This paper proposes the trans-domain digital twin approach to connect heterogeneous domain twins through aligned shared state, explicit coupling, heterogeneous temporal coordination, joint decision-ma…

This paper proposes Workflow Cognition as a theoretical framework for explaining expertise as a dynamic cognitive phenomenon.

The paper introduces Rationalize, a role-pair framework that facilitates shared semantic reasoning between humans and AI models to achieve deep alignment of intent and action.

This paper documents and analyzes the failure process of strategies used to address conceptual drift in long-horizon LLM collaboration and introduces the concept of 'Index Sickness' and the 'Pang Prin…

This paper unifies the fragmented field of Tree-of-Thoughts (ToT) reasoning by mapping LLM-based search processes onto a formal taxonomy derived from classical heuristic search theory.

The paper introduces GeoCoupling, a framework that systematically optimizes the temporal coupling between heterogeneous modalities to improve the co-design of biomolecules, outperforming fixed synchro…

This paper challenges the claim that neural networks have met the challenge of systematicity in language and thought as proposed by Fodor and Pylyshyn, demonstrating limitations in a recent neural net…

This paper explores when language models (LMs) generate faithful introspection during explanation training, finding that LMs can produce more faithful explanations from earlier checkpoints or similar…

EvoGens is an evolution-inspired framework that treats scientific idea generation as an evolutionary search, significantly boosting the novelty and diversity of generated research ideas compared to ex…

This paper introduces the Data-Model Compatibility (DMC) metric to quantify how suitable a dataset is for reasoning distillation, showing that optimizing data selection using DMC significantly improve…

The paper introduces an ontology-driven framework, From Prompts to Context, to explicitly model and structure the often-opaque context of human-Generative AI collaborations, thereby improving traceabi…

The paper introduces COMPOSE, a dual-graph framework that generates plausible future mathematical theorems by simultaneously conditioning a language model on both the scientific citation context and t…

The paper proposes CoEvo-AHD, an LLM-driven co-evolutionary framework that co-evolves two coupled operator populations to design effective heuristics for combinatorial optimization problems with stron…

The paper investigates compositional abilities in LLMs and humans using the Personal Relation Task, finding that LLMs excel at the structured (Intensional) task while humans are better at the real-wor…

This paper proposes an efficient human intervention mechanism, Deep Interaction, for correcting reasoning errors in large language models, achieving over 25% improvement in correction success rate and…

The paper introduces ERUnderstand, a benchmark for structured understanding of Entity-Relationship Diagrams (ERDs) with machine-readable representations for 2,960 diagrams.

The paper proposes integrating dependent pattern matching into the unification process in dependently typed languages to synthesize functions defined by case analysis, addressing the limitation of exi…

The paper proposes CheckRLM, a framework that improves the reliability of Reasoning Language Models by identifying and correcting factual errors using Retrieval-Augmented Generation.