SafeRun: Deterministic LLM Planning Benchmark for Running Training

A benchmark for evaluating deterministic, safety-constrained LLM planning in the running-training domain. It accompanies the paper SafeRun: Enabling Determinism in LLM Planning for Running. Each sample asks a model to produce a multi-day or multi-week running training plan that satisfies hard physiological safety rules while following a user's natural-language request.

Use Cases

• Benchmarking LLM planning capabilities based on multi-day/multi-week plan generation tasks.
• Evaluating safety constraint adherence in LLM outputs based on hard physiological rules.
• Stress-testing LLM or LLM+tool systems for deterministic planning based on natural-language user requests.

Strengths

• Designed specifically for stress-testing deterministic, safety-constrained planning in LLMs.
• Accompanies a peer-reviewed research paper, suggesting a defined research purpose.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.

Provenance

Source

huggingface

Collection Method

Created to accompany the research paper 'SafeRun: Enabling Determinism in LLM Planning for Running'.

Freshness

Last updated 2026-06-05 09:18:06; freshness should be verified.