Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual Recombination

• URL: http://arxiv.org/abs/2607.00924v1
• Date: Wed, 01 Jul 2026 13:26:10 GMT
• Title: Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual Recombination
• Abstract summary: Graph-PRefLexOR organizes reasoning into explicit phases for mechanism exploration, graph construction, pattern extraction, and hypothesis synthesis.<n>On 100 open-ended questions from materials science and mechanics literature, Graph-PRefLexOR achieves 40-65% improvements over corresponding base models.
• Score: 4.811614746460565
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Accelerating materials discovery requires AI systems that can generate scientifically valid hypotheses through multi-step, domain-grounded reasoning. Standard large language models often produce fluent but weakly traceable responses to open-ended materials design problems, making it difficult to determine whether final answers are supported by coherent intermediate reasoning. We develop Graph-PRefLexOR, a family of graph-native reasoning models fine-tuned with Group Relative Policy Optimization (GRPO) to organize reasoning into explicit phases for mechanism exploration, graph construction, pattern extraction, and hypothesis synthesis. This design links neural language generation with symbolic relational structure, enabling causal connections to be constructed, inspected, and reused. On 100 open-ended questions from materials science and mechanics literature, Graph-PRefLexOR achieves 40-65% improvements over corresponding base models, with the largest gains in reasoning traceability. Embedding analyses show broader semantic exploration and approximately 2-3 times greater semantic diversity than baselines. Semantic backtracking and layer-wise hidden-state analyses further show stronger alignment between structured reasoning and final answers. Finally, test-time graph expansion reveals that additional compute primarily increases long-range conceptual recombination within a bounded semantic space, rather than simply expanding semantic coverage. These results establish graph-native reinforcement learning as a pathway toward interpretable AI systems for scientific hypothesis generation in materials design and other scientific applications.

Related papers

• Topology of Reasoning: Retrieved Cell Complex-Augmented Generation for Textual Graph Question Answering [13.616604189732262]
  Topology-enhanced Retrieval-Augmented Generation (TopoRAG) is a novel framework for textual graph question answering.<n>TopoRAG first lifts textual graphs into cellular complexes to model multi-dimensional topological structures.<n>A multi-dimensional topological reasoning mechanism operates over these complexes to propagate relational information.
  arXiv  Detail & Related papers  (2026-02-22T15:44:53Z)
• Higher-Order Knowledge Representations for Agentic Scientific Reasoning [1.1458853556386797]
  We introduce a methodology for constructing hypergraph-based knowledge representations that faithfully encode multi-entity relationships.<n> Applied to a corpus of 1,100 manuscripts on biocomposite scaffolds, our framework constructs a global hypergraph of 161,172 nodes and 320,201 hyperedges.<n>We further demonstrate that equipping agentic systems with hypergraph tools, specifically using node-intersection constraints, enables them to bridge semantically distant concepts.
  arXiv  Detail & Related papers  (2026-01-08T12:25:37Z)
• Figure It Out: Improve the Frontier of Reasoning with Executable Visual States [53.77871196174248]
  Complex reasoning problems often involve implicit spatial and geometric relationships that are not explicitly encoded in text.<n>We introduce FIGR, which integrates executable visual construction into multi-turn reasoning via end-to-end reinforcement learning.<n>Experiments on eight challenging mathematical benchmarks demonstrate that FIGR outperforms strong text-only chain-of-thought baselines.
  arXiv  Detail & Related papers  (2025-12-30T15:39:11Z)
• SciNets: Graph-Constrained Multi-Hop Reasoning for Scientific Literature Synthesis [0.0]
  Cross-domain scientific synthesis requires connecting mechanistic explanations across fragmented literature.<n>We frame mechanistic synthesis as a graph-constrained multi-hop reasoning problem over literature-derived concept graphs.
  arXiv  Detail & Related papers  (2025-12-28T12:27:42Z)
• Unifying Deductive and Abductive Reasoning in Knowledge Graphs with Masked Diffusion Model [64.31242163019242]
  Deductive and abductive reasoning are critical paradigms for analyzing knowledge graphs.<n>We propose a unified framework for Deductive and Abductive Reasoning in Knowledge graphs, called DARK.<n>We show that DARK achieves state-of-the-art performance on both deductive and abductive reasoning tasks.
  arXiv  Detail & Related papers  (2025-10-13T14:34:57Z)
• Explain Before You Answer: A Survey on Compositional Visual Reasoning [74.27548620675748]
  Compositional visual reasoning has emerged as a key research frontier in multimodal AI.<n>This survey systematically reviews 260+ papers from top venues (CVPR, ICCV, NeurIPS, ICML, ACL, etc.)<n>We then catalog 60+ benchmarks and corresponding metrics that probe compositional visual reasoning along dimensions such as grounding accuracy, chain-of-thought faithfulness, and high-resolution perception.
  arXiv  Detail & Related papers  (2025-08-24T11:01:51Z)
• A Survey on Latent Reasoning [100.54120559169735]
  Large Language Models (LLMs) have demonstrated impressive reasoning capabilities.<n>CoT reasoning that verbalizes intermediate steps limits the model's expressive bandwidth.<n>Latent reasoning tackles this bottleneck by performing multi-step inference entirely in the model's continuous hidden state.
  arXiv  Detail & Related papers  (2025-07-08T17:29:07Z)
• Controllable Logical Hypothesis Generation for Abductive Reasoning in Knowledge Graphs [54.596180382762036]
  Abductive reasoning in knowledge graphs aims to generate plausible logical hypotheses from observed entities.<n>Due to a lack of controllability, a single observation may yield numerous plausible but redundant or irrelevant hypotheses.<n>We introduce the task of controllable hypothesis generation to improve the practical utility of abductive reasoning.
  arXiv  Detail & Related papers  (2025-05-27T09:36:47Z)
• In-situ graph reasoning and knowledge expansion using Graph-PReFLexOR [0.0]
  We present Graph-PReFLexOR, a framework that combines graph reasoning with symbolic abstraction to dynamically expand domain knowledge.<n>Inspired by reinforcement learning, it defines reasoning as a structured mapping, where tasks yield knowledge graphs, abstract patterns, and ultimately, final answers.<n>Results show superior reasoning depth and adaptability, underscoring the potential for transparent, multidisciplinary AI-driven discovery.
  arXiv  Detail & Related papers  (2025-01-14T13:52:41Z)
• Graph Stochastic Neural Process for Inductive Few-shot Knowledge Graph Completion [63.68647582680998]
  We focus on a task called inductive few-shot knowledge graph completion (I-FKGC) Inspired by the idea of inductive reasoning, we cast I-FKGC as an inductive reasoning problem. We present a neural process-based hypothesis extractor that models the joint distribution of hypothesis, from which we can sample a hypothesis for predictions. In the second module, based on the hypothesis, we propose a graph attention-based predictor to test if the triple in the query set aligns with the extracted hypothesis.
  arXiv  Detail & Related papers  (2024-08-03T13:37:40Z)
• G-SAP: Graph-based Structure-Aware Prompt Learning over Heterogeneous Knowledge for Commonsense Reasoning [8.02547453169677]
  We propose a novel Graph-based Structure-Aware Prompt Learning Model for commonsense reasoning, named G-SAP. In particular, an evidence graph is constructed by integrating multiple knowledge sources, i.e. ConceptNet, Wikipedia, and Cambridge Dictionary. The results reveal a significant advancement over the existing models, especially, with 6.12% improvement over the SoTA LM+GNNs model on the OpenbookQA dataset.
  arXiv  Detail & Related papers  (2024-05-09T08:28:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.