0

WordLadder

Fresh

WordLadder is an environment for evaluating agents on building word ladders by changing one letter at a time to transform a start word into an end word.

Type
RL Env
Runtime
TextArena
License
unknown
Size
900 tasks
Published
Mar 2026

Cite

Notes

Only stored in your browser.

WordLadder

OpenReward Environment

Description

WordLadder is an environment for evaluating agents on building word ladders by changing one letter at a time to transform a start word into an end word. This environment wraps the WordLadder implementation from TextArena, a framework for text-based game environments.

Capabilities

  • Building valid word transformation sequences
  • Vocabulary knowledge and word recognition
  • Path-finding in word networks
  • Testing sequential reasoning and planning

Compute Requirements

WordLadder does not require a sandbox. It has minimal compute requirements.

License

MIT.

Tasks

There are two splits: train (450 tasks) and test (450 tasks). Each split contains 50 tasks across each of 9 variants:

  • WordLadder-v0
  • WordLadder-v0-hard
  • WordLadder-v0-hard-raw
  • WordLadder-v0-hard-train
  • WordLadder-v0-medium
  • WordLadder-v0-medium-raw
  • WordLadder-v0-medium-train
  • WordLadder-v0-raw
  • WordLadder-v0-train

Each task is seeded for reproducibility.

Reward Structure

This is a sparse reward environment. Rewards are mapped from TextArena's native range of {-1, 0, 1} to {0.0, 0.5, 1.0} via (raw + 1) / 2.

We do not use LLM graders for this environment; reward is determined programmatically.

Data

Game state is generated procedurally by the TextArena engine using seeded randomness. No external data files are required.

Tools

Agents are given a single tool:

  • submit_word(word): Submit the next word in the ladder.

Time Horizon

WordLadder is a multi-turn environment.

Environment Difficulty

Medium to Hard. Word Ladder requires vocabulary knowledge, understanding of valid English words, and path-finding through word networks. Difficulty increases with longer optimal paths.

Other Environment Requirements

There are no further environment requirements; WordLadder works out of the box without any secrets or API keys.

Safety

Agents in WordLadder interact only with a word transformation puzzle and have no access to external systems, the internet, or sensitive data. The environment does not present safety risks.

Citations

@software{textarena2024,
  author    = {Guertler, Leon and Banting, Wilfried and Pignatelli, Eduardo},
  title     = {TextArena},
  year      = {2024},
  publisher = {GitHub},
  url       = {https://github.com/LeonGuertler/TextArena}
}