adp
diapason.evals.datasets.adp
¶
Agent Data Collection (neulab) — external agent-trajectory corpus.
NOT USED FOR EVALUATION. Surfaces multi-turn agent trajectories to the
LLM-guided spec search proposer via
diapason.learning.spec_search.external_adapter so the diagnose
phase can reason over a broad pool of agent traces without depending on
the per-cell student's own trace history.
HF dataset: neulab/agent-data-collection — a multi-config collection of
agent trajectory datasets (AgentTuning subsets, CodeAct, OpenHands, etc.).
Each config shares the same std split schema:
- id: trajectory identifier
- content: list-of-dicts with keys class_, source, content
- details: per-config metadata dict
Conversion to EvalRecord
problem: content of the first turn whosesource == "user"reference: content of the last turn whoseclass_ == "message_action"(the agent's final response/action), truncated to 2000 chars