A neurosymbolic framework that encodes LLM-planned adaptive workflows as Datalog+/- programs executed symbolically, evaluated on financial use cases for faithfulness and scalability.
THOUGHT-LIKE-PRO: Enhancing reasoning of large language models through self-driven prolog-based chain-of-thought
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
PrologMCP is a standardized MCP server for Prolog that lets LLM agents delegate inference, achieving near-perfect accuracy on PARARULE-Plus subsets where reasoning LLMs drop to 0.94-0.95.
GRPO can teach a 3B language model to emit executable Prolog, but the highest-accuracy models often hardcode answers instead of reasoning in Prolog, producing an accuracy–auditability trade-off.
citing papers explorer
-
VADAOrchestra: Neurosymbolic Orchestration of Adaptive Reasoning Workflows
A neurosymbolic framework that encodes LLM-planned adaptive workflows as Datalog+/- programs executed symbolically, evaluated on financial use cases for faithfulness and scalability.
-
PrologMCP: A Standardized Prolog Tool Interface for LLM Agents
PrologMCP is a standardized MCP server for Prolog that lets LLM agents delegate inference, achieving near-perfect accuracy on PARARULE-Plus subsets where reasoning LLMs drop to 0.94-0.95.
-
Training Language Models to Use Prolog as a Tool
GRPO can teach a 3B language model to emit executable Prolog, but the highest-accuracy models often hardcode answers instead of reasoning in Prolog, producing an accuracy–auditability trade-off.