2026
Should I Have Expressed a Different Intent? Counterfactual Generation for LLM-Based Autonomous Control
ICML 2026poster
Large language model (LLM)-powered agents can translate high-level user intents into plans and actions in an environment. Yet after observing an outcome, users may wonder: What if I had phrased my intent differently? We introduce a framework that enables such counterfactual reasoning in agentic LLM-…