AXIS couples an LLM with a multi-agent simulator to produce counterfactual action explanations, and reports higher judged correctness and goal-prediction accuracy than baselines on ten autonomous-driving scenarios.
Lucas, Shay B
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Integrating Counterfactual Simulations with Language Models for Explaining Multi-Agent Behaviour
AXIS couples an LLM with a multi-agent simulator to produce counterfactual action explanations, and reports higher judged correctness and goal-prediction accuracy than baselines on ten autonomous-driving scenarios.