analytical and problem-solving skills

Modeling the structural representation of scientific methodology units and their cross-problem recombination mechanisms remains challenging, particularly in identifying common patterns among historically disruptive method combinations and discovering high-potential knowledge recombination pathways for novel problems. Method: We propose a novel framework comprising (1) contrastive learning to automatically extract structured representations of disruptive method combinations from multi-domain scientific literature, and (2) a reasoning-guided Monte Carlo search algorithm that integrates large language model (LLM)-based chain-of-thought reasoning with empirically derived historical innovation patterns to enable interpretable, goal-directed knowledge recombination. Contribution/Results: Empirical evaluation across physics, biology, and artificial intelligence demonstrates that our framework accurately identifies method combinations with high disruptive potential and significantly advances the modeling and predictive capability of scientific innovation dynamics—achieving improved fidelity in capturing structural evolution and recombination efficacy in scientific discovery processes.

This study addresses a critical limitation in current AI research systems, which often treat hypotheses as endpoints rather than active drivers of the investigative process. To overcome this, the authors propose Hypothesis-Driven Deep Research (HDRI), a novel methodology that centers structured hypotheses as the organizing principle for cross-domain in-depth inquiry. The framework incorporates a gap-driven iterative mechanism, traceable reasoning chains, entity anchoring, and a multidimensional quality assessment system. Implemented via the INFOMINER system built on large language models, HDRI integrates gap identification, factual reasoning, confidence propagation, entity disambiguation, and multi-source verification. Experimental results demonstrate a 22.4% increase in factual density, 90% entity-matching accuracy, a multi-source verification confidence score of 0.92, 14% improvement in completeness, and an average case quality rating of 4.46 out of 5.0.

Social science research urgently requires interpretable and reproducible exploratory discovery from unstructured text—without presupposing measurement constructs. This paper proposes an end-to-end framework addressing this challenge. First, it constructs a high-dimensional, semantically transparent, and interpretable concept dictionary via sparse coding and semantic modeling. Second, it introduces a novel high-dimensional multiple testing procedure that rigorously controls the k-familywise error rate (k-FWER) under arbitrary variable dependence, substantially reducing researcher degrees of freedom. Third, it integrates machine learning interpretability techniques with selective inference to ensure statistical validity. The method is empirically validated in economic analyses—both causal and descriptive—and is accompanied by an open-source Jupyter toolkit, enabling low-cost, fully reproducible empirical workflows.

This study addresses the narrow scope of purely theory- or data-driven approaches in AI-assisted innovation by proposing the first LLM-based hypothesis generation framework that jointly leverages scholarly literature and empirical data. Methodologically, it introduces a novel dual-source synergy mechanism integrating literature semantic parsing with multi-source data alignment, augmented by domain-specific prompt engineering and rigorous human evaluation. Key contributions include: (1) establishing the first theory- and data-coordinated paradigm for automated hypothesis generation; (2) achieving statistically significant improvements in hypothesis quality—+8.97% over few-shot baselines, +15.75% over literature-only methods, and +3.37% over data-only methods—across five benchmark datasets; and (3) demonstrating via human evaluation that the framework substantially enhances decision-making accuracy in AI-content identification tasks, with gains ranging from 7.44% to 14.19%.

Business professionals—non-technical domain experts—lack appropriate tools and methodologies for effective what-if analysis (WIA), hindering data-informed decision-making. Method: We conducted a two-phase mixed-methods user study—comprising contextual interviews and in-situ task-based evaluations—to systematically characterize their analytical behaviors for the first time. Contribution/Results: Based on empirical findings, we propose three domain-grounded design principles: business-contextual data preparation, risk-aware assessment, and domain-knowledge integration. We implemented and validated these principles in an interactive visual analytics prototype. The study identifies three critical support gaps, empirically confirms that six classes of what-if techniques significantly improve decision efficiency and confidence, and yields eight actionable design guidelines for commercial business intelligence systems. This work bridges a key theoretical and practical gap in WIA research concerning non-technical users.

Scientific creativity generation is often oversimplified, lacking effective modeling of systematic thinking. This work proposes SCISENSE, a novel framework that introduces constrained sensemaking into the scientific ideation process, formalizing it into eight cognitive stages. The authors construct SCISENSE-Traj, a large-scale dataset, and train SCISENSE-LM—a suite of large language models spanning 3B to 70B parameters—using citation-conditioned trajectory reconstruction, reasoning, and model distillation. Remarkably, Target-mode training enhances both novelty and diversity of generated content (+2.0% trajectory quality) while maintaining goal-directedness, thereby significantly improving the quality of executable scientific artifacts produced by downstream agents. These findings challenge the conventional assumption that looser supervision better facilitates exploratory creativity.

This study addresses a critical limitation in traditional reproducible research, where sharing only code and results fails to expose the implicit assumptions, expectations, and premises underlying an analyst’s reasoning—thereby hindering thorough evaluation of analytical quality. To overcome this, the paper proposes a formal modeling framework that explicitly translates the analyst’s tacit reasoning process into structured logical representations, statically capturing the construction logic of the analysis. This approach enables systematic scrutiny of the analytical chain of reasoning, assumption sensitivity, and conclusion robustness—even in the absence of the original data. Empirical validation on representative data analysis tasks demonstrates the framework’s effectiveness, achieving both logical visualization and data-free static assessment of analytical integrity.

Empirical research often yields conflicting conclusions due to variations in analytical workflows, yet traditional multi-team replication efforts are costly and difficult to scale. This work proposes an autonomous AI analyst framework powered by large language models that, on a fixed dataset, generates diverse analytical pathways through varied prompts and model configurations. An integrated AI auditing mechanism filters out invalid analyses, enabling the first low-cost, large-scale simulation of human analytical diversity. The approach systematically reveals how preprocessing choices, modeling strategies, and inference procedures substantially influence effect sizes, p-values, and hypothesis support judgments. Furthermore, it demonstrates that analytical outcomes can be steered by modulating the AI’s role or underlying model, while remaining robust after excluding invalid analyses.

This study addresses the persistent gap between knowledge and action in biodiversity conservation by proposing an action-oriented, assertion-centered knowledge infrastructure. The framework introduces “action units” as structured extensions of planning specifications, explicitly modeling applicability conditions and contextual anchoring to support cognitive, translational, and interventional operations. Native decision support is achieved through composable, executable IF-THEN rules embedded within knowledge graphs. The work makes a novel distinction between “actionability” and “applicability” and advances the TripleA principles—Actionability, Applicability, and Auditability—to drive the evolution of knowledge infrastructures beyond the FAIR paradigm toward post-FAIR approaches. Case studies demonstrate that the structural integrity of action units is critical for effective implementation and confirm their potential as a general-purpose mechanism for decision support.