AIBullisharXiv – CS AI · May 127/10
🧠Researchers introduce NEXUS, a framework enabling embodied AI agents to learn symbolic constraints for safer decision-making in physical environments. The system addresses the gap between probabilistic language models and the deterministic safety requirements of robotics by decoupling physical feasibility from safety specifications, achieving improved task success while refusing unsafe instructions.
AIBullisharXiv – CS AI · Apr 147/10
🧠Researchers introduce a framework that automatically learns context-sensitive constraints from LLM interactions, eliminating the need for manual specification while ensuring perfect constraint adherence during generation. The method enables even 1B-parameter models to outperform larger models and state-of-the-art reasoning systems in constraint-compliant generation.
AINeutralarXiv – CS AI · Jun 26/10
🧠Researchers introduce Repair-Augmented Constraint Learning (RACL), a machine learning framework that decides whether to repair constraint violations before rejecting candidates, rather than applying hard vetoes immediately. The method achieves significantly lower false-veto rates (0.25%) compared to baseline approaches (26.4%) on real-world airline data, with applications to automated decision systems.
AINeutralarXiv – CS AI · Jun 26/10
🧠Researchers introduce Physics-Informed Deep Learning (PIDL), a unified neural framework that enforces both differential equations and thermodynamic constraints simultaneously across different physical domains. The framework demonstrates exceptional data efficiency and zero Second Law violations in both thermodynamic and financial modeling applications.
AINeutralarXiv – CS AI · Jun 16/10
🧠Researchers propose a Neuro-Symbolic Predictive Process Monitoring approach that combines deep learning with Linear Temporal Logic constraints to improve suffix prediction accuracy in business process management. The method introduces a differentiable logical loss function that ensures generated sequences satisfy both predictive accuracy and temporal logic constraints, with applications extending beyond BPM to general symbolic sequence generation tasks.
AIBullisharXiv – CS AI · May 286/10
🧠Researchers propose Palla, an algorithm that learns symbolic constraint functions called prefix filters to capture and correct systematic error patterns in large language models. By analyzing domain-specific failures (e.g., using Python syntax in TypeScript code), Palla enables constrained sampling to significantly improve compilation rates and output validity without retraining models.
🧠 Llama
AINeutralarXiv – CS AI · May 275/10
🧠Researchers present a framework for managing uncertainty in language model-generated laboratory procedures for virtual educational environments. The system uses structured domain representations and LLM outputs to extract, validate, and repair procedural steps, addressing common LLM failures like missing actions, incorrect sequencing, and logical incompatibilities.
AINeutralarXiv – CS AI · May 276/10
🧠Researchers propose a two-stage adapter that constrains tabular foundation model predictions within economic theory frameworks, ensuring price-demand relationships remain logically consistent while recovering accuracy gains over standard choice models. The approach achieves up to 13 percentage points of accuracy improvement on transportation datasets while guaranteeing economic validity—a problem raw foundation models fail to solve.
AINeutralarXiv – CS AI · May 116/10
🧠Researchers propose Direct Reasoning Optimization (DRO), a constrained reinforcement learning framework that improves LLM training on unverifiable tasks by combining token-level reasoning rewards with rubric-based feasibility gates. The approach demonstrates faster, more sample-efficient learning across scientific, medical, legal, and financial domains.
AINeutralarXiv – CS AI · Mar 27/1013
🧠Researchers propose SafeQIL, a new Q-learning algorithm that learns safe policies from expert demonstrations in constrained environments where safety constraints are unknown. The approach balances maximizing task rewards while maintaining safety by learning from demonstrated trajectories that successfully complete tasks without violating hidden constraints.
