LLM agents with validator-reprompting loops achieve 100% valid path recovery on random finite-state-machine benchmarks and temperature control close to PID on a lab dual-heater setup.
Title resolution pending
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
-
Autonomous Control Leveraging LLMs: An Agentic Framework for Next-Generation Industrial Automation
LLM agents with validator-reprompting loops achieve 100% valid path recovery on random finite-state-machine benchmarks and temperature control close to PID on a lab dual-heater setup.