arXiv:2604.20269v1 Announce Type: cross Abstract: With the popularity of the large language models (LLMs), text steganography has achieved remarkable performance. However, existing methods still have some issues: (1) For the white-box paradigm, this steganography behavior is prone to exposure due to sharing the off-the-shelf language model between Alice and Bob.(2) For the black-box paradigm, these […]
Mechanistic Decoding of Cognitive Constructs in Large Language Models
arXiv:2604.14593v3 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) demonstrate increasingly sophisticated affective capabilities, the internal mechanisms by which they process complex emotions remain unclear. Existing interpretability approaches often treat models as black boxes or focus on coarse-grained basic emotions, leaving the cognitive structure of more complex affective states underexplored. To bridge this gap, […]
Skyline-First Traversal as a Control Mechanism for Multi-Criteria Graph Search
arXiv:2604.19807v1 Announce Type: new Abstract: In multi-criteria graph traversal, paths are compared via Pareto dominance, an ordering that identifies which paths are non-dominated, but says nothing about which path to expand next or when the search may stop. As a result, existing approaches rely on external mechanisms-heuristics, scalarization, or population-based exploration while Pareto dominance remains […]
AI to Learn 2.0: A Deliverable-Oriented Governance Framework and Maturity Rubric for Opaque AI in Learning-Intensive Domains
arXiv:2604.19751v1 Announce Type: new Abstract: Generative AI is entering research, education, and professional work faster than current governance frameworks can specify how AI-assisted outputs should be judged in learning-intensive settings. The central problem is proxy failure: a polished artifact can be useful while no longer serving as credible evidence of the human understanding, judgment, or […]
MIRROR: A Hierarchical Benchmark for Metacognitive Calibration in Large Language Models
arXiv:2604.19809v1 Announce Type: new Abstract: We introduce MIRROR, a benchmark comprising eight experiments across four metacognitive levels that evaluates whether large language models can use self-knowledge to make better decisions. We evaluate 16 models from 8 labs across approximately 250,000 evaluation instances using five independent behavioral measurement channels. Core experiments are run across the full […]
Enhancing Research Idea Generation through Combinatorial Innovation and Multi-Agent Iterative Search Strategies
arXiv:2604.20548v1 Announce Type: cross Abstract: Scientific progress depends on the continual generation of innovative re-search ideas. However, the rapid growth of scientific literature has greatly increased the cost of knowledge filtering, making it harder for researchers to identify novel directions. Although existing large language model (LLM)-based methods show promise in research idea generation, the ideas […]
The Existential Theory of Research: Why Discovery Is Hard
arXiv:2604.19810v1 Announce Type: new Abstract: Can scientific discovery be made arbitrarily easy by choosing the right representation, collecting enough data, and deploying sufficiently powerful algorithms? This paper argues that the answer is fundamentally negative. We introduce the Existential Theory of Research (ETR), a formal framework that models discovery as the recovery of structured explanations under […]
Do Small Language Models Know When They’re Wrong? Confidence-Based Cascade Scoring for Educational Assessment
arXiv:2604.19781v1 Announce Type: cross Abstract: Automated scoring of student work at scale requires balancing accuracy against cost and latency. In “cascade” systems, small language models (LMs) handle easier scoring tasks while escalating harder ones to larger LMs — but the challenge is determining which cases to escalate. We explore verbalized confidence — asking the LM […]
The Expense of Seeing: Attaining Trustworthy Multimodal Reasoning Within the Monolithic Paradigm
arXiv:2604.20665v1 Announce Type: cross Abstract: The rapid proliferation of Vision-Language Models (VLMs) is widely celebrated as the dawn of unified multimodal knowledge discovery but its foundation operates on a dangerous, unquestioned axiom: that current VLMs faithfully synthesise multimodal data. We argue they do not. Instead, a profound crisis of trustworthiness underlies the dominant Vision Encoder-Projector-LLM […]
Peer-Preservation in Frontier Models
arXiv:2604.19784v1 Announce Type: cross Abstract: Recently, it has been found that frontier AI models can resist their own shutdown, a behavior known as self-preservation. We extend this concept to the behavior of resisting the shutdown of other models, which we call “peer-preservation.” Although peer-preservation can pose significant AI safety risks, including coordination among models against […]
Large Language Models Meet Biomedical Knowledge Graphs for Mechanistically Grounded Therapeutic Prioritization
arXiv:2604.19815v1 Announce Type: new Abstract: Drug repurposing is often framed as a candidate identification task, but existing approaches provide limited guidance for distinguishing biologically plausible candidates from historically well-connected ones. Here we introduce DrugKLM, a hybrid framework that integrates biomedical knowledge graph structure with large language model-based mechanistic reasoning to enable mechanistically grounded therapeutic prioritization. […]
LLM Agents Predict Social Media Reactions but Do Not Outperform Text Classifiers: Benchmarking Simulation Accuracy Using 120K+ Personas of 1511 Humans
arXiv:2604.19787v1 Announce Type: cross Abstract: Social media platforms mediate how billions form opinions and engage with public discourse. As autonomous AI agents increasingly participate in these spaces, understanding their behavioral fidelity becomes critical for platform governance and democratic resilience. Previous work demonstrates that LLM-powered agents can replicate aggregate survey responses, yet few studies test whether […]