AvalancheBench introduces a benchmark for data agents based on recovering a known latent world from observations, reporting that the best coding agent recovers only 26% on an e-commerce case.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DB 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
AvalancheBench: Evaluating Enterprise Data Agents Through Latent World Recovery
AvalancheBench introduces a benchmark for data agents based on recovering a known latent world from observations, reporting that the best coding agent recovers only 26% on an e-commerce case.