Prospector learns to navigate knowledge graphs for better scientific reasoning
Prospector: learning a compact graph traversal policy for scientific reasoning
Artificial IntelligenceComputation and LanguageMachine Learning
Summary
Answering complex scientific questions often requires sifting through large and specialized collections of knowledge that big language models don't fully know. The authors created a smaller model called Prospector that moves step-by-step through a knowledge graph, gathering evidence carefully and building a clear reasoning chain. This model works well on semiconductor data and even adapts to other scientific fields without retraining. It runs efficiently on normal GPUs, letting companies keep their sensitive data private while getting solid answers.
What this means in practice
- •For engineering teams: Build efficient reasoning tools that retrieve and verify domain knowledge from private knowledge graphs during scientific problem solving.
- •For materials science developers: Develop specialized assistants that can interpret and navigate knowledge graphs for improved understanding of materials properties and bio-inspired materials.
Authors
Haiqian Yang, Markus J. Buehler
Abstract
Scientific reasoning in specialized engineering fields depends on knowledge scattered across the literature, often proprietary and absent from frontier LLM training data. In such domains, frontier models tend to give generic answers. Knowledge graphs (KGs) can ground LLM reasoning. Because a graph is too large to provide in full, typical LLM+KG systems preselect a portion, deciding relevance before reasoning begins. Here we train a compact model, Prospector, to reason over a domain knowledge graph by traversing it step by step, seeking evidence in light of what it has already found. Prospector calls a small set of tools one at a time to progressively build its context, and answers with a chain of evidence that can be checked edge by edge against what its tools retrieved from the graph. On a knowledge graph built from the semiconductor-manufacturing literature, Prospector approaches the strongest off-the-shelf models given the same graph and tools, and it far exceeds off-the-shelf models answering closed-book or from a pre-selected portion of the graph. Although trained only on the semiconductor graph, Prospector transfers to unseen knowledge graphs from three other distinct fields: bio-inspired materials, per- and polyfluoroalkyl substances (PFAS) and materials properties. Served on a single GPU, Prospector answers faster and at a fraction of the cost of a hosted service, while keeping proprietary data on the owner's hardware. We find that the policy's latent state is indicative of its next move on both seen and unseen graphs, and modulating the latent state can steer the policy from one behavior mode to another. These results suggest a practical LLM + KG paradigm for scientific and engineering reasoning over private data, in which a compact model trained on a graph from published literature transfers its traversal to unseen graphs that stay with their owners.