arXiv:2604.14430v1 Announce Type: cross Abstract: We present Three-Phase Transformer (3PT), a residual-stream structural prior for decoder-only Transformers on a standard SwiGLU + RMSNorm + RoPE + GQA backbone. The hidden vector is partitioned into N equally-sized cyclic channels, each maintained by phase-respecting ops: a per-channel RMSNorm, a 2D Givens rotation between attention and FFN that […]
Hybrid Decision Making via Conformal VLM-generated Guidance
arXiv:2604.14980v1 Announce Type: new Abstract: Building on recent advances in AI, hybrid decision making (HDM) holds the promise of improving human decision quality and reducing cognitive load. We work in the context of learning to guide (LtG), a recently proposed HDM framework in which the human is always responsible for the final decision: rather than […]
Unity and Diversity of Intracellular pH Maintenance Mechanisms
arXiv:2604.15296v1 Announce Type: new Abstract: All cells must sustain ionic motive forces (IMFs) — the electrochemical gradients of permeant ions, together with the membrane potential they produce — to regulate intracellular pH, drive secondary transport, and power ATP synthesis. Because membranes are imperfectly impermeable, IMFs continuously dissipate through passive leakage, and active transport must compensate […]
Learning to Draw ASCII Improves Spatial Reasoning in Language Models
arXiv:2604.14641v1 Announce Type: new Abstract: When faced with complex spatial problems, humans naturally sketch layouts to organize their thinking, and the act of drawing further sharpens their understanding. In this work, we ask whether a similar principle holds for Large Language Models (LLMs): can learning to construct explicit visual layouts from spatial descriptions instill genuine […]
Acceptance Dynamics Across Cognitive Domains in Speculative Decoding
arXiv:2604.14682v1 Announce Type: new Abstract: Speculative decoding accelerates large language model (LLM) inference. It uses a small draft model to propose a tree of future tokens. A larger target model then verifies these tokens in a single batched forward pass. Despite the growing body of work on speculative methods, the degree to which the cognitive […]
MARS$^2$: Scaling Multi-Agent Tree Search via Reinforcement Learning for Code Generation
arXiv:2604.14564v1 Announce Type: new Abstract: Reinforcement learning (RL) paradigms have demonstrated strong performance on reasoning-intensive tasks such as code generation. However, limited trajectory diversity often leads to diminishing returns, which constrains the achievable performance ceiling. Search-enhanced RL alleviates this issue by introducing structured exploration, which remains constrained by the single-agent policy priors. Meanwhile, leveraging multiple […]
GDPR Auto-Formalization with AI Agents and Human Verification
arXiv:2604.14607v1 Announce Type: new Abstract: We study the overall process of automatic formalization of GDPR provisions using large language models, within a human-in-the-loop verification framework. Rather than aiming for full autonomy, we adopt a role-specialized workflow in which LLM-based AI components, operating in a multi-agent setting with iterative feedback, generate legal scenarios, formal rules, and […]
Beyond Literal Summarization: Redefining Hallucination for Medical SOAP Note Evaluation
arXiv:2604.14829v1 Announce Type: new Abstract: Evaluating large language models (LLMs) for clinical documentation tasks such as SOAP note generation remains challenging. Unlike standard summarization, these tasks require clinical abstraction, normalization of colloquial language, and medically grounded inference. However, prevailing evaluation methods including automated metrics and LLM as judge frameworks rely on lexical faithfulness, often labeling […]
Governing Reflective Human-AI Collaboration: A Framework for Epistemic Scaffolding and Traceable Reasoning
arXiv:2604.14898v1 Announce Type: new Abstract: Large language models have advanced rapidly, from pattern recognition to emerging forms of reasoning, yet they remain confined to linguistic simulation rather than grounded understanding. They can produce fluent outputs that resemble reflection, but lack temporal continuity, causal feedback, and anchoring in real-world interaction. This paper proposes a complementary approach […]
METER: Evaluating Multi-Level Contextual Causal Reasoning in Large Language Models
arXiv:2604.11502v2 Announce Type: replace-cross Abstract: Contextual causal reasoning is a critical yet challenging capability for Large Language Models (LLMs). Existing benchmarks, however, often evaluate this skill in fragmented settings, failing to ensure context consistency or cover the full causal hierarchy. To address this, we pioneer METER to systematically benchmark LLMs across all three levels of […]
CoTEvol: Self-Evolving Chain-of-Thoughts for Data Synthesis in Mathematical Reasoning
arXiv:2604.14768v1 Announce Type: new Abstract: Large Language Models (LLMs) exhibit strong mathematical reasoning when trained on high-quality Chain-of-Thought (CoT) that articulates intermediate steps, yet costly CoT curation hinders further progress. While existing remedies such as distillation from stronger LLMs and self-synthesis based on test-time search alleviate this issue, they often suffer from diminishing returns or […]
Beyond LLMs, Sparse Distributed Memory, and Neuromorphics
arXiv:2604.11665v3 Announce Type: replace-cross Abstract: This paper reports an unexpected finding: in a deterministic hyperdimensional computing (HDC) architecture based on Galois-field algebra, a path-dependent semantic selection mechanism emerges, equivalent to spike-timing-dependent plasticity (STDP), with magnitude predictable a priori by a closed-form expression matching large-scale measurements. This addresses limitations of modern AI including catastrophic forgetting, learning […]