arXiv cs.AI· Haiqian Yang, Markus J. Buehler·· 13 小时前AI 评分42
Prospector：为科学推理学习紧凑图遍历策略
Prospector: learning a compact graph traversal policy for scientific reasoning
AI 导读
Prospector 是一个在领域知识图谱上逐步遍历、按已有发现寻找证据的紧凑模型，通过逐个调用少量工具渐进构建上下文，并给出可逐边核验的证据链。在半导体制造文献构建的知识图谱上，其表现接近同等图谱与工具条件下的最强现成模型，并远超闭卷或从预选子图作答的模型。该策略可迁移到生物启发材料、PFAS 和材料性质三个未见领域，单 GPU 部署时比托管服务更快、成本更低。
正文 · 原文
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.
| Subjects: | Artificial Intelligence (cs.AI); Materials Science (cond-mat.mtrl-sci); Computation and Language (cs.CL); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.37121 [cs.AI] |
| (or arXiv:2610.37121v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.37121 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Markus Buehler [view email]
[v1]
Tue, 27 Oct 2026 12:21:37 UTC (1,085 KB)
来源：arXiv cs.AI · arxiv.org