Path-Constrained Retrieval: A Structural Approach to Reliable LLM Agent Reasoning Through Graph-Scoped Semantic Search

Large Language Model (LLM) agents have shown remarkable capabilities in reasoning and problem-solving when augmented with retrieval mechanisms [1, 2]. However, a critical challenge persists: ensuring that retrieved information maintains logical and structural consistency with the agent's current reasoning context. Traditional retrieval methods, such as vector similarity search, retrieve information based solely on semantic similarity, without considering structural relationships within knowledge bases. This limitation becomes particularly problematic in multi-hop reasoning scenarios, where an agent must traverse a knowledge graph to answer complex queries. When an agent is reasoning about a specific concept (the "anchor"), retrieving information from structurally disconnected parts of the knowledge graph can introduce inconsistencies and contradictions into the reasoning process. For example, if an agent is reasoning about "cloud computing architecture" starting from a specific node, retrieving information about unrelated topics that happen to be semantically similar can lead to incoherent reasoning chains due to lack of structural consistency. We propose Path-Constrained Retrieval (PCR), a retrieval method that enforces structural constraints by restricting the search space to nodes reachable from an anchor node in a knowledge graph.