Memory Dial: A Training Framework for Controllable Memorization in Language Models
arXiv:2604.05074v1 Announce Type: new Abstract: Memorization in language models is widely studied but remains difficult to isolate and control. Understanding when and what models memorize is essential for explaining their predictions, yet existing approaches are post-hoc: they can detect memorization...
Beneath the Surface: Investigating LLMs' Capabilities for Communicating with Subtext
arXiv:2604.05273v1 Announce Type: new Abstract: Human communication is fundamentally creative, and often makes use of subtext -- implied meaning that goes beyond the literal content of the text. Here, we systematically study whether language models can use subtext in communicative...
Thinking Diffusion: Penalize and Guide Visual-Grounded Reasoning in Diffusion Multimodal Language Models
arXiv:2604.05497v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) are emerging as promising alternatives to autoregressive (AR) LLMs. Recently, this paradigm has been extended to multimodal tasks, leading to the development of diffusion multimodal large language models (dMLLMs). These...
AutoSOTA: An End-to-End Automated Research System for State-of-the-Art AI Model Discovery
arXiv:2604.05550v1 Announce Type: new Abstract: Artificial intelligence research increasingly depends on prolonged cycles of reproduction, debugging, and iterative refinement to achieve State-Of-The-Art (SOTA) performance, creating a growing need for systems that can accelerate the full pipeline of empirical model optimization....
Pramana: Fine-Tuning Large Language Models for Epistemic Reasoning through Navya-Nyaya
arXiv:2604.04937v1 Announce Type: new Abstract: Large language models produce fluent text but struggle with systematic reasoning, often hallucinating confident but unfounded claims. When Apple researchers added irrelevant context to mathematical problems, LLM performance degraded by 65% Apple Machine Learning Research,...
Auditable Agents
arXiv:2604.05485v1 Announce Type: new Abstract: LLM agents call tools, query databases, delegate tasks, and trigger external side effects. Once an agent system can act in the world, the question is no longer only whether harmful actions can be prevented--it is...
Non-monotonic causal discovery with Kolmogorov-Arnold Fuzzy Cognitive Maps
arXiv:2604.05136v1 Announce Type: new Abstract: Fuzzy Cognitive Maps constitute a neuro-symbolic paradigm for modeling complex dynamic systems, widely adopted for their inherent interpretability and recurrent inference capabilities. However, the standard FCM formulation, characterized by scalar synaptic weights and monotonic activation...
The Illusion of Latent Generalization: Bi-directionality and the Reversal Curse
arXiv:2604.04943v1 Announce Type: new Abstract: The reversal curse describes a failure of autoregressive language models to retrieve a fact in reverse order (e.g., training on ``$A > B$'' but failing on ``$B < A$''). Recent work shows that objectives with...
Do Domain-specific Experts exist in MoE-based LLMs?
arXiv:2604.05267v1 Announce Type: new Abstract: In the era of Large Language Models (LLMs), the Mixture of Experts (MoE) architecture has emerged as an effective approach for training extremely large models with improved computational efficiency. This success builds upon extensive prior...
DQA: Diagnostic Question Answering for IT Support
arXiv:2604.05350v1 Announce Type: new Abstract: Enterprise IT support interactions are fundamentally diagnostic: effective resolution requires iterative evidence gathering from ambiguous user reports to identify an underlying root cause. While retrieval-augmented generation (RAG) provides grounding through historical cases, standard multi-turn RAG...
Phase-Associative Memory: Sequence Modeling in Complex Hilbert Space
arXiv:2604.05030v1 Announce Type: new Abstract: We present Phase-Associative Memory (PAM), a recurrent sequence model in which all representations are complex-valued, associations accumulate in a matrix state $S_{t}$ $\in$ $\mathbb{C}^{d \times d}$ via outer products, and retrieval operates through the conjugate...
From Governance Norms to Enforceable Controls: A Layered Translation Method for Runtime Guardrails in Agentic AI
arXiv:2604.05229v1 Announce Type: new Abstract: Agentic AI systems plan, use tools, maintain state, and produce multi-step trajectories with external effects. Those properties create a governance problem that differs materially from single-turn generative AI: important risks emerge dur- ing execution, not...
Blind-Spot Mass: A Good-Turing Framework for Quantifying Deployment Coverage Risk in Machine Learning Systems
arXiv:2604.05057v1 Announce Type: new Abstract: Blind-spot mass is a Good-Turing framework for quantifying deployment coverage risk in machine learning. In modern ML systems, operational state distributions are often heavy-tailed, implying that a long tail of valid but rare states is...
The who, what, and where of gun control
A Second Opinion is a recurring series by Haley Proctor on the Second Amendment and constitutional litigation. My previous column examined what it means for a gun control measure to […]The postThe who, what, and where of gun controlappeared first...
Single-agent vs. Multi-agents for Automated Video Analysis of On-Screen Collaborative Learning Behaviors
arXiv:2604.03631v1 Announce Type: new Abstract: On-screen learning behavior provides valuable insights into how students seek, use, and create information during learning. Analyzing on-screen behavioral engagement is essential for capturing students' cognitive and collaborative processes. The recent development of Vision Language...
