arXiv:2604.18916v3 Announce Type: replace Abstract: In this paper, we introduce a new concept called Artificial Special Intelligence by which Machine Learning models for the classification problem can be trained error-free, thus acquiring the capability of not making repeated mistakes. The method is applied to 18 MedMNIST biomedical datasets. Except for three datasets, which suffer from […]
From Unstructured Recall to Schema-Grounded Memory: Reliable AI Memory via Iterative, Schema-Aware Extraction
arXiv:2604.27906v2 Announce Type: replace Abstract: Persistent AI memory is often reduced to a retrieval problem: store prior interactions as text, embed them, and ask the model to recover relevant context later. This design is useful for thematic recall, but it is mismatched to the kinds of memory that agents need in production: exact facts, current […]
Are Tools All We Need? Unveiling the Tool-Use Tax in LLM Agents
arXiv:2605.00136v1 Announce Type: new Abstract: Tool-augmented reasoning has become a popular direction for LLM-based agents, and it is widely assumed to improve reasoning and reliability. However, we demonstrate that this consensus does not always hold: in the presence of semantic distractors, tool-augmented reasoning does not necessarily outperform native CoT. To explain this performance gap, we […]
Markets with Heterogeneous Agents: Dynamics and Survival of Bayesian vs. No-Regret Learners
arXiv:2502.08597v3 Announce Type: replace-cross Abstract: We analyze the performance of heterogeneous learning agents in asset markets with stochastic payoffs. Our main focus is on comparing Bayesian learners and no-regret learners who compete in markets and identifying the conditions under which each approach is more effective. We formally relate the notions of survival and market dominance […]
Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment
arXiv:2506.00166v2 Announce Type: replace-cross Abstract: Existing paradigms for ensuring AI safety, such as guardrail models and alignment training, often compromise either inference efficiency or development flexibility. We introduce Disentangled Safety Adapters (DSA), a novel framework addressing these challenges by decoupling safety-specific computations from a task-optimized base model. DSA utilizes lightweight adapters that leverage the base […]
Effective LLM Code Refinement via Property-Oriented and Structurally Minimal Feedback
arXiv:2506.18315v2 Announce Type: replace-cross Abstract: LLMs excel at code generation, yet ensuring the functional correctness of their outputs remains a persistent challenge. While recent studies have applied Test-Driven Development (TDD) to refine code, these methods are often undermined by poor feedback quality, stemming from the scarcity of high-quality test cases and noisy signals from auto-generated […]
TUR-DPO: Topology- and Uncertainty-Aware Direct Preference Optimization
arXiv:2605.00224v1 Announce Type: new Abstract: Aligning large language models (LLMs) with human preferences is commonly done via reinforcement learning from human feedback (RLHF) with Proximal Policy Optimization (PPO) or, more simply, via Direct Preference Optimization (DPO). While DPO is stable and RL-free, it treats preferences as flat winner vs. loser signals and is sensitive to […]
AIDA-ReID: Adaptive Intermediate Domain Adaptation for Generalizable and Source-Free Person Re-Identification
arXiv:2605.00111v1 Announce Type: cross Abstract: Person re-identification (Re-ID) aims to match images of the same individual across non-overlapping camera views and remains challenging due to domain shifts caused by variations in illumination, background, camera characteristics, and population distributions. Although supervised models perform well under matched training and testing conditions, their performance degrades significantly when deployed […]
LLM-Oriented Information Retrieval: A Denoising-First Perspective
arXiv:2605.00505v1 Announce Type: cross Abstract: Modern information retrieval (IR) is no longer consumed primarily by humans but increasingly by large language models (LLMs) via retrieval-augmented generation (RAG) and agentic search. Unlike human users, LLMs are constrained by limited attention budgets and are uniquely vulnerable to noise; misleading or irrelevant information is no longer just a […]
Human-in-the-Loop Meta Bayesian Optimization for Fusion Energy and Scientific Applications
arXiv:2605.00068v1 Announce Type: cross Abstract: Inertial Confinement Fusion (ICF) holds transformative promise for sustainable, near-limitless clean energy, yet remains constrained by prohibitively high costs and limited experimental opportunities. This paper presents Human-in-the-Loop Meta Bayesian Optimization (HL-MBO), a framework that integrates expert knowledge with few-shot, uncertainty-aware machine learning to accelerate discovery in data-scarce, high-stakes scientific domains. […]
How Frontier LLMs Adapt to Neurodivergence Context: A Measurement Framework for Surface vs. Structural Change in System-Prompted Responses
arXiv:2605.00113v1 Announce Type: cross Abstract: We examine if frontier chat-based large language models (LLMs) adjust their outputs based on neurodivergence (ND) context in system prompts and describe the nature of these adjustments. Specifically, we propose NDBench, a 576-output benchmark involving two frontier models, three system prompt types (baseline, ND-profile assertion, and ND-profile assertion with explicit […]
“What Are You Really Trying to Do?”: Co-Creating Life Goals from Everyday Computer Use
arXiv:2605.00497v1 Announce Type: cross Abstract: Recent advances in user modeling make it feasible to conduct open-ended inference over a person’s everyday computer use. Despite longstanding visions of systems that deeply understand our actions and the purposes they serve in our lives, existing systems only capture what a person is doing in the moment — not […]