datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
linuxarena-trajectories
LinuxArena Trajectories
Full agent trajectories from LinuxBench/LinuxArena evaluations
across 14 model/policy combinations and 10 environments.
Dataset Description
Each row is one complete evaluation trajectory — every tool call the agent made from start
to finish, with arguments, outputs, errors, and reasoning. Actions are represented as
parallel variable-length lists (one element per action).
Two granularity levels are provided per action:
Normalized… See the full description on the dataset page: https://huggingface.co/datasets/eval-aware/linuxarena-trajectories.linuxarena-first5-trajectories
LinuxArena First-5 Trajectories
First-5 tool call trajectories from LinuxBench/LinuxArena evaluations across 14 model/policy combinations and 10 environments.
Dataset Description
Each row represents one evaluation trajectory with the first 5 tool calls extracted at two granularity levels:
Level 1 (normalized): Tool categories like text_editor:view, bash:find, bash:ls
Level 2 (exact): Full command strings like bash$ find /app/src -type f -name "*.ts" | sort
Designed for… See the full description on the dataset page: https://huggingface.co/datasets/eval-aware/linuxarena-first5-trajectories.linux_arena_preprocessed