FeynmanBench: Benchmarking Multimodal LLMs on Diagrammatic Physics Reasoning
arXiv:2604.03893v1 Announce Type: new Abstract: Breakthroughs in frontier theory often depend on the combination of concrete diagrammatic notations with rigorous logic. While multimodal large language models (MLLMs) show promise in general scientific tasks, current benchmarks often focus on local information...
Beyond Retrieval: Modeling Confidence Decay and Deterministic Agentic Platforms in Generative Engine Optimization
arXiv:2604.03656v1 Announce Type: new Abstract: Generative Engine Optimization (GEO) is rapidly reshaping digital marketing paradigms in the era of Large Language Models (LLMs). However, current GEO strategies predominantly rely on Retrieval-Augmented Generation (RAG), which inherently suffers from probabilistic hallucinations and...
Comparative reversal learning reveals rigid adaptation in LLMs under non-stationary uncertainty
arXiv:2604.04182v1 Announce Type: new Abstract: Non-stationary environments require agents to revise previously learned action values when contingencies change. We treat large language models (LLMs) as sequential decision policies in a two-option probabilistic reversal-learning task with three latent states and switch...
A Model of Understanding in Deep Learning Systems
arXiv:2604.04171v1 Announce Type: new Abstract: I propose a model of systematic understanding, suitable for machine learning systems. On this account, an agent understands a property of a target system when it contains an adequate internal model that tracks real regularities,...
Solar-VLM: Multimodal Vision-Language Models for Augmented Solar Power Forecasting
arXiv:2604.04145v1 Announce Type: new Abstract: Photovoltaic (PV) power forecasting plays a critical role in power system dispatch and market participation. Because PV generation is highly sensitive to weather conditions and cloud motion, accurate forecasting requires effective modeling of complex spatiotemporal...
IC3-Evolve: Proof-/Witness-Gated Offline LLM-Driven Heuristic Evolution for IC3 Hardware Model Checking
arXiv:2604.03232v1 Announce Type: new Abstract: IC3, also known as property-directed reachability (PDR), is a commonly-used algorithm for hardware safety model checking. It checks if a state transition system complies with a given safety property. IC3 either returns UNSAFE (indicating property...
When Adaptive Rewards Hurt: Causal Probing and the Switching-Stability Dilemma in LLM-Guided LEO Satellite Scheduling
arXiv:2604.03562v1 Announce Type: new Abstract: Adaptive reward design for deep reinforcement learning (DRL) in multi-beam LEO satellite scheduling is motivated by the intuition that regime-aware reward weights should outperform static ones. We systematically test this intuition and uncover a switching-stability...
Align Your Structures: Generating Trajectories with Structure Pretraining for Molecular Dynamics
arXiv:2604.03911v1 Announce Type: new Abstract: Generating molecular dynamics (MD) trajectories using deep generative models has attracted increasing attention, yet remains inherently challenging due to the limited availability of MD data and the complexities involved in modeling high-dimensional MD distributions. To...
Neural Operators for Multi-Task Control and Adaptation
arXiv:2604.03449v1 Announce Type: new Abstract: Neural operator methods have emerged as powerful tools for learning mappings between infinite-dimensional function spaces, yet their potential in optimal control remains largely unexplored. We focus on multi-task control problems, whose solution is a mapping...
The Tool Illusion: Rethinking Tool Use in Web Agents
arXiv:2604.03465v1 Announce Type: new Abstract: As web agents rapidly evolve, an increasing body of work has moved beyond conventional atomic browser interactions and explored tool use as a higher-level action paradigm. Although prior studies have shown the promise of tools,...
Where to Steer: Input-Dependent Layer Selection for Steering Improves LLM Alignment
arXiv:2604.03867v1 Announce Type: new Abstract: Steering vectors have emerged as a lightweight and effective approach for aligning large language models (LLMs) at inference time, enabling modulation over model behaviors by shifting LLM representations towards a target behavior. However, existing methods...
Understanding When Poisson Log-Normal Models Outperform Penalized Poisson Regression for Microbiome Count Data
arXiv:2604.03853v1 Announce Type: new Abstract: Multivariate count models are often justified by their ability to capture latent dependence, but researchers receive little guidance on when this added structure improves on simpler penalized marginal Poisson regression. We study this question using...
FactReview: Evidence-Grounded Reviews with Literature Positioning and Execution-Based Claim Verification
arXiv:2604.04074v1 Announce Type: new Abstract: Peer review in machine learning is under growing pressure from rising submission volume and limited reviewer time. Most LLM-based reviewing systems read only the manuscript and generate comments from the paper's own narrative. This makes...
Representational Collapse in Multi-Agent LLM Committees: Measurement and Diversity-Aware Consensus
arXiv:2604.03809v1 Announce Type: new Abstract: Multi-agent LLM committees replicate the same model under different role prompts and aggregate outputs by majority vote, implicitly assuming that agents contribute complementary evidence. We embed each agent's chain-of-thought rationale and measure pairwise similarity: across...