P4IR applies supervised fine-tuning followed by GRPO reinforcement learning to reduce tree edit distance by up to 23.8% and Levenshtein distance by up to 38.6% versus SFT baselines while outperforming several frontier LLMs on code structure and semantics for automated building code compliance.
Shields, and Lori Graham-Brady
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A multi-agent system combining contextual bandits, LLM agents, and semantic checkpoints improves convergence and robustness in adaptive method selection for sensitivity analysis and uncertainty quantification.
citing papers explorer
-
Reinforcement learning to improve large language model-based automated code compliance systems
P4IR applies supervised fine-tuning followed by GRPO reinforcement learning to reduce tree edit distance by up to 23.8% and Levenshtein distance by up to 38.6% versus SFT baselines while outperforming several frontier LLMs on code structure and semantics for automated building code compliance.
-
Learning to Choose: An Empowerment-Guided Multi-Agent System with semantic communication for Adaptive Method Selection
A multi-agent system combining contextual bandits, LLM agents, and semantic checkpoints improves convergence and robustness in adaptive method selection for sensitivity analysis and uncertainty quantification.