EvoClaw:Evaluating AI Agents on Continuous Software Evolution
Long-running agents build customized software (a “Claw”) to interact with their environments. For practical use in complex, real-world tasks, these agents must fully and autonomously evolve this software in response to a continuous stream of end-user requirements. EvoClaw evaluates how well frontier LLM agents handle this continuous development, benchmarking them against real-world evolution itineraries from open-source repositories.
Overall Cost / Performance on EvoClaw
Leaderboard
| # | Model | Agent | Score (%) | Precision (%) | Recall (%) | Resolve (%) | Cost ($) | Out Tok. (K) | Time (h) | Turns |
|---|
