtime self-evolving software engineering agent that expands and revises its own capabilities on the fly while working on a real-world issue.
Our key insight is that software agents are themselves software systems, and modern LLM-based agents already possess the intrinsic capability to extend or modify their own behavior at runtime.
gpt-5-mini_swebench_verified_traj
Live-SWE-agent: live, self-evolving software agent
Live-SWE-agent is the first live, runtime self-evolving software engineering agent that expands and revises its own capabilities on the fly while working on a real-world issue.
Our key insight is that software agents are themselves software systems, and modern LLM-based agents already possess the intrinsic capability to extend or modify their own behavior at runtime.
claude-sonnet-4-5_swebench_verified_traj
Live-SWE-agent: live, self-evolving software agent
Live-SWE-agent is the first live, runtime self-evolving software engineering agent that expands and revises its own capabilities on the fly while working on a real-world issue.
Our key insight is that software agents are themselves software systems, and modern LLM-based agents already possess the intrinsic capability to extend or modify their own behavior at runtime.
claude-sonnet-4-5_swebench_pro_traj
Live-SWE-agent: live, self-evolving software agent
Live-SWE-agent is the first live, runtime self-evolving software engineering agent that expands and revises its own capabilities on the fly while working on a real-world issue.
Our key insight is that software agents are themselves software systems, and modern LLM-based agents already possess the intrinsic capability to extend or modify their own behavior at runtime.
livesweagent-devstral2-123b-swebench-verified
Live-SWE-agent + Devstral 2 (123B) SWE-bench Verified Trajectories
This dataset contains agent trajectories from running Devstral 2 (123B) via OpenRouter on the SWE-bench Verified benchmark using the Live-SWE-agent framework.
⚠️ Framework Note
This run uses Live-SWE-agent, NOT standard mini-swe-agent. Live-SWE-agent is a self-evolving agent framework that encourages the model to create custom Python tools during runtime.
Key differences from mini-swe-agent:
Self-evolving… See the full description on the dataset page: https://huggingface.co/datasets/pankajmathur/livesweagent-devstral2-123b-swebench-verified.gemini_3_pro_swebench_verified_traj
Live-SWE-agent: live, self-evolving software agent
Live-SWE-agent is the first live, runtime self-evolving software engineering agent that expands and revises its own capabilities on the fly while working on a real-world issue.
Our key insight is that software agents are themselves software systems, and modern LLM-based agents already possess the intrinsic capability to extend or modify their own behavior at runtime.