SERA uses LLM-driven failure analysis and scenario retrieval to select training scenarios for few-shot fine-tuning, improving simulated autonomous driving scores.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
From Failures to Fixes: LLM-Driven Scenario Repair for Self-Evolving Autonomous Driving
SERA uses LLM-driven failure analysis and scenario retrieval to select training scenarios for few-shot fine-tuning, improving simulated autonomous driving scores